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, 301 insertions, 0 deletions

diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
new file mode 100644
index 000000000..ab47aeb55
--- /dev/null
+++ b/drivers/ata/pata_cs5536.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * pata_cs5536.c	- CS5536 PATA for new ATA layer
+ *			  (C) 2007 Martin K. Petersen <mkp@mkp.net>
+ *			  (C) 2011 Bartlomiej Zolnierkiewicz
+ *
+ * Documentation:
+ *	Available from AMD web site.
+ *
+ * The IDE timing registers for the CS5536 live in the Geode Machine
+ * Specific Register file and not PCI config space.  Most BIOSes
+ * virtualize the PCI registers so the chip looks like a standard IDE
+ * controller.	Unfortunately not all implementations get this right.
+ * In particular some have problems with unaligned accesses to the
+ * virtualized PCI registers.  This driver always does full dword
+ * writes to work around the issue.  Also, in case of a bad BIOS this
+ * driver can be loaded with the "msr=1" parameter which forces using
+ * the Machine Specific Registers to configure the device.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/libata.h>
+#include <scsi/scsi_host.h>
+#include <linux/dmi.h>
+
+#ifdef CONFIG_X86_32
+#include <asm/msr.h>
+static int use_msr;
+module_param_named(msr, use_msr, int, 0644);
+MODULE_PARM_DESC(msr, "Force using MSR to configure IDE function (Default: 0)");
+#else
+#undef rdmsr	/* avoid accidental MSR usage on, e.g. x86-64 */
+#undef wrmsr
+#define rdmsr(x, y, z) do { } while (0)
+#define wrmsr(x, y, z) do { } while (0)
+#define use_msr 0
+#endif
+
+#define DRV_NAME	"pata_cs5536"
+#define DRV_VERSION	"0.0.8"
+
+enum {
+	MSR_IDE_CFG		= 0x51300010,
+	PCI_IDE_CFG		= 0x40,
+
+	CFG			= 0,
+	DTC			= 2,
+	CAST			= 3,
+	ETC			= 4,
+
+	IDE_CFG_CHANEN		= (1 << 1),
+	IDE_CFG_CABLE		= (1 << 17) | (1 << 16),
+
+	IDE_D0_SHIFT		= 24,
+	IDE_D1_SHIFT		= 16,
+	IDE_DRV_MASK		= 0xff,
+
+	IDE_CAST_D0_SHIFT	= 6,
+	IDE_CAST_D1_SHIFT	= 4,
+	IDE_CAST_DRV_MASK	= 0x3,
+	IDE_CAST_CMD_MASK	= 0xff,
+	IDE_CAST_CMD_SHIFT	= 24,
+
+	IDE_ETC_UDMA_MASK	= 0xc0,
+};
+
+/* Some Bachmann OT200 devices have a non working UDMA support due a
+ * missing resistor.
+ */
+static const struct dmi_system_id udma_quirk_dmi_table[] = {
+	{
+		.ident = "Bachmann electronic OT200",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Bachmann electronic"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OT200"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "1")
+		},
+	},
+	{ }
+};
+
+static int cs5536_read(struct pci_dev *pdev, int reg, u32 *val)
+{
+	if (unlikely(use_msr)) {
+		u32 dummy __maybe_unused;
+
+		rdmsr(MSR_IDE_CFG + reg, *val, dummy);
+		return 0;
+	}
+
+	return pci_read_config_dword(pdev, PCI_IDE_CFG + reg * 4, val);
+}
+
+static int cs5536_write(struct pci_dev *pdev, int reg, int val)
+{
+	if (unlikely(use_msr)) {
+		wrmsr(MSR_IDE_CFG + reg, val, 0);
+		return 0;
+	}
+
+	return pci_write_config_dword(pdev, PCI_IDE_CFG + reg * 4, val);
+}
+
+static void cs5536_program_dtc(struct ata_device *adev, u8 tim)
+{
+	struct pci_dev *pdev = to_pci_dev(adev->link->ap->host->dev);
+	int dshift = adev->devno ? IDE_D1_SHIFT : IDE_D0_SHIFT;
+	u32 dtc;
+
+	cs5536_read(pdev, DTC, &dtc);
+	dtc &= ~(IDE_DRV_MASK << dshift);
+	dtc |= tim << dshift;
+	cs5536_write(pdev, DTC, dtc);
+}
+
+/**
+ *	cs5536_cable_detect	-	detect cable type
+ *	@ap: Port to detect on
+ *
+ *	Perform cable detection for ATA66 capable cable.
+ *
+ *	Returns a cable type.
+ */
+
+static int cs5536_cable_detect(struct ata_port *ap)
+{
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	u32 cfg;
+
+	cs5536_read(pdev, CFG, &cfg);
+
+	if (cfg & IDE_CFG_CABLE)
+		return ATA_CBL_PATA80;
+	else
+		return ATA_CBL_PATA40;
+}
+
+/**
+ *	cs5536_set_piomode		-	PIO setup
+ *	@ap: ATA interface
+ *	@adev: device on the interface
+ */
+
+static void cs5536_set_piomode(struct ata_port *ap, struct ata_device *adev)
+{
+	static const u8 drv_timings[5] = {
+		0x98, 0x55, 0x32, 0x21, 0x20,
+	};
+
+	static const u8 addr_timings[5] = {
+		0x2, 0x1, 0x0, 0x0, 0x0,
+	};
+
+	static const u8 cmd_timings[5] = {
+		0x99, 0x92, 0x90, 0x22, 0x20,
+	};
+
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	struct ata_device *pair = ata_dev_pair(adev);
+	int mode = adev->pio_mode - XFER_PIO_0;
+	int cmdmode = mode;
+	int cshift = adev->devno ? IDE_CAST_D1_SHIFT : IDE_CAST_D0_SHIFT;
+	u32 cast;
+
+	if (pair)
+		cmdmode = min(mode, pair->pio_mode - XFER_PIO_0);
+
+	cs5536_program_dtc(adev, drv_timings[mode]);
+
+	cs5536_read(pdev, CAST, &cast);
+
+	cast &= ~(IDE_CAST_DRV_MASK << cshift);
+	cast |= addr_timings[mode] << cshift;
+
+	cast &= ~(IDE_CAST_CMD_MASK << IDE_CAST_CMD_SHIFT);
+	cast |= cmd_timings[cmdmode] << IDE_CAST_CMD_SHIFT;
+
+	cs5536_write(pdev, CAST, cast);
+}
+
+/**
+ *	cs5536_set_dmamode		-	DMA timing setup
+ *	@ap: ATA interface
+ *	@adev: Device being configured
+ *
+ */
+
+static void cs5536_set_dmamode(struct ata_port *ap, struct ata_device *adev)
+{
+	static const u8 udma_timings[6] = {
+		0xc2, 0xc1, 0xc0, 0xc4, 0xc5, 0xc6,
+	};
+
+	static const u8 mwdma_timings[3] = {
+		0x67, 0x21, 0x20,
+	};
+
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	u32 etc;
+	int mode = adev->dma_mode;
+	int dshift = adev->devno ? IDE_D1_SHIFT : IDE_D0_SHIFT;
+
+	cs5536_read(pdev, ETC, &etc);
+
+	if (mode >= XFER_UDMA_0) {
+		etc &= ~(IDE_DRV_MASK << dshift);
+		etc |= udma_timings[mode - XFER_UDMA_0] << dshift;
+	} else { /* MWDMA */
+		etc &= ~(IDE_ETC_UDMA_MASK << dshift);
+		cs5536_program_dtc(adev, mwdma_timings[mode - XFER_MW_DMA_0]);
+	}
+
+	cs5536_write(pdev, ETC, etc);
+}
+
+static struct scsi_host_template cs5536_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+};
+
+static struct ata_port_operations cs5536_port_ops = {
+	.inherits		= &ata_bmdma32_port_ops,
+	.cable_detect		= cs5536_cable_detect,
+	.set_piomode		= cs5536_set_piomode,
+	.set_dmamode		= cs5536_set_dmamode,
+};
+
+/**
+ *	cs5536_init_one
+ *	@dev: PCI device
+ *	@id: Entry in match table
+ *
+ */
+
+static int cs5536_init_one(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	static const struct ata_port_info info = {
+		.flags = ATA_FLAG_SLAVE_POSS,
+		.pio_mask = ATA_PIO4,
+		.mwdma_mask = ATA_MWDMA2,
+		.udma_mask = ATA_UDMA5,
+		.port_ops = &cs5536_port_ops,
+	};
+
+	static const struct ata_port_info no_udma_info = {
+		.flags = ATA_FLAG_SLAVE_POSS,
+		.pio_mask = ATA_PIO4,
+		.port_ops = &cs5536_port_ops,
+	};
+
+
+	const struct ata_port_info *ppi[2];
+	u32 cfg;
+
+	if (dmi_check_system(udma_quirk_dmi_table))
+		ppi[0] = &no_udma_info;
+	else
+		ppi[0] = &info;
+
+	ppi[1] = &ata_dummy_port_info;
+
+	if (use_msr)
+		dev_err(&dev->dev, DRV_NAME ": Using MSR regs instead of PCI\n");
+
+	cs5536_read(dev, CFG, &cfg);
+
+	if ((cfg & IDE_CFG_CHANEN) == 0) {
+		dev_err(&dev->dev, DRV_NAME ": disabled by BIOS\n");
+		return -ENODEV;
+	}
+
+	return ata_pci_bmdma_init_one(dev, ppi, &cs5536_sht, NULL, 0);
+}
+
+static const struct pci_device_id cs5536[] = {
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_IDE), },
+	{ PCI_VDEVICE(AMD,	PCI_DEVICE_ID_AMD_CS5536_DEV_IDE), },
+	{ },
+};
+
+static struct pci_driver cs5536_pci_driver = {
+	.name		= DRV_NAME,
+	.id_table	= cs5536,
+	.probe		= cs5536_init_one,
+	.remove		= ata_pci_remove_one,
+#ifdef CONFIG_PM_SLEEP
+	.suspend	= ata_pci_device_suspend,
+	.resume		= ata_pci_device_resume,
+#endif
+};
+
+module_pci_driver(cs5536_pci_driver);
+
+MODULE_AUTHOR("Martin K. Petersen");
+MODULE_DESCRIPTION("low-level driver for the CS5536 IDE controller");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pci, cs5536);
+MODULE_VERSION(DRV_VERSION);