Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - 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.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 326 insertions, 0 deletions

diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
new file mode 100644
index 000000000..e3da4da24
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*******************************************************************************
+  This contains the functions to handle the normal descriptors.
+
+  Copyright (C) 2007-2009  STMicroelectronics Ltd
+
+
+  Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+*******************************************************************************/
+
+#include <linux/stmmac.h>
+#include "common.h"
+#include "descs_com.h"
+
+static int ndesc_get_tx_status(void *data, struct stmmac_extra_stats *x,
+			       struct dma_desc *p, void __iomem *ioaddr)
+{
+	struct net_device_stats *stats = (struct net_device_stats *)data;
+	unsigned int tdes0 = le32_to_cpu(p->des0);
+	unsigned int tdes1 = le32_to_cpu(p->des1);
+	int ret = tx_done;
+
+	/* Get tx owner first */
+	if (unlikely(tdes0 & TDES0_OWN))
+		return tx_dma_own;
+
+	/* Verify tx error by looking at the last segment. */
+	if (likely(!(tdes1 & TDES1_LAST_SEGMENT)))
+		return tx_not_ls;
+
+	if (unlikely(tdes0 & TDES0_ERROR_SUMMARY)) {
+		if (unlikely(tdes0 & TDES0_UNDERFLOW_ERROR)) {
+			x->tx_underflow++;
+			stats->tx_fifo_errors++;
+		}
+		if (unlikely(tdes0 & TDES0_NO_CARRIER)) {
+			x->tx_carrier++;
+			stats->tx_carrier_errors++;
+		}
+		if (unlikely(tdes0 & TDES0_LOSS_CARRIER)) {
+			x->tx_losscarrier++;
+			stats->tx_carrier_errors++;
+		}
+		if (unlikely((tdes0 & TDES0_EXCESSIVE_DEFERRAL) ||
+			     (tdes0 & TDES0_EXCESSIVE_COLLISIONS) ||
+			     (tdes0 & TDES0_LATE_COLLISION))) {
+			unsigned int collisions;
+
+			collisions = (tdes0 & TDES0_COLLISION_COUNT_MASK) >> 3;
+			stats->collisions += collisions;
+		}
+		ret = tx_err;
+	}
+
+	if (tdes0 & TDES0_VLAN_FRAME)
+		x->tx_vlan++;
+
+	if (unlikely(tdes0 & TDES0_DEFERRED))
+		x->tx_deferred++;
+
+	return ret;
+}
+
+static int ndesc_get_tx_len(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des1) & RDES1_BUFFER1_SIZE_MASK);
+}
+
+/* This function verifies if each incoming frame has some errors
+ * and, if required, updates the multicast statistics.
+ * In case of success, it returns good_frame because the GMAC device
+ * is supposed to be able to compute the csum in HW. */
+static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
+			       struct dma_desc *p)
+{
+	int ret = good_frame;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
+	struct net_device_stats *stats = (struct net_device_stats *)data;
+
+	if (unlikely(rdes0 & RDES0_OWN))
+		return dma_own;
+
+	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
+		stats->rx_length_errors++;
+		return discard_frame;
+	}
+
+	if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) {
+		if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR))
+			x->rx_desc++;
+		if (unlikely(rdes0 & RDES0_SA_FILTER_FAIL))
+			x->sa_filter_fail++;
+		if (unlikely(rdes0 & RDES0_OVERFLOW_ERROR))
+			x->overflow_error++;
+		if (unlikely(rdes0 & RDES0_IPC_CSUM_ERROR))
+			x->ipc_csum_error++;
+		if (unlikely(rdes0 & RDES0_COLLISION)) {
+			x->rx_collision++;
+			stats->collisions++;
+		}
+		if (unlikely(rdes0 & RDES0_CRC_ERROR)) {
+			x->rx_crc_errors++;
+			stats->rx_crc_errors++;
+		}
+		ret = discard_frame;
+	}
+	if (unlikely(rdes0 & RDES0_DRIBBLING))
+		x->dribbling_bit++;
+
+	if (unlikely(rdes0 & RDES0_LENGTH_ERROR)) {
+		x->rx_length++;
+		ret = discard_frame;
+	}
+	if (unlikely(rdes0 & RDES0_MII_ERROR)) {
+		x->rx_mii++;
+		ret = discard_frame;
+	}
+#ifdef STMMAC_VLAN_TAG_USED
+	if (rdes0 & RDES0_VLAN_TAG)
+		x->vlan_tag++;
+#endif
+	return ret;
+}
+
+static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
+			       int end, int bfsize)
+{
+	int bfsize1;
+
+	p->des0 |= cpu_to_le32(RDES0_OWN);
+
+	bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1);
+	p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK);
+
+	if (mode == STMMAC_CHAIN_MODE)
+		ndesc_rx_set_on_chain(p, end);
+	else
+		ndesc_rx_set_on_ring(p, end, bfsize);
+
+	if (disable_rx_ic)
+		p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
+}
+
+static void ndesc_init_tx_desc(struct dma_desc *p, int mode, int end)
+{
+	p->des0 &= cpu_to_le32(~TDES0_OWN);
+	if (mode == STMMAC_CHAIN_MODE)
+		ndesc_tx_set_on_chain(p);
+	else
+		ndesc_end_tx_desc_on_ring(p, end);
+}
+
+static int ndesc_get_tx_owner(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des0) & TDES0_OWN) >> 31;
+}
+
+static void ndesc_set_tx_owner(struct dma_desc *p)
+{
+	p->des0 |= cpu_to_le32(TDES0_OWN);
+}
+
+static void ndesc_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
+{
+	p->des0 |= cpu_to_le32(RDES0_OWN);
+}
+
+static int ndesc_get_tx_ls(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des1) & TDES1_LAST_SEGMENT) >> 30;
+}
+
+static void ndesc_release_tx_desc(struct dma_desc *p, int mode)
+{
+	int ter = (le32_to_cpu(p->des1) & TDES1_END_RING) >> 25;
+
+	memset(p, 0, offsetof(struct dma_desc, des2));
+	if (mode == STMMAC_CHAIN_MODE)
+		ndesc_tx_set_on_chain(p);
+	else
+		ndesc_end_tx_desc_on_ring(p, ter);
+}
+
+static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
+				  bool csum_flag, int mode, bool tx_own,
+				  bool ls, unsigned int tot_pkt_len)
+{
+	unsigned int tdes1 = le32_to_cpu(p->des1);
+
+	if (is_fs)
+		tdes1 |= TDES1_FIRST_SEGMENT;
+	else
+		tdes1 &= ~TDES1_FIRST_SEGMENT;
+
+	if (likely(csum_flag))
+		tdes1 |= (TX_CIC_FULL) << TDES1_CHECKSUM_INSERTION_SHIFT;
+	else
+		tdes1 &= ~(TX_CIC_FULL << TDES1_CHECKSUM_INSERTION_SHIFT);
+
+	if (ls)
+		tdes1 |= TDES1_LAST_SEGMENT;
+
+	p->des1 = cpu_to_le32(tdes1);
+
+	if (mode == STMMAC_CHAIN_MODE)
+		norm_set_tx_desc_len_on_chain(p, len);
+	else
+		norm_set_tx_desc_len_on_ring(p, len);
+
+	if (tx_own)
+		p->des0 |= cpu_to_le32(TDES0_OWN);
+}
+
+static void ndesc_set_tx_ic(struct dma_desc *p)
+{
+	p->des1 |= cpu_to_le32(TDES1_INTERRUPT);
+}
+
+static int ndesc_get_rx_frame_len(struct dma_desc *p, int rx_coe_type)
+{
+	unsigned int csum = 0;
+
+	/* The type-1 checksum offload engines append the checksum at
+	 * the end of frame and the two bytes of checksum are added in
+	 * the length.
+	 * Adjust for that in the framelen for type-1 checksum offload
+	 * engines
+	 */
+	if (rx_coe_type == STMMAC_RX_COE_TYPE1)
+		csum = 2;
+
+	return (((le32_to_cpu(p->des0) & RDES0_FRAME_LEN_MASK)
+				>> RDES0_FRAME_LEN_SHIFT) -
+		csum);
+
+}
+
+static void ndesc_enable_tx_timestamp(struct dma_desc *p)
+{
+	p->des1 |= cpu_to_le32(TDES1_TIME_STAMP_ENABLE);
+}
+
+static int ndesc_get_tx_timestamp_status(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des0) & TDES0_TIME_STAMP_STATUS) >> 17;
+}
+
+static void ndesc_get_timestamp(void *desc, u32 ats, u64 *ts)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	u64 ns;
+
+	ns = le32_to_cpu(p->des2);
+	/* convert high/sec time stamp value to nanosecond */
+	ns += le32_to_cpu(p->des3) * 1000000000ULL;
+
+	*ts = ns;
+}
+
+static int ndesc_get_rx_timestamp_status(void *desc, void *next_desc, u32 ats)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+
+	if ((le32_to_cpu(p->des2) == 0xffffffff) &&
+	    (le32_to_cpu(p->des3) == 0xffffffff))
+		/* timestamp is corrupted, hence don't store it */
+		return 0;
+	else
+		return 1;
+}
+
+static void ndesc_display_ring(void *head, unsigned int size, bool rx,
+			       dma_addr_t dma_rx_phy, unsigned int desc_size)
+{
+	struct dma_desc *p = (struct dma_desc *)head;
+	dma_addr_t dma_addr;
+	int i;
+
+	pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
+
+	for (i = 0; i < size; i++) {
+		u64 x;
+		dma_addr = dma_rx_phy + i * sizeof(*p);
+
+		x = *(u64 *)p;
+		pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x",
+			i, &dma_addr,
+			(unsigned int)x, (unsigned int)(x >> 32),
+			p->des2, p->des3);
+		p++;
+	}
+	pr_info("\n");
+}
+
+static void ndesc_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des2 = cpu_to_le32(addr);
+}
+
+static void ndesc_clear(struct dma_desc *p)
+{
+	p->des2 = 0;
+}
+
+const struct stmmac_desc_ops ndesc_ops = {
+	.tx_status = ndesc_get_tx_status,
+	.rx_status = ndesc_get_rx_status,
+	.get_tx_len = ndesc_get_tx_len,
+	.init_rx_desc = ndesc_init_rx_desc,
+	.init_tx_desc = ndesc_init_tx_desc,
+	.get_tx_owner = ndesc_get_tx_owner,
+	.release_tx_desc = ndesc_release_tx_desc,
+	.prepare_tx_desc = ndesc_prepare_tx_desc,
+	.set_tx_ic = ndesc_set_tx_ic,
+	.get_tx_ls = ndesc_get_tx_ls,
+	.set_tx_owner = ndesc_set_tx_owner,
+	.set_rx_owner = ndesc_set_rx_owner,
+	.get_rx_frame_len = ndesc_get_rx_frame_len,
+	.enable_tx_timestamp = ndesc_enable_tx_timestamp,
+	.get_tx_timestamp_status = ndesc_get_tx_timestamp_status,
+	.get_timestamp = ndesc_get_timestamp,
+	.get_rx_timestamp_status = ndesc_get_rx_timestamp_status,
+	.display_ring = ndesc_display_ring,
+	.set_addr = ndesc_set_addr,
+	.clear = ndesc_clear,
+};