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, 257 insertions, 0 deletions

diff --git a/drivers/hwmon/occ/p8_i2c.c b/drivers/hwmon/occ/p8_i2c.c
new file mode 100644
index 000000000..9e1744fcc
--- /dev/null
+++ b/drivers/hwmon/occ/p8_i2c.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright IBM Corp 2019
+
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/fsi-occ.h>
+#include <linux/i2c.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <asm/unaligned.h>
+
+#include "common.h"
+
+#define OCC_TIMEOUT_MS			1000
+#define OCC_CMD_IN_PRG_WAIT_MS		50
+
+/* OCB (on-chip control bridge - interface to OCC) registers */
+#define OCB_DATA1			0x6B035
+#define OCB_ADDR			0x6B070
+#define OCB_DATA3			0x6B075
+
+/* OCC SRAM address space */
+#define OCC_SRAM_ADDR_CMD		0xFFFF6000
+#define OCC_SRAM_ADDR_RESP		0xFFFF7000
+
+#define OCC_DATA_ATTN			0x20010000
+
+struct p8_i2c_occ {
+	struct occ occ;
+	struct i2c_client *client;
+};
+
+#define to_p8_i2c_occ(x)	container_of((x), struct p8_i2c_occ, occ)
+
+static int p8_i2c_occ_getscom(struct i2c_client *client, u32 address, u8 *data)
+{
+	ssize_t rc;
+	__be64 buf;
+	struct i2c_msg msgs[2];
+
+	/* p8 i2c slave requires shift */
+	address <<= 1;
+
+	msgs[0].addr = client->addr;
+	msgs[0].flags = client->flags & I2C_M_TEN;
+	msgs[0].len = sizeof(u32);
+	/* address is a scom address; bus-endian */
+	msgs[0].buf = (char *)&address;
+
+	/* data from OCC is big-endian */
+	msgs[1].addr = client->addr;
+	msgs[1].flags = (client->flags & I2C_M_TEN) | I2C_M_RD;
+	msgs[1].len = sizeof(u64);
+	msgs[1].buf = (char *)&buf;
+
+	rc = i2c_transfer(client->adapter, msgs, 2);
+	if (rc < 0)
+		return rc;
+
+	*(u64 *)data = be64_to_cpu(buf);
+
+	return 0;
+}
+
+static int p8_i2c_occ_putscom(struct i2c_client *client, u32 address, u8 *data)
+{
+	u32 buf[3];
+	ssize_t rc;
+
+	/* p8 i2c slave requires shift */
+	address <<= 1;
+
+	/* address is bus-endian; data passed through from user as-is */
+	buf[0] = address;
+	memcpy(&buf[1], &data[4], sizeof(u32));
+	memcpy(&buf[2], data, sizeof(u32));
+
+	rc = i2c_master_send(client, (const char *)buf, sizeof(buf));
+	if (rc < 0)
+		return rc;
+	else if (rc != sizeof(buf))
+		return -EIO;
+
+	return 0;
+}
+
+static int p8_i2c_occ_putscom_u32(struct i2c_client *client, u32 address,
+				  u32 data0, u32 data1)
+{
+	u8 buf[8];
+
+	memcpy(buf, &data0, 4);
+	memcpy(buf + 4, &data1, 4);
+
+	return p8_i2c_occ_putscom(client, address, buf);
+}
+
+static int p8_i2c_occ_putscom_be(struct i2c_client *client, u32 address,
+				 u8 *data, size_t len)
+{
+	__be32 data0 = 0, data1 = 0;
+
+	memcpy(&data0, data, min_t(size_t, len, 4));
+	if (len > 4) {
+		len -= 4;
+		memcpy(&data1, data + 4, min_t(size_t, len, 4));
+	}
+
+	return p8_i2c_occ_putscom_u32(client, address, be32_to_cpu(data0),
+				      be32_to_cpu(data1));
+}
+
+static int p8_i2c_occ_send_cmd(struct occ *occ, u8 *cmd, size_t len,
+			       void *resp, size_t resp_len)
+{
+	int i, rc;
+	unsigned long start;
+	u16 data_length;
+	const unsigned long timeout = msecs_to_jiffies(OCC_TIMEOUT_MS);
+	const long wait_time = msecs_to_jiffies(OCC_CMD_IN_PRG_WAIT_MS);
+	struct p8_i2c_occ *ctx = to_p8_i2c_occ(occ);
+	struct i2c_client *client = ctx->client;
+	struct occ_response *or = (struct occ_response *)resp;
+
+	start = jiffies;
+
+	/* set sram address for command */
+	rc = p8_i2c_occ_putscom_u32(client, OCB_ADDR, OCC_SRAM_ADDR_CMD, 0);
+	if (rc)
+		return rc;
+
+	/* write command (expected to already be BE), we need bus-endian... */
+	rc = p8_i2c_occ_putscom_be(client, OCB_DATA3, cmd, len);
+	if (rc)
+		return rc;
+
+	/* trigger OCC attention */
+	rc = p8_i2c_occ_putscom_u32(client, OCB_DATA1, OCC_DATA_ATTN, 0);
+	if (rc)
+		return rc;
+
+	do {
+		/* set sram address for response */
+		rc = p8_i2c_occ_putscom_u32(client, OCB_ADDR,
+					    OCC_SRAM_ADDR_RESP, 0);
+		if (rc)
+			return rc;
+
+		rc = p8_i2c_occ_getscom(client, OCB_DATA3, (u8 *)resp);
+		if (rc)
+			return rc;
+
+		/* wait for OCC */
+		if (or->return_status == OCC_RESP_CMD_IN_PRG) {
+			rc = -EALREADY;
+
+			if (time_after(jiffies, start + timeout))
+				break;
+
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule_timeout(wait_time);
+		}
+	} while (rc);
+
+	/* check the OCC response */
+	switch (or->return_status) {
+	case OCC_RESP_CMD_IN_PRG:
+		rc = -ETIMEDOUT;
+		break;
+	case OCC_RESP_SUCCESS:
+		rc = 0;
+		break;
+	case OCC_RESP_CMD_INVAL:
+	case OCC_RESP_CMD_LEN_INVAL:
+	case OCC_RESP_DATA_INVAL:
+	case OCC_RESP_CHKSUM_ERR:
+		rc = -EINVAL;
+		break;
+	case OCC_RESP_INT_ERR:
+	case OCC_RESP_BAD_STATE:
+	case OCC_RESP_CRIT_EXCEPT:
+	case OCC_RESP_CRIT_INIT:
+	case OCC_RESP_CRIT_WATCHDOG:
+	case OCC_RESP_CRIT_OCB:
+	case OCC_RESP_CRIT_HW:
+		rc = -EREMOTEIO;
+		break;
+	default:
+		rc = -EPROTO;
+	}
+
+	if (rc < 0)
+		return rc;
+
+	data_length = get_unaligned_be16(&or->data_length);
+	if ((data_length + 7) > resp_len)
+		return -EMSGSIZE;
+
+	/* fetch the rest of the response data */
+	for (i = 8; i < data_length + 7; i += 8) {
+		rc = p8_i2c_occ_getscom(client, OCB_DATA3, ((u8 *)resp) + i);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int p8_i2c_occ_probe(struct i2c_client *client)
+{
+	struct occ *occ;
+	struct p8_i2c_occ *ctx = devm_kzalloc(&client->dev, sizeof(*ctx),
+					      GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->client = client;
+	occ = &ctx->occ;
+	occ->bus_dev = &client->dev;
+	dev_set_drvdata(&client->dev, occ);
+
+	occ->powr_sample_time_us = 250;
+	occ->poll_cmd_data = 0x10;		/* P8 OCC poll data */
+	occ->send_cmd = p8_i2c_occ_send_cmd;
+
+	return occ_setup(occ);
+}
+
+static void p8_i2c_occ_remove(struct i2c_client *client)
+{
+	struct occ *occ = dev_get_drvdata(&client->dev);
+
+	occ_shutdown(occ);
+}
+
+static const struct of_device_id p8_i2c_occ_of_match[] = {
+	{ .compatible = "ibm,p8-occ-hwmon" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, p8_i2c_occ_of_match);
+
+static struct i2c_driver p8_i2c_occ_driver = {
+	.class = I2C_CLASS_HWMON,
+	.driver = {
+		.name = "occ-hwmon",
+		.of_match_table = p8_i2c_occ_of_match,
+	},
+	.probe_new = p8_i2c_occ_probe,
+	.remove = p8_i2c_occ_remove,
+};
+
+module_i2c_driver(p8_i2c_occ_driver);
+
+MODULE_AUTHOR("Eddie James <eajames@linux.ibm.com>");
+MODULE_DESCRIPTION("BMC P8 OCC hwmon driver");
+MODULE_LICENSE("GPL");