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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-12-18

This PR is larger than usual and contains changes in various parts
of the kernel.

The main changes are:

1) Fix kCFI bugs in BPF, from Peter Zijlstra.

End result: all forms of indirect calls from BPF into kernel
and from kernel into BPF work with CFI enabled. This allows BPF
to work with CONFIG_FINEIBT=y.

2) Introduce BPF token object, from Andrii Nakryiko.

It adds an ability to delegate a subset of BPF features from privileged
daemon (e.g., systemd) through special mount options for userns-bound
BPF FS to a trusted unprivileged application. The design accommodates
suggestions from Christian Brauner and Paul Moore.

Example:
$ sudo mkdir -p /sys/fs/bpf/token
$ sudo mount -t bpf bpffs /sys/fs/bpf/token \
             -o delegate_cmds=prog_load:MAP_CREATE \
             -o delegate_progs=kprobe \
             -o delegate_attachs=xdp

3) Various verifier improvements and fixes, from Andrii Nakryiko, Andrei Matei.

 - Complete precision tracking support for register spills
 - Fix verification of possibly-zero-sized stack accesses
 - Fix access to uninit stack slots
 - Track aligned STACK_ZERO cases as imprecise spilled registers.
   It improves the verifier "instructions processed" metric from single
   digit to 50-60% for some programs.
 - Fix verifier retval logic

4) Support for VLAN tag in XDP hints, from Larysa Zaremba.

5) Allocate BPF trampoline via bpf_prog_pack mechanism, from Song Liu.

End result: better memory utilization and lower I$ miss for calls to BPF
via BPF trampoline.

6) Fix race between BPF prog accessing inner map and parallel delete,
from Hou Tao.

7) Add bpf_xdp_get_xfrm_state() kfunc, from Daniel Xu.

It allows BPF interact with IPSEC infra. The intent is to support
software RSS (via XDP) for the upcoming ipsec pcpu work.
Experiments on AWS demonstrate single tunnel pcpu ipsec reaching
line rate on 100G ENA nics.

8) Expand bpf_cgrp_storage to support cgroup1 non-attach, from Yafang Shao.

9) BPF file verification via fsverity, from Song Liu.

It allows BPF progs get fsverity digest.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (164 commits)
  bpf: Ensure precise is reset to false in __mark_reg_const_zero()
  selftests/bpf: Add more uprobe multi fail tests
  bpf: Fail uprobe multi link with negative offset
  selftests/bpf: Test the release of map btf
  s390/bpf: Fix indirect trampoline generation
  selftests/bpf: Temporarily disable dummy_struct_ops test on s390
  x86/cfi,bpf: Fix bpf_exception_cb() signature
  bpf: Fix dtor CFI
  cfi: Add CFI_NOSEAL()
  x86/cfi,bpf: Fix bpf_struct_ops CFI
  x86/cfi,bpf: Fix bpf_callback_t CFI
  x86/cfi,bpf: Fix BPF JIT call
  cfi: Flip headers
  selftests/bpf: Add test for abnormal cnt during multi-kprobe attachment
  selftests/bpf: Don't use libbpf_get_error() in kprobe_multi_test
  selftests/bpf: Add test for abnormal cnt during multi-uprobe attachment
  bpf: Limit the number of kprobes when attaching program to multiple kprobes
  bpf: Limit the number of uprobes when attaching program to multiple uprobes
  bpf: xdp: Register generic_kfunc_set with XDP programs
  selftests/bpf: utilize string values for delegate_xxx mount options
  ...
====================

Link: https://lore.kernel.org/r/20231219000520.34178-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 184 insertions, 23 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 7e06373e14d9..839e5da24ad5 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -63,28 +63,42 @@ static enum pkt_hash_types ice_ptype_to_htype(u16 ptype)
 }
 
 /**
- * ice_rx_hash - set the hash value in the skb
+ * ice_get_rx_hash - get RX hash value from descriptor
+ * @rx_desc: specific descriptor
+ *
+ * Returns hash, if present, 0 otherwise.
+ */
+static u32 ice_get_rx_hash(const union ice_32b_rx_flex_desc *rx_desc)
+{
+	const struct ice_32b_rx_flex_desc_nic *nic_mdid;
+
+	if (unlikely(rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC))
+		return 0;
+
+	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+	return le32_to_cpu(nic_mdid->rss_hash);
+}
+
+/**
+ * ice_rx_hash_to_skb - set the hash value in the skb
  * @rx_ring: descriptor ring
  * @rx_desc: specific descriptor
  * @skb: pointer to current skb
  * @rx_ptype: the ptype value from the descriptor
  */
 static void
-ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
-	    struct sk_buff *skb, u16 rx_ptype)
+ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
+		   const union ice_32b_rx_flex_desc *rx_desc,
+		   struct sk_buff *skb, u16 rx_ptype)
 {
-	struct ice_32b_rx_flex_desc_nic *nic_mdid;
 	u32 hash;
 
 	if (!(rx_ring->netdev->features & NETIF_F_RXHASH))
 		return;
 
-	if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)
-		return;
-
-	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
-	hash = le32_to_cpu(nic_mdid->rss_hash);
-	skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
+	hash = ice_get_rx_hash(rx_desc);
+	if (likely(hash))
+		skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
 }
 
 /**
@@ -171,11 +185,38 @@ checksum_fail:
 }
 
 /**
+ * ice_ptp_rx_hwts_to_skb - Put RX timestamp into skb
+ * @rx_ring: Ring to get the VSI info
+ * @rx_desc: Receive descriptor
+ * @skb: Particular skb to send timestamp with
+ *
+ * The timestamp is in ns, so we must convert the result first.
+ */
+static void
+ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring,
+		       const union ice_32b_rx_flex_desc *rx_desc,
+		       struct sk_buff *skb)
+{
+	u64 ts_ns = ice_ptp_get_rx_hwts(rx_desc, &rx_ring->pkt_ctx);
+
+	skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ts_ns);
+}
+
+/**
+ * ice_get_ptype - Read HW packet type from the descriptor
+ * @rx_desc: RX descriptor
+ */
+static u16 ice_get_ptype(const union ice_32b_rx_flex_desc *rx_desc)
+{
+	return le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
+	       ICE_RX_FLEX_DESC_PTYPE_M;
+}
+
+/**
  * ice_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: Rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @ptype: the packet type decoded by hardware
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
@@ -184,9 +225,11 @@ checksum_fail:
 void
 ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u16 ptype)
+		       struct sk_buff *skb)
 {
-	ice_rx_hash(rx_ring, rx_desc, skb, ptype);
+	u16 ptype = ice_get_ptype(rx_desc);
+
+	ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype);
 
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
@@ -194,28 +237,24 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
 
 	if (rx_ring->ptp_rx)
-		ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
+		ice_ptp_rx_hwts_to_skb(rx_ring, rx_desc, skb);
 }
 
 /**
  * ice_receive_skb - Send a completed packet up the stack
  * @rx_ring: Rx ring in play
  * @skb: packet to send up
- * @vlan_tag: VLAN tag for packet
+ * @vlan_tci: VLAN TCI for packet
  *
  * This function sends the completed packet (via. skb) up the stack using
  * gro receive functions (with/without VLAN tag)
  */
 void
-ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag)
+ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci)
 {
-	netdev_features_t features = rx_ring->netdev->features;
-	bool non_zero_vlan = !!(vlan_tag & VLAN_VID_MASK);
-
-	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && non_zero_vlan)
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
-	else if ((features & NETIF_F_HW_VLAN_STAG_RX) && non_zero_vlan)
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), vlan_tag);
+	if ((vlan_tci & VLAN_VID_MASK) && rx_ring->vlan_proto)
+		__vlan_hwaccel_put_tag(skb, rx_ring->vlan_proto,
+				       vlan_tci);
 
 	napi_gro_receive(&rx_ring->q_vector->napi, skb);
 }
@@ -464,3 +503,125 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
 			spin_unlock(&xdp_ring->tx_lock);
 	}
 }
+
+/**
+ * ice_xdp_rx_hw_ts - HW timestamp XDP hint handler
+ * @ctx: XDP buff pointer
+ * @ts_ns: destination address
+ *
+ * Copy HW timestamp (if available) to the destination address.
+ */
+static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc,
+				     xdp_ext->pkt_ctx);
+	if (!*ts_ns)
+		return -ENODATA;
+
+	return 0;
+}
+
+/* Define a ptype index -> XDP hash type lookup table.
+ * It uses the same ptype definitions as ice_decode_rx_desc_ptype[],
+ * avoiding possible copy-paste errors.
+ */
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+	[PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL
+
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0
+
+/* A few supplementary definitions for when XDP hash types do not coincide
+ * with what can be generated from ptype definitions
+ * by means of preprocessor concatenation.
+ */
+#define XDP_RSS_L3_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY2	XDP_RSS_TYPE_L2
+#define XDP_RSS_TYPE_PAY3	XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY4	XDP_RSS_L4
+
+static const enum xdp_rss_hash_type
+ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
+	ICE_PTYPES
+};
+
+#undef XDP_RSS_L3_NONE
+#undef XDP_RSS_L4_NONE
+#undef XDP_RSS_TYPE_PAY2
+#undef XDP_RSS_TYPE_PAY3
+#undef XDP_RSS_TYPE_PAY4
+
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+/**
+ * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor
+ * @eop_desc: End of Packet descriptor
+ */
+static enum xdp_rss_hash_type
+ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc)
+{
+	u16 ptype = ice_get_ptype(eop_desc);
+
+	if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES))
+		return 0;
+
+	return ice_ptype_to_xdp_hash[ptype];
+}
+
+/**
+ * ice_xdp_rx_hash - RX hash XDP hint handler
+ * @ctx: XDP buff pointer
+ * @hash: hash destination address
+ * @rss_type: XDP hash type destination address
+ *
+ * Copy RX hash (if available) and its type to the destination address.
+ */
+static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*hash = ice_get_rx_hash(xdp_ext->eop_desc);
+	*rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc);
+	if (!likely(*hash))
+		return -ENODATA;
+
+	return 0;
+}
+
+/**
+ * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler
+ * @ctx: XDP buff pointer
+ * @vlan_proto: destination address for VLAN protocol
+ * @vlan_tci: destination address for VLAN TCI
+ *
+ * Copy VLAN tag (if was stripped) and corresponding protocol
+ * to the destination address.
+ */
+static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto,
+			       u16 *vlan_tci)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*vlan_proto = xdp_ext->pkt_ctx->vlan_proto;
+	if (!*vlan_proto)
+		return -ENODATA;
+
+	*vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc);
+	if (!*vlan_tci)
+		return -ENODATA;
+
+	return 0;
+}
+
+const struct xdp_metadata_ops ice_xdp_md_ops = {
+	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
+	.xmo_rx_hash			= ice_xdp_rx_hash,
+	.xmo_rx_vlan_tag		= ice_xdp_rx_vlan_tag,
+};