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().
  ...

3 files changed, 285 insertions, 0 deletions

diff --git a/drivers/soc/sifive/Kconfig b/drivers/soc/sifive/Kconfig
new file mode 100644
index 000000000..ed4c571f8
--- /dev/null
+++ b/drivers/soc/sifive/Kconfig
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+
+if SOC_SIFIVE
+
+config SIFIVE_CCACHE
+	bool "Sifive Composable Cache controller"
+	help
+	  Support for the composable cache controller on SiFive platforms.
+
+endif
diff --git a/drivers/soc/sifive/Makefile b/drivers/soc/sifive/Makefile
new file mode 100644
index 000000000..1f5dc339b
--- /dev/null
+++ b/drivers/soc/sifive/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_SIFIVE_CCACHE)	+= sifive_ccache.o
diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c
new file mode 100644
index 000000000..3684f5b40
--- /dev/null
+++ b/drivers/soc/sifive/sifive_ccache.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SiFive composable cache controller Driver
+ *
+ * Copyright (C) 2018-2022 SiFive, Inc.
+ *
+ */
+
+#define pr_fmt(fmt) "CCACHE: " fmt
+
+#include <linux/debugfs.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/device.h>
+#include <linux/bitfield.h>
+#include <asm/cacheinfo.h>
+#include <soc/sifive/sifive_ccache.h>
+
+#define SIFIVE_CCACHE_DIRECCFIX_LOW 0x100
+#define SIFIVE_CCACHE_DIRECCFIX_HIGH 0x104
+#define SIFIVE_CCACHE_DIRECCFIX_COUNT 0x108
+
+#define SIFIVE_CCACHE_DIRECCFAIL_LOW 0x120
+#define SIFIVE_CCACHE_DIRECCFAIL_HIGH 0x124
+#define SIFIVE_CCACHE_DIRECCFAIL_COUNT 0x128
+
+#define SIFIVE_CCACHE_DATECCFIX_LOW 0x140
+#define SIFIVE_CCACHE_DATECCFIX_HIGH 0x144
+#define SIFIVE_CCACHE_DATECCFIX_COUNT 0x148
+
+#define SIFIVE_CCACHE_DATECCFAIL_LOW 0x160
+#define SIFIVE_CCACHE_DATECCFAIL_HIGH 0x164
+#define SIFIVE_CCACHE_DATECCFAIL_COUNT 0x168
+
+#define SIFIVE_CCACHE_CONFIG 0x00
+#define SIFIVE_CCACHE_CONFIG_BANK_MASK GENMASK_ULL(7, 0)
+#define SIFIVE_CCACHE_CONFIG_WAYS_MASK GENMASK_ULL(15, 8)
+#define SIFIVE_CCACHE_CONFIG_SETS_MASK GENMASK_ULL(23, 16)
+#define SIFIVE_CCACHE_CONFIG_BLKS_MASK GENMASK_ULL(31, 24)
+
+#define SIFIVE_CCACHE_WAYENABLE 0x08
+#define SIFIVE_CCACHE_ECCINJECTERR 0x40
+
+#define SIFIVE_CCACHE_MAX_ECCINTR 4
+
+static void __iomem *ccache_base;
+static int g_irq[SIFIVE_CCACHE_MAX_ECCINTR];
+static struct riscv_cacheinfo_ops ccache_cache_ops;
+static int level;
+
+enum {
+	DIR_CORR = 0,
+	DATA_CORR,
+	DATA_UNCORR,
+	DIR_UNCORR,
+};
+
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *sifive_test;
+
+static ssize_t ccache_write(struct file *file, const char __user *data,
+			    size_t count, loff_t *ppos)
+{
+	unsigned int val;
+
+	if (kstrtouint_from_user(data, count, 0, &val))
+		return -EINVAL;
+	if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF))
+		writel(val, ccache_base + SIFIVE_CCACHE_ECCINJECTERR);
+	else
+		return -EINVAL;
+	return count;
+}
+
+static const struct file_operations ccache_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = ccache_write
+};
+
+static void setup_sifive_debug(void)
+{
+	sifive_test = debugfs_create_dir("sifive_ccache_cache", NULL);
+
+	debugfs_create_file("sifive_debug_inject_error", 0200,
+			    sifive_test, NULL, &ccache_fops);
+}
+#endif
+
+static void ccache_config_read(void)
+{
+	u32 cfg;
+
+	cfg = readl(ccache_base + SIFIVE_CCACHE_CONFIG);
+	pr_info("%llu banks, %llu ways, sets/bank=%llu, bytes/block=%llu\n",
+		FIELD_GET(SIFIVE_CCACHE_CONFIG_BANK_MASK, cfg),
+		FIELD_GET(SIFIVE_CCACHE_CONFIG_WAYS_MASK, cfg),
+		BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_SETS_MASK, cfg)),
+		BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_BLKS_MASK, cfg)));
+
+	cfg = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE);
+	pr_info("Index of the largest way enabled: %u\n", cfg);
+}
+
+static const struct of_device_id sifive_ccache_ids[] = {
+	{ .compatible = "sifive,fu540-c000-ccache" },
+	{ .compatible = "sifive,fu740-c000-ccache" },
+	{ .compatible = "sifive,ccache0" },
+	{ /* end of table */ }
+};
+
+static ATOMIC_NOTIFIER_HEAD(ccache_err_chain);
+
+int register_sifive_ccache_error_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&ccache_err_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_sifive_ccache_error_notifier);
+
+int unregister_sifive_ccache_error_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&ccache_err_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_sifive_ccache_error_notifier);
+
+static int ccache_largest_wayenabled(void)
+{
+	return readl(ccache_base + SIFIVE_CCACHE_WAYENABLE) & 0xFF;
+}
+
+static ssize_t number_of_ways_enabled_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	return sprintf(buf, "%u\n", ccache_largest_wayenabled());
+}
+
+static DEVICE_ATTR_RO(number_of_ways_enabled);
+
+static struct attribute *priv_attrs[] = {
+	&dev_attr_number_of_ways_enabled.attr,
+	NULL,
+};
+
+static const struct attribute_group priv_attr_group = {
+	.attrs = priv_attrs,
+};
+
+static const struct attribute_group *ccache_get_priv_group(struct cacheinfo
+							   *this_leaf)
+{
+	/* We want to use private group for composable cache only */
+	if (this_leaf->level == level)
+		return &priv_attr_group;
+	else
+		return NULL;
+}
+
+static irqreturn_t ccache_int_handler(int irq, void *device)
+{
+	unsigned int add_h, add_l;
+
+	if (irq == g_irq[DIR_CORR]) {
+		add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_HIGH);
+		add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_LOW);
+		pr_err("DirError @ 0x%08X.%08X\n", add_h, add_l);
+		/* Reading this register clears the DirError interrupt sig */
+		readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_COUNT);
+		atomic_notifier_call_chain(&ccache_err_chain,
+					   SIFIVE_CCACHE_ERR_TYPE_CE,
+					   "DirECCFix");
+	}
+	if (irq == g_irq[DIR_UNCORR]) {
+		add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_HIGH);
+		add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_LOW);
+		/* Reading this register clears the DirFail interrupt sig */
+		readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_COUNT);
+		atomic_notifier_call_chain(&ccache_err_chain,
+					   SIFIVE_CCACHE_ERR_TYPE_UE,
+					   "DirECCFail");
+		panic("CCACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l);
+	}
+	if (irq == g_irq[DATA_CORR]) {
+		add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_HIGH);
+		add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_LOW);
+		pr_err("DataError @ 0x%08X.%08X\n", add_h, add_l);
+		/* Reading this register clears the DataError interrupt sig */
+		readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_COUNT);
+		atomic_notifier_call_chain(&ccache_err_chain,
+					   SIFIVE_CCACHE_ERR_TYPE_CE,
+					   "DatECCFix");
+	}
+	if (irq == g_irq[DATA_UNCORR]) {
+		add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_HIGH);
+		add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_LOW);
+		pr_err("DataFail @ 0x%08X.%08X\n", add_h, add_l);
+		/* Reading this register clears the DataFail interrupt sig */
+		readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_COUNT);
+		atomic_notifier_call_chain(&ccache_err_chain,
+					   SIFIVE_CCACHE_ERR_TYPE_UE,
+					   "DatECCFail");
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int __init sifive_ccache_init(void)
+{
+	struct device_node *np;
+	struct resource res;
+	int i, rc, intr_num;
+
+	np = of_find_matching_node(NULL, sifive_ccache_ids);
+	if (!np)
+		return -ENODEV;
+
+	if (of_address_to_resource(np, 0, &res)) {
+		rc = -ENODEV;
+		goto err_node_put;
+	}
+
+	ccache_base = ioremap(res.start, resource_size(&res));
+	if (!ccache_base) {
+		rc = -ENOMEM;
+		goto err_node_put;
+	}
+
+	if (of_property_read_u32(np, "cache-level", &level)) {
+		rc = -ENOENT;
+		goto err_unmap;
+	}
+
+	intr_num = of_property_count_u32_elems(np, "interrupts");
+	if (!intr_num) {
+		pr_err("No interrupts property\n");
+		rc = -ENODEV;
+		goto err_unmap;
+	}
+
+	for (i = 0; i < intr_num; i++) {
+		g_irq[i] = irq_of_parse_and_map(np, i);
+		rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc",
+				 NULL);
+		if (rc) {
+			pr_err("Could not request IRQ %d\n", g_irq[i]);
+			goto err_free_irq;
+		}
+	}
+	of_node_put(np);
+
+	ccache_config_read();
+
+	ccache_cache_ops.get_priv_group = ccache_get_priv_group;
+	riscv_set_cacheinfo_ops(&ccache_cache_ops);
+
+#ifdef CONFIG_DEBUG_FS
+	setup_sifive_debug();
+#endif
+	return 0;
+
+err_free_irq:
+	while (--i >= 0)
+		free_irq(g_irq[i], NULL);
+err_unmap:
+	iounmap(ccache_base);
+err_node_put:
+	of_node_put(np);
+	return rc;
+}
+
+device_initcall(sifive_ccache_init);