Merge tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core & protocols:

   - Continue Netlink conversions to per-namespace RTNL lock
     (IPv4 routing, routing rules, routing next hops, ARP ioctls)

   - Continue extending the use of netdev instance locks. As a driver
     opt-in protect queue operations and (in due course) ethtool
     operations with the instance lock and not RTNL lock.

   - Support collecting TCP timestamps (data submitted, sent, acked) in
     BPF, allowing for transparent (to the application) and lower
     overhead tracking of TCP RPC performance.

   - Tweak existing networking Rx zero-copy infra to support zero-copy
     Rx via io_uring.

   - Optimize MPTCP performance in single subflow mode by 29%.

   - Enable GRO on packets which went thru XDP CPU redirect (were queued
     for processing on a different CPU). Improving TCP stream
     performance up to 2x.

   - Improve performance of contended connect() by 200% by searching for
     an available 4-tuple under RCU rather than a spin lock. Bring an
     additional 229% improvement by tweaking hash distribution.

   - Avoid unconditionally touching sk_tsflags on RX, improving
     performance under UDP flood by as much as 10%.

   - Avoid skb_clone() dance in ping_rcv() to improve performance under
     ping flood.

   - Avoid FIB lookup in netfilter if socket is available, 20% perf win.

   - Rework network device creation (in-kernel) API to more clearly
     identify network namespaces and their roles. There are up to 4
     namespace roles but we used to have just 2 netns pointer arguments,
     interpreted differently based on context.

   - Use sysfs_break_active_protection() instead of trylock to avoid
     deadlocks between unregistering objects and sysfs access.

   - Add a new sysctl and sockopt for capping max retransmit timeout in
     TCP.

   - Support masking port and DSCP in routing rule matches.

   - Support dumping IPv4 multicast addresses with RTM_GETMULTICAST.

   - Support specifying at what time packet should be sent on AF_XDP
     sockets.

   - Expose TCP ULP diagnostic info (for TLS and MPTCP) to non-admin
     users.

   - Add Netlink YAML spec for WiFi (nl80211) and conntrack.

   - Introduce EXPORT_IPV6_MOD() and EXPORT_IPV6_MOD_GPL() for symbols
     which only need to be exported when IPv6 support is built as a
     module.

   - Age FDB entries based on Rx not Tx traffic in VxLAN, similar to
     normal bridging.

   - Allow users to specify source port range for GENEVE tunnels.

   - netconsole: allow attaching kernel release, CPU ID and task name to
     messages as metadata

  Driver API:

   - Continue rework / fixing of Energy Efficient Ethernet (EEE) across
     the SW layers. Delegate the responsibilities to phylink where
     possible. Improve its handling in phylib.

   - Support symmetric OR-XOR RSS hashing algorithm.

   - Support tracking and preserving IRQ affinity by NAPI itself.

   - Support loopback mode speed selection for interface selftests.

  Device drivers:

   - Remove the IBM LCS driver for s390

   - Remove the sb1000 cable modem driver

   - Add support for SFP module access over SMBus

   - Add MCTP transport driver for MCTP-over-USB

   - Enable XDP metadata support in multiple drivers

   - Ethernet high-speed NICs:
      - Broadcom (bnxt):
         - add PCIe TLP Processing Hints (TPH) support for new AMD
           platforms
         - support dumping RoCE queue state for debug
         - opt into instance locking
      - Intel (100G, ice, idpf):
         - ice: rework MSI-X IRQ management and distribution
         - ice: support for E830 devices
         - iavf: add support for Rx timestamping
         - iavf: opt into instance locking
      - nVidia/Mellanox:
         - mlx4: use page pool memory allocator for Rx
         - mlx5: support for one PTP device per hardware clock
         - mlx5: support for 200Gbps per-lane link modes
         - mlx5: move IPSec policy check after decryption
      - AMD/Solarflare:
         - support FW flashing via devlink
      - Cisco (enic):
         - use page pool memory allocator for Rx
         - enable 32, 64 byte CQEs
         - get max rx/tx ring size from the device
      - Meta (fbnic):
         - support flow steering and RSS configuration
         - report queue stats
         - support TCP segmentation
         - support IRQ coalescing
         - support ring size configuration
      - Marvell/Cavium:
         - support AF_XDP
      - Wangxun:
         - support for PTP clock and timestamping
      - Huawei (hibmcge):
         - checksum offload
         - add more statistics

   - Ethernet virtual:
      - VirtIO net:
         - aggressively suppress Tx completions, improve perf by 96%
           with 1 CPU and 55% with 2 CPUs
         - expose NAPI to IRQ mapping and persist NAPI settings
      - Google (gve):
         - support XDP in DQO RDA Queue Format
         - opt into instance locking
      - Microsoft vNIC:
         - support BIG TCP

   - Ethernet NICs consumer, and embedded:
      - Synopsys (stmmac):
         - cleanup Tx and Tx clock setting and other link-focused
           cleanups
         - enable SGMII and 2500BASEX mode switching for Intel platforms
         - support Sophgo SG2044
      - Broadcom switches (b53):
         - support for BCM53101
      - TI:
         - iep: add perout configuration support
         - icssg: support XDP
      - Cadence (macb):
         - implement BQL
      - Xilinx (axinet):
         - support dynamic IRQ moderation and changing coalescing at
           runtime
         - implement BQL
         - report standard stats
      - MediaTek:
         - support phylink managed EEE
      - Intel:
         - igc: don't restart the interface on every XDP program change
      - RealTek (r8169):
         - support reading registers of internal PHYs directly
         - increase max jumbo packet size on RTL8125/RTL8126
      - Airoha:
         - support for RISC-V NPU packet processing unit
         - enable scatter-gather and support MTU up to 9kB
      - Tehuti (tn40xx):
         - support cards with TN4010 MAC and an Aquantia AQR105 PHY

   - Ethernet PHYs:
      - support for TJA1102S, TJA1121
      - dp83tg720: add randomized polling intervals for link detection
      - dp83822: support changing the transmit amplitude voltage
      - support for LEDs on 88q2xxx

   - CAN:
      - canxl: support Remote Request Substitution bit access
      - flexcan: add S32G2/S32G3 SoC

   - WiFi:
      - remove cooked monitor support
      - strict mode for better AP testing
      - basic EPCS support
      - OMI RX bandwidth reduction support
      - batman-adv: add support for jumbo frames

   - WiFi drivers:
      - RealTek (rtw88):
         - support RTL8814AE and RTL8814AU
      - RealTek (rtw89):
         - switch using wiphy_lock and wiphy_work
         - add BB context to manipulate two PHY as preparation of MLO
         - improve BT-coexistence mechanism to play A2DP smoothly
      - Intel (iwlwifi):
         - add new iwlmld sub-driver for latest HW/FW combinations
      - MediaTek (mt76):
         - preparation for mt7996 Multi-Link Operation (MLO) support
      - Qualcomm/Atheros (ath12k):
         - continued work on MLO
      - Silabs (wfx):
         - Wake-on-WLAN support

   - Bluetooth:
      - add support for skb TX SND/COMPLETION timestamping
      - hci_core: enable buffer flow control for SCO/eSCO
      - coredump: log devcd dumps into the monitor

   - Bluetooth drivers:
      - intel: add support to configure TX power
      - nxp: handle bootloader error during cmd5 and cmd7"

* tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1681 commits)
  unix: fix up for "apparmor: add fine grained af_unix mediation"
  mctp: Fix incorrect tx flow invalidation condition in mctp-i2c
  net: usb: asix: ax88772: Increase phy_name size
  net: phy: Introduce PHY_ID_SIZE — minimum size for PHY ID string
  net: libwx: fix Tx L4 checksum
  net: libwx: fix Tx descriptor content for some tunnel packets
  atm: Fix NULL pointer dereference
  net: tn40xx: add pci-id of the aqr105-based Tehuti TN4010 cards
  net: tn40xx: prepare tn40xx driver to find phy of the TN9510 card
  net: tn40xx: create swnode for mdio and aqr105 phy and add to mdiobus
  net: phy: aquantia: add essential functions to aqr105 driver
  net: phy: aquantia: search for firmware-name in fwnode
  net: phy: aquantia: add probe function to aqr105 for firmware loading
  net: phy: Add swnode support to mdiobus_scan
  gve: add XDP DROP and PASS support for DQ
  gve: update XDP allocation path support RX buffer posting
  gve: merge packet buffer size fields
  gve: update GQ RX to use buf_size
  gve: introduce config-based allocation for XDP
  gve: remove xdp_xsk_done and xdp_xsk_wakeup statistics
  ...

1 files changed, 107 insertions, 12 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index ff4ad788d96a..7c3006eb68dd 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS;
 
+	if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP;
+
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
@@ -562,7 +565,7 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
  *
  * check for the valid queue ID
  */
-static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid)
+static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid)
 {
 	/* allocated Tx and Rx queues should be always equal for VF VSI */
 	return qid < vsi->alloc_txq;
@@ -1862,15 +1865,33 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
 
 	for (i = 0; i < qbw->num_queues; i++) {
 		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.peak > vf->max_tx_rate)
+		    qbw->cfg[i].shaper.peak > vf->max_tx_rate) {
 			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
 				 qbw->cfg[i].queue_id, vf->vf_id,
 				 vf->max_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
 		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.committed < vf->min_tx_rate)
+		    qbw->cfg[i].shaper.committed < vf->min_tx_rate) {
 			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
 				 qbw->cfg[i].queue_id, vf->vf_id,
-				 vf->max_tx_rate);
+				 vf->min_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].queue_id > vf->num_vf_qs) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
 	}
 
 	for (i = 0; i < qbw->num_queues; i++) {
@@ -1900,13 +1921,21 @@ err:
  */
 static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 {
+	u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i;
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	u16 quanta_prof_id, quanta_size, start_qid, end_qid, i;
 	struct virtchnl_quanta_cfg *qquanta =
 		(struct virtchnl_quanta_cfg *)msg;
 	struct ice_vsi *vsi;
 	int ret;
 
+	start_qid = qquanta->queue_select.start_queue_id;
+	num_queues = qquanta->queue_select.num_queues;
+
+	if (check_add_overflow(start_qid, num_queues, &end_qid)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto err;
@@ -1918,8 +1947,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	end_qid = qquanta->queue_select.start_queue_id +
-		  qquanta->queue_select.num_queues;
 	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
 	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
 		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
@@ -1948,7 +1975,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	start_qid = qquanta->queue_select.start_queue_id;
 	for (i = start_qid; i < end_qid; i++)
 		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
 
@@ -1975,6 +2001,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	struct ice_vsi *vsi;
 	u8 act_prt, pri_prt;
 	int i = -1, q_idx;
+	bool ena_ts;
 
 	lag = pf->lag;
 	mutex_lock(&pf->lag_mutex);
@@ -2104,9 +2131,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 				rxdid = ICE_RXDID_LEGACY_1;
 			}
 
+			ena_ts = ((vf->driver_caps &
+				  VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) &&
+				  (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) &&
+				  (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP));
+
 			ice_write_qrxflxp_cntxt(&vsi->back->hw,
-						vsi->rxq_map[q_idx],
-						rxdid, 0x03, false);
+						vsi->rxq_map[q_idx], rxdid,
+						ICE_RXDID_PRIO, ena_ts);
 		}
 	}
 
@@ -3031,8 +3063,8 @@ err:
 static int ice_vc_query_rxdid(struct ice_vf *vf)
 {
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_supported_rxdids rxdid = {};
 	struct ice_pf *pf = vf->pf;
+	u64 rxdid;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -3044,7 +3076,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf)
 		goto err;
 	}
 
-	rxdid.supported_rxdids = pf->supported_rxdids;
+	rxdid = pf->supported_rxdids;
 
 err:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
@@ -4092,6 +4124,59 @@ out:
 				     v_ret, NULL, 0);
 }
 
+static int ice_vc_get_ptp_cap(struct ice_vf *vf,
+			      const struct virtchnl_ptp_caps *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP |
+		   VIRTCHNL_1588_PTP_CAP_READ_PHC;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	if (msg->caps & caps)
+		vf->ptp_caps = caps;
+
+err:
+	/* send the response back to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret,
+				     (u8 *)&vf->ptp_caps,
+				     sizeof(struct virtchnl_ptp_caps));
+}
+
+static int ice_vc_get_phc_time(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	struct virtchnl_phc_time *phc_time = NULL;
+	struct ice_pf *pf = vf->pf;
+	u32 len = 0;
+	int ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL);
+	if (!phc_time) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		goto err;
+	}
+
+	len = sizeof(*phc_time);
+
+	phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL);
+
+err:
+	/* send the response back to the VF */
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret,
+				    (u8 *)phc_time, len);
+	kfree(phc_time);
+	return ret;
+}
+
 static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_ver_msg = ice_vc_get_ver_msg,
 	.get_vf_res_msg = ice_vc_get_vf_res_msg,
@@ -4128,6 +4213,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 	/* If you add a new op here please make sure to add it to
 	 * ice_virtchnl_repr_ops as well.
 	 */
@@ -4264,6 +4351,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 };
 
 /**
@@ -4501,6 +4590,12 @@ error_handler:
 	case VIRTCHNL_OP_CONFIG_QUANTA:
 		err = ops->cfg_q_quanta(vf, msg);
 		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		err = ops->get_ptp_cap(vf, (const void *)msg);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		err = ops->get_phc_time(vf);
+		break;
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
 		dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,