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, 324 insertions, 0 deletions

diff --git a/drivers/edac/octeon_edac-lmc.c b/drivers/edac/octeon_edac-lmc.c
new file mode 100644
index 000000000..aeb222ca3
--- /dev/null
+++ b/drivers/edac/octeon_edac-lmc.c
@@ -0,0 +1,324 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2009 Wind River Systems,
+ *   written by Ralf Baechle <ralf@linux-mips.org>
+ *
+ * Copyright (c) 2013 by Cisco Systems, Inc.
+ * All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/edac.h>
+#include <linux/ctype.h>
+
+#include <asm/octeon/octeon.h>
+#include <asm/octeon/cvmx-lmcx-defs.h>
+
+#include "edac_module.h"
+
+#define OCTEON_MAX_MC 4
+
+#define to_mci(k) container_of(k, struct mem_ctl_info, dev)
+
+struct octeon_lmc_pvt {
+	unsigned long inject;
+	unsigned long error_type;
+	unsigned long dimm;
+	unsigned long rank;
+	unsigned long bank;
+	unsigned long row;
+	unsigned long col;
+};
+
+static void octeon_lmc_edac_poll(struct mem_ctl_info *mci)
+{
+	union cvmx_lmcx_mem_cfg0 cfg0;
+	bool do_clear = false;
+	char msg[64];
+
+	cfg0.u64 = cvmx_read_csr(CVMX_LMCX_MEM_CFG0(mci->mc_idx));
+	if (cfg0.s.sec_err || cfg0.s.ded_err) {
+		union cvmx_lmcx_fadr fadr;
+		fadr.u64 = cvmx_read_csr(CVMX_LMCX_FADR(mci->mc_idx));
+		snprintf(msg, sizeof(msg),
+			 "DIMM %d rank %d bank %d row %d col %d",
+			 fadr.cn30xx.fdimm, fadr.cn30xx.fbunk,
+			 fadr.cn30xx.fbank, fadr.cn30xx.frow, fadr.cn30xx.fcol);
+	}
+
+	if (cfg0.s.sec_err) {
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0,
+				     -1, -1, -1, msg, "");
+		cfg0.s.sec_err = -1;	/* Done, re-arm */
+		do_clear = true;
+	}
+
+	if (cfg0.s.ded_err) {
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0,
+				     -1, -1, -1, msg, "");
+		cfg0.s.ded_err = -1;	/* Done, re-arm */
+		do_clear = true;
+	}
+	if (do_clear)
+		cvmx_write_csr(CVMX_LMCX_MEM_CFG0(mci->mc_idx), cfg0.u64);
+}
+
+static void octeon_lmc_edac_poll_o2(struct mem_ctl_info *mci)
+{
+	struct octeon_lmc_pvt *pvt = mci->pvt_info;
+	union cvmx_lmcx_int int_reg;
+	bool do_clear = false;
+	char msg[64];
+
+	if (!pvt->inject)
+		int_reg.u64 = cvmx_read_csr(CVMX_LMCX_INT(mci->mc_idx));
+	else {
+		int_reg.u64 = 0;
+		if (pvt->error_type == 1)
+			int_reg.s.sec_err = 1;
+		if (pvt->error_type == 2)
+			int_reg.s.ded_err = 1;
+	}
+
+	if (int_reg.s.sec_err || int_reg.s.ded_err) {
+		union cvmx_lmcx_fadr fadr;
+		if (likely(!pvt->inject))
+			fadr.u64 = cvmx_read_csr(CVMX_LMCX_FADR(mci->mc_idx));
+		else {
+			fadr.cn61xx.fdimm = pvt->dimm;
+			fadr.cn61xx.fbunk = pvt->rank;
+			fadr.cn61xx.fbank = pvt->bank;
+			fadr.cn61xx.frow = pvt->row;
+			fadr.cn61xx.fcol = pvt->col;
+		}
+		snprintf(msg, sizeof(msg),
+			 "DIMM %d rank %d bank %d row %d col %d",
+			 fadr.cn61xx.fdimm, fadr.cn61xx.fbunk,
+			 fadr.cn61xx.fbank, fadr.cn61xx.frow, fadr.cn61xx.fcol);
+	}
+
+	if (int_reg.s.sec_err) {
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0,
+				     -1, -1, -1, msg, "");
+		int_reg.s.sec_err = -1;	/* Done, re-arm */
+		do_clear = true;
+	}
+
+	if (int_reg.s.ded_err) {
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0,
+				     -1, -1, -1, msg, "");
+		int_reg.s.ded_err = -1;	/* Done, re-arm */
+		do_clear = true;
+	}
+
+	if (do_clear) {
+		if (likely(!pvt->inject))
+			cvmx_write_csr(CVMX_LMCX_INT(mci->mc_idx), int_reg.u64);
+		else
+			pvt->inject = 0;
+	}
+}
+
+/************************ MC SYSFS parts ***********************************/
+
+/* Only a couple naming differences per template, so very similar */
+#define TEMPLATE_SHOW(reg)						\
+static ssize_t octeon_mc_inject_##reg##_show(struct device *dev,	\
+			       struct device_attribute *attr,		\
+			       char *data)				\
+{									\
+	struct mem_ctl_info *mci = to_mci(dev);				\
+	struct octeon_lmc_pvt *pvt = mci->pvt_info;			\
+	return sprintf(data, "%016llu\n", (u64)pvt->reg);		\
+}
+
+#define TEMPLATE_STORE(reg)						\
+static ssize_t octeon_mc_inject_##reg##_store(struct device *dev,	\
+			       struct device_attribute *attr,		\
+			       const char *data, size_t count)		\
+{									\
+	struct mem_ctl_info *mci = to_mci(dev);				\
+	struct octeon_lmc_pvt *pvt = mci->pvt_info;			\
+	if (isdigit(*data)) {						\
+		if (!kstrtoul(data, 0, &pvt->reg))			\
+			return count;					\
+	}								\
+	return 0;							\
+}
+
+TEMPLATE_SHOW(inject);
+TEMPLATE_STORE(inject);
+TEMPLATE_SHOW(dimm);
+TEMPLATE_STORE(dimm);
+TEMPLATE_SHOW(bank);
+TEMPLATE_STORE(bank);
+TEMPLATE_SHOW(rank);
+TEMPLATE_STORE(rank);
+TEMPLATE_SHOW(row);
+TEMPLATE_STORE(row);
+TEMPLATE_SHOW(col);
+TEMPLATE_STORE(col);
+
+static ssize_t octeon_mc_inject_error_type_store(struct device *dev,
+					  struct device_attribute *attr,
+					  const char *data,
+					  size_t count)
+{
+	struct mem_ctl_info *mci = to_mci(dev);
+	struct octeon_lmc_pvt *pvt = mci->pvt_info;
+
+	if (!strncmp(data, "single", 6))
+		pvt->error_type = 1;
+	else if (!strncmp(data, "double", 6))
+		pvt->error_type = 2;
+
+	return count;
+}
+
+static ssize_t octeon_mc_inject_error_type_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *data)
+{
+	struct mem_ctl_info *mci = to_mci(dev);
+	struct octeon_lmc_pvt *pvt = mci->pvt_info;
+	if (pvt->error_type == 1)
+		return sprintf(data, "single");
+	else if (pvt->error_type == 2)
+		return sprintf(data, "double");
+
+	return 0;
+}
+
+static DEVICE_ATTR(inject, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_inject_show, octeon_mc_inject_inject_store);
+static DEVICE_ATTR(error_type, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_error_type_show, octeon_mc_inject_error_type_store);
+static DEVICE_ATTR(dimm, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_dimm_show, octeon_mc_inject_dimm_store);
+static DEVICE_ATTR(rank, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_rank_show, octeon_mc_inject_rank_store);
+static DEVICE_ATTR(bank, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_bank_show, octeon_mc_inject_bank_store);
+static DEVICE_ATTR(row, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_row_show, octeon_mc_inject_row_store);
+static DEVICE_ATTR(col, S_IRUGO | S_IWUSR,
+		   octeon_mc_inject_col_show, octeon_mc_inject_col_store);
+
+static struct attribute *octeon_dev_attrs[] = {
+	&dev_attr_inject.attr,
+	&dev_attr_error_type.attr,
+	&dev_attr_dimm.attr,
+	&dev_attr_rank.attr,
+	&dev_attr_bank.attr,
+	&dev_attr_row.attr,
+	&dev_attr_col.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(octeon_dev);
+
+static int octeon_lmc_edac_probe(struct platform_device *pdev)
+{
+	struct mem_ctl_info *mci;
+	struct edac_mc_layer layers[1];
+	int mc = pdev->id;
+
+	opstate_init();
+
+	layers[0].type = EDAC_MC_LAYER_CHANNEL;
+	layers[0].size = 1;
+	layers[0].is_virt_csrow = false;
+
+	if (OCTEON_IS_OCTEON1PLUS()) {
+		union cvmx_lmcx_mem_cfg0 cfg0;
+
+		cfg0.u64 = cvmx_read_csr(CVMX_LMCX_MEM_CFG0(0));
+		if (!cfg0.s.ecc_ena) {
+			dev_info(&pdev->dev, "Disabled (ECC not enabled)\n");
+			return 0;
+		}
+
+		mci = edac_mc_alloc(mc, ARRAY_SIZE(layers), layers, sizeof(struct octeon_lmc_pvt));
+		if (!mci)
+			return -ENXIO;
+
+		mci->pdev = &pdev->dev;
+		mci->dev_name = dev_name(&pdev->dev);
+
+		mci->mod_name = "octeon-lmc";
+		mci->ctl_name = "octeon-lmc-err";
+		mci->edac_check = octeon_lmc_edac_poll;
+
+		if (edac_mc_add_mc_with_groups(mci, octeon_dev_groups)) {
+			dev_err(&pdev->dev, "edac_mc_add_mc() failed\n");
+			edac_mc_free(mci);
+			return -ENXIO;
+		}
+
+		cfg0.u64 = cvmx_read_csr(CVMX_LMCX_MEM_CFG0(mc));
+		cfg0.s.intr_ded_ena = 0;	/* We poll */
+		cfg0.s.intr_sec_ena = 0;
+		cvmx_write_csr(CVMX_LMCX_MEM_CFG0(mc), cfg0.u64);
+	} else {
+		/* OCTEON II */
+		union cvmx_lmcx_int_en en;
+		union cvmx_lmcx_config config;
+
+		config.u64 = cvmx_read_csr(CVMX_LMCX_CONFIG(0));
+		if (!config.s.ecc_ena) {
+			dev_info(&pdev->dev, "Disabled (ECC not enabled)\n");
+			return 0;
+		}
+
+		mci = edac_mc_alloc(mc, ARRAY_SIZE(layers), layers, sizeof(struct octeon_lmc_pvt));
+		if (!mci)
+			return -ENXIO;
+
+		mci->pdev = &pdev->dev;
+		mci->dev_name = dev_name(&pdev->dev);
+
+		mci->mod_name = "octeon-lmc";
+		mci->ctl_name = "co_lmc_err";
+		mci->edac_check = octeon_lmc_edac_poll_o2;
+
+		if (edac_mc_add_mc_with_groups(mci, octeon_dev_groups)) {
+			dev_err(&pdev->dev, "edac_mc_add_mc() failed\n");
+			edac_mc_free(mci);
+			return -ENXIO;
+		}
+
+		en.u64 = cvmx_read_csr(CVMX_LMCX_MEM_CFG0(mc));
+		en.s.intr_ded_ena = 0;	/* We poll */
+		en.s.intr_sec_ena = 0;
+		cvmx_write_csr(CVMX_LMCX_MEM_CFG0(mc), en.u64);
+	}
+	platform_set_drvdata(pdev, mci);
+
+	return 0;
+}
+
+static int octeon_lmc_edac_remove(struct platform_device *pdev)
+{
+	struct mem_ctl_info *mci = platform_get_drvdata(pdev);
+
+	edac_mc_del_mc(&pdev->dev);
+	edac_mc_free(mci);
+	return 0;
+}
+
+static struct platform_driver octeon_lmc_edac_driver = {
+	.probe = octeon_lmc_edac_probe,
+	.remove = octeon_lmc_edac_remove,
+	.driver = {
+		   .name = "octeon_lmc_edac",
+	}
+};
+module_platform_driver(octeon_lmc_edac_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ralf Baechle <ralf@linux-mips.org>");