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, 340 insertions, 0 deletions

diff --git a/drivers/mmc/host/cavium-octeon.c b/drivers/mmc/host/cavium-octeon.c
new file mode 100644
index 000000000..12dca91a8
--- /dev/null
+++ b/drivers/mmc/host/cavium-octeon.c
@@ -0,0 +1,340 @@
+/*
+ * Driver for MMC and SSD cards for Cavium OCTEON SOCs.
+ *
+ * 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) 2012-2017 Cavium Inc.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/slot-gpio.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <asm/octeon/octeon.h>
+#include "cavium.h"
+
+#define CVMX_MIO_BOOT_CTL CVMX_ADD_IO_SEG(0x00011800000000D0ull)
+
+/*
+ * The l2c* functions below are used for the EMMC-17978 workaround.
+ *
+ * Due to a bug in the design of the MMC bus hardware, the 2nd to last
+ * cache block of a DMA read must be locked into the L2 Cache.
+ * Otherwise, data corruption may occur.
+ */
+static inline void *phys_to_ptr(u64 address)
+{
+	return (void *)(address | (1ull << 63)); /* XKPHYS */
+}
+
+/*
+ * Lock a single line into L2. The line is zeroed before locking
+ * to make sure no dram accesses are made.
+ */
+static void l2c_lock_line(u64 addr)
+{
+	char *addr_ptr = phys_to_ptr(addr);
+
+	asm volatile (
+		"cache 31, %[line]"	/* Unlock the line */
+		::[line] "m" (*addr_ptr));
+}
+
+/* Unlock a single line in the L2 cache. */
+static void l2c_unlock_line(u64 addr)
+{
+	char *addr_ptr = phys_to_ptr(addr);
+
+	asm volatile (
+		"cache 23, %[line]"	/* Unlock the line */
+		::[line] "m" (*addr_ptr));
+}
+
+/* Locks a memory region in the L2 cache. */
+static void l2c_lock_mem_region(u64 start, u64 len)
+{
+	u64 end;
+
+	/* Round start/end to cache line boundaries */
+	end = ALIGN(start + len - 1, CVMX_CACHE_LINE_SIZE);
+	start = ALIGN(start, CVMX_CACHE_LINE_SIZE);
+
+	while (start <= end) {
+		l2c_lock_line(start);
+		start += CVMX_CACHE_LINE_SIZE;
+	}
+	asm volatile("sync");
+}
+
+/* Unlock a memory region in the L2 cache. */
+static void l2c_unlock_mem_region(u64 start, u64 len)
+{
+	u64 end;
+
+	/* Round start/end to cache line boundaries */
+	end = ALIGN(start + len - 1, CVMX_CACHE_LINE_SIZE);
+	start = ALIGN(start, CVMX_CACHE_LINE_SIZE);
+
+	while (start <= end) {
+		l2c_unlock_line(start);
+		start += CVMX_CACHE_LINE_SIZE;
+	}
+}
+
+static void octeon_mmc_acquire_bus(struct cvm_mmc_host *host)
+{
+	if (!host->has_ciu3) {
+		down(&octeon_bootbus_sem);
+		/* For CN70XX, switch the MMC controller onto the bus. */
+		if (OCTEON_IS_MODEL(OCTEON_CN70XX))
+			writeq(0, (void __iomem *)CVMX_MIO_BOOT_CTL);
+	} else {
+		down(&host->mmc_serializer);
+	}
+}
+
+static void octeon_mmc_release_bus(struct cvm_mmc_host *host)
+{
+	if (!host->has_ciu3)
+		up(&octeon_bootbus_sem);
+	else
+		up(&host->mmc_serializer);
+}
+
+static void octeon_mmc_int_enable(struct cvm_mmc_host *host, u64 val)
+{
+	writeq(val, host->base + MIO_EMM_INT(host));
+	if (!host->has_ciu3)
+		writeq(val, host->base + MIO_EMM_INT_EN(host));
+}
+
+static void octeon_mmc_set_shared_power(struct cvm_mmc_host *host, int dir)
+{
+	if (dir == 0)
+		if (!atomic_dec_return(&host->shared_power_users))
+			gpiod_set_value_cansleep(host->global_pwr_gpiod, 0);
+	if (dir == 1)
+		if (atomic_inc_return(&host->shared_power_users) == 1)
+			gpiod_set_value_cansleep(host->global_pwr_gpiod, 1);
+}
+
+static void octeon_mmc_dmar_fixup(struct cvm_mmc_host *host,
+				  struct mmc_command *cmd,
+				  struct mmc_data *data,
+				  u64 addr)
+{
+	if (cmd->opcode != MMC_WRITE_MULTIPLE_BLOCK)
+		return;
+	if (data->blksz * data->blocks <= 1024)
+		return;
+
+	host->n_minus_one = addr + (data->blksz * data->blocks) - 1024;
+	l2c_lock_mem_region(host->n_minus_one, 512);
+}
+
+static void octeon_mmc_dmar_fixup_done(struct cvm_mmc_host *host)
+{
+	if (!host->n_minus_one)
+		return;
+	l2c_unlock_mem_region(host->n_minus_one, 512);
+	host->n_minus_one = 0;
+}
+
+static int octeon_mmc_probe(struct platform_device *pdev)
+{
+	struct device_node *cn, *node = pdev->dev.of_node;
+	struct cvm_mmc_host *host;
+	void __iomem *base;
+	int mmc_irq[9];
+	int i, ret = 0;
+	u64 val;
+
+	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	spin_lock_init(&host->irq_handler_lock);
+	sema_init(&host->mmc_serializer, 1);
+
+	host->dev = &pdev->dev;
+	host->acquire_bus = octeon_mmc_acquire_bus;
+	host->release_bus = octeon_mmc_release_bus;
+	host->int_enable = octeon_mmc_int_enable;
+	host->set_shared_power = octeon_mmc_set_shared_power;
+	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) ||
+	    OCTEON_IS_MODEL(OCTEON_CNF7XXX)) {
+		host->dmar_fixup = octeon_mmc_dmar_fixup;
+		host->dmar_fixup_done = octeon_mmc_dmar_fixup_done;
+	}
+
+	host->sys_freq = octeon_get_io_clock_rate();
+
+	if (of_device_is_compatible(node, "cavium,octeon-7890-mmc")) {
+		host->big_dma_addr = true;
+		host->need_irq_handler_lock = true;
+		host->has_ciu3 = true;
+		host->use_sg = true;
+		/*
+		 * First seven are the EMM_INT bits 0..6, then two for
+		 * the EMM_DMA_INT bits
+		 */
+		for (i = 0; i < 9; i++) {
+			mmc_irq[i] = platform_get_irq(pdev, i);
+			if (mmc_irq[i] < 0)
+				return mmc_irq[i];
+
+			/* work around legacy u-boot device trees */
+			irq_set_irq_type(mmc_irq[i], IRQ_TYPE_EDGE_RISING);
+		}
+	} else {
+		host->big_dma_addr = false;
+		host->need_irq_handler_lock = false;
+		host->has_ciu3 = false;
+		/* First one is EMM second DMA */
+		for (i = 0; i < 2; i++) {
+			mmc_irq[i] = platform_get_irq(pdev, i);
+			if (mmc_irq[i] < 0)
+				return mmc_irq[i];
+		}
+	}
+
+	host->last_slot = -1;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+	host->base = base;
+	host->reg_off = 0;
+
+	base = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+	host->dma_base = base;
+	/*
+	 * To keep the register addresses shared we intentionaly use
+	 * a negative offset here, first register used on Octeon therefore
+	 * starts at 0x20 (MIO_EMM_DMA_CFG).
+	 */
+	host->reg_off_dma = -0x20;
+
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret)
+		return ret;
+
+	/*
+	 * Clear out any pending interrupts that may be left over from
+	 * bootloader.
+	 */
+	val = readq(host->base + MIO_EMM_INT(host));
+	writeq(val, host->base + MIO_EMM_INT(host));
+
+	if (host->has_ciu3) {
+		/* Only CMD_DONE, DMA_DONE, CMD_ERR, DMA_ERR */
+		for (i = 1; i <= 4; i++) {
+			ret = devm_request_irq(&pdev->dev, mmc_irq[i],
+					       cvm_mmc_interrupt,
+					       0, cvm_mmc_irq_names[i], host);
+			if (ret < 0) {
+				dev_err(&pdev->dev, "Error: devm_request_irq %d\n",
+					mmc_irq[i]);
+				return ret;
+			}
+		}
+	} else {
+		ret = devm_request_irq(&pdev->dev, mmc_irq[0],
+				       cvm_mmc_interrupt, 0, KBUILD_MODNAME,
+				       host);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Error: devm_request_irq %d\n",
+				mmc_irq[0]);
+			return ret;
+		}
+	}
+
+	host->global_pwr_gpiod = devm_gpiod_get_optional(&pdev->dev,
+							 "power",
+							 GPIOD_OUT_HIGH);
+	if (IS_ERR(host->global_pwr_gpiod)) {
+		dev_err(&pdev->dev, "Invalid power GPIO\n");
+		return PTR_ERR(host->global_pwr_gpiod);
+	}
+
+	platform_set_drvdata(pdev, host);
+
+	i = 0;
+	for_each_child_of_node(node, cn) {
+		host->slot_pdev[i] =
+			of_platform_device_create(cn, NULL, &pdev->dev);
+		if (!host->slot_pdev[i]) {
+			i++;
+			continue;
+		}
+		ret = cvm_mmc_of_slot_probe(&host->slot_pdev[i]->dev, host);
+		if (ret) {
+			dev_err(&pdev->dev, "Error populating slots\n");
+			octeon_mmc_set_shared_power(host, 0);
+			of_node_put(cn);
+			goto error;
+		}
+		i++;
+	}
+	return 0;
+
+error:
+	for (i = 0; i < CAVIUM_MAX_MMC; i++) {
+		if (host->slot[i])
+			cvm_mmc_of_slot_remove(host->slot[i]);
+		if (host->slot_pdev[i])
+			of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+	}
+	return ret;
+}
+
+static int octeon_mmc_remove(struct platform_device *pdev)
+{
+	struct cvm_mmc_host *host = platform_get_drvdata(pdev);
+	u64 dma_cfg;
+	int i;
+
+	for (i = 0; i < CAVIUM_MAX_MMC; i++)
+		if (host->slot[i])
+			cvm_mmc_of_slot_remove(host->slot[i]);
+
+	dma_cfg = readq(host->dma_base + MIO_EMM_DMA_CFG(host));
+	dma_cfg &= ~MIO_EMM_DMA_CFG_EN;
+	writeq(dma_cfg, host->dma_base + MIO_EMM_DMA_CFG(host));
+
+	octeon_mmc_set_shared_power(host, 0);
+	return 0;
+}
+
+static const struct of_device_id octeon_mmc_match[] = {
+	{
+		.compatible = "cavium,octeon-6130-mmc",
+	},
+	{
+		.compatible = "cavium,octeon-7890-mmc",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, octeon_mmc_match);
+
+static struct platform_driver octeon_mmc_driver = {
+	.probe		= octeon_mmc_probe,
+	.remove		= octeon_mmc_remove,
+	.driver		= {
+		.name	= KBUILD_MODNAME,
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+		.of_match_table = octeon_mmc_match,
+	},
+};
+
+module_platform_driver(octeon_mmc_driver);
+
+MODULE_AUTHOR("Cavium Inc. <support@cavium.com>");
+MODULE_DESCRIPTION("Low-level driver for Cavium OCTEON MMC/SSD card");
+MODULE_LICENSE("GPL");