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, 399 insertions, 0 deletions

diff --git a/drivers/fpga/microchip-spi.c b/drivers/fpga/microchip-spi.c
new file mode 100644
index 000000000..7436976ea
--- /dev/null
+++ b/drivers/fpga/microchip-spi.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microchip Polarfire FPGA programming over slave SPI interface.
+ */
+
+#include <asm/unaligned.h>
+#include <linux/delay.h>
+#include <linux/fpga/fpga-mgr.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+
+#define	MPF_SPI_ISC_ENABLE	0x0B
+#define	MPF_SPI_ISC_DISABLE	0x0C
+#define	MPF_SPI_READ_STATUS	0x00
+#define	MPF_SPI_READ_DATA	0x01
+#define	MPF_SPI_FRAME_INIT	0xAE
+#define	MPF_SPI_FRAME		0xEE
+#define	MPF_SPI_PRG_MODE	0x01
+#define	MPF_SPI_RELEASE		0x23
+
+#define	MPF_SPI_FRAME_SIZE	16
+
+#define	MPF_HEADER_SIZE_OFFSET	24
+#define	MPF_DATA_SIZE_OFFSET	55
+
+#define	MPF_LOOKUP_TABLE_RECORD_SIZE		9
+#define	MPF_LOOKUP_TABLE_BLOCK_ID_OFFSET	0
+#define	MPF_LOOKUP_TABLE_BLOCK_START_OFFSET	1
+
+#define	MPF_COMPONENTS_SIZE_ID	5
+#define	MPF_BITSTREAM_ID	8
+
+#define	MPF_BITS_PER_COMPONENT_SIZE	22
+
+#define	MPF_STATUS_POLL_RETRIES		10000
+#define	MPF_STATUS_BUSY			BIT(0)
+#define	MPF_STATUS_READY		BIT(1)
+#define	MPF_STATUS_SPI_VIOLATION	BIT(2)
+#define	MPF_STATUS_SPI_ERROR		BIT(3)
+
+struct mpf_priv {
+	struct spi_device *spi;
+	bool program_mode;
+};
+
+static int mpf_read_status(struct spi_device *spi)
+{
+	u8 status = 0, status_command = MPF_SPI_READ_STATUS;
+	struct spi_transfer xfers[2] = { 0 };
+	int ret;
+
+	/*
+	 * HW status is returned on MISO in the first byte after CS went
+	 * active. However, first reading can be inadequate, so we submit
+	 * two identical SPI transfers and use result of the later one.
+	 */
+	xfers[0].tx_buf = &status_command;
+	xfers[1].tx_buf = &status_command;
+	xfers[0].rx_buf = &status;
+	xfers[1].rx_buf = &status;
+	xfers[0].len = 1;
+	xfers[1].len = 1;
+	xfers[0].cs_change = 1;
+
+	ret = spi_sync_transfer(spi, xfers, 2);
+
+	if ((status & MPF_STATUS_SPI_VIOLATION) ||
+	    (status & MPF_STATUS_SPI_ERROR))
+		ret = -EIO;
+
+	return ret ? : status;
+}
+
+static enum fpga_mgr_states mpf_ops_state(struct fpga_manager *mgr)
+{
+	struct mpf_priv *priv = mgr->priv;
+	struct spi_device *spi;
+	bool program_mode;
+	int status;
+
+	spi = priv->spi;
+	program_mode = priv->program_mode;
+	status = mpf_read_status(spi);
+
+	if (!program_mode && !status)
+		return FPGA_MGR_STATE_OPERATING;
+
+	return FPGA_MGR_STATE_UNKNOWN;
+}
+
+static int mpf_ops_parse_header(struct fpga_manager *mgr,
+				struct fpga_image_info *info,
+				const char *buf, size_t count)
+{
+	size_t component_size_byte_num, component_size_byte_off,
+	       components_size_start, bitstream_start,
+	       block_id_offset, block_start_offset;
+	u8 header_size, blocks_num, block_id;
+	u32 block_start, component_size;
+	u16 components_num, i;
+
+	if (!buf) {
+		dev_err(&mgr->dev, "Image buffer is not provided\n");
+		return -EINVAL;
+	}
+
+	header_size = *(buf + MPF_HEADER_SIZE_OFFSET);
+	if (header_size > count) {
+		info->header_size = header_size;
+		return -EAGAIN;
+	}
+
+	/*
+	 * Go through look-up table to find out where actual bitstream starts
+	 * and where sizes of components of the bitstream lies.
+	 */
+	blocks_num = *(buf + header_size - 1);
+	block_id_offset = header_size + MPF_LOOKUP_TABLE_BLOCK_ID_OFFSET;
+	block_start_offset = header_size + MPF_LOOKUP_TABLE_BLOCK_START_OFFSET;
+
+	header_size += blocks_num * MPF_LOOKUP_TABLE_RECORD_SIZE;
+	if (header_size > count) {
+		info->header_size = header_size;
+		return -EAGAIN;
+	}
+
+	components_size_start = 0;
+	bitstream_start = 0;
+
+	while (blocks_num--) {
+		block_id = *(buf + block_id_offset);
+		block_start = get_unaligned_le32(buf + block_start_offset);
+
+		switch (block_id) {
+		case MPF_BITSTREAM_ID:
+			bitstream_start = block_start;
+			info->header_size = block_start;
+			if (block_start > count)
+				return -EAGAIN;
+
+			break;
+		case MPF_COMPONENTS_SIZE_ID:
+			components_size_start = block_start;
+			break;
+		default:
+			break;
+		}
+
+		if (bitstream_start && components_size_start)
+			break;
+
+		block_id_offset += MPF_LOOKUP_TABLE_RECORD_SIZE;
+		block_start_offset += MPF_LOOKUP_TABLE_RECORD_SIZE;
+	}
+
+	if (!bitstream_start || !components_size_start) {
+		dev_err(&mgr->dev, "Failed to parse header look-up table\n");
+		return -EFAULT;
+	}
+
+	/*
+	 * Parse bitstream size.
+	 * Sizes of components of the bitstream are 22-bits long placed next
+	 * to each other. Image header should be extended by now up to where
+	 * actual bitstream starts, so no need for overflow check anymore.
+	 */
+	components_num = get_unaligned_le16(buf + MPF_DATA_SIZE_OFFSET);
+
+	for (i = 0; i < components_num; i++) {
+		component_size_byte_num =
+			(i * MPF_BITS_PER_COMPONENT_SIZE) / BITS_PER_BYTE;
+		component_size_byte_off =
+			(i * MPF_BITS_PER_COMPONENT_SIZE) % BITS_PER_BYTE;
+
+		component_size = get_unaligned_le32(buf +
+						    components_size_start +
+						    component_size_byte_num);
+		component_size >>= component_size_byte_off;
+		component_size &= GENMASK(MPF_BITS_PER_COMPONENT_SIZE - 1, 0);
+
+		info->data_size += component_size * MPF_SPI_FRAME_SIZE;
+	}
+
+	return 0;
+}
+
+/* Poll HW status until busy bit is cleared and mask bits are set. */
+static int mpf_poll_status(struct spi_device *spi, u8 mask)
+{
+	int status, retries = MPF_STATUS_POLL_RETRIES;
+
+	while (retries--) {
+		status = mpf_read_status(spi);
+		if (status < 0)
+			return status;
+
+		if (status & MPF_STATUS_BUSY)
+			continue;
+
+		if (!mask || (status & mask))
+			return status;
+	}
+
+	return -EBUSY;
+}
+
+static int mpf_spi_write(struct spi_device *spi, const void *buf, size_t buf_size)
+{
+	int status = mpf_poll_status(spi, 0);
+
+	if (status < 0)
+		return status;
+
+	return spi_write(spi, buf, buf_size);
+}
+
+static int mpf_spi_write_then_read(struct spi_device *spi,
+				   const void *txbuf, size_t txbuf_size,
+				   void *rxbuf, size_t rxbuf_size)
+{
+	const u8 read_command[] = { MPF_SPI_READ_DATA };
+	int ret;
+
+	ret = mpf_spi_write(spi, txbuf, txbuf_size);
+	if (ret)
+		return ret;
+
+	ret = mpf_poll_status(spi, MPF_STATUS_READY);
+	if (ret < 0)
+		return ret;
+
+	return spi_write_then_read(spi, read_command, sizeof(read_command),
+				   rxbuf, rxbuf_size);
+}
+
+static int mpf_ops_write_init(struct fpga_manager *mgr,
+			      struct fpga_image_info *info, const char *buf,
+			      size_t count)
+{
+	const u8 program_mode[] = { MPF_SPI_FRAME_INIT, MPF_SPI_PRG_MODE };
+	const u8 isc_en_command[] = { MPF_SPI_ISC_ENABLE };
+	struct mpf_priv *priv = mgr->priv;
+	struct device *dev = &mgr->dev;
+	struct spi_device *spi;
+	u32 isc_ret = 0;
+	int ret;
+
+	if (info->flags & FPGA_MGR_PARTIAL_RECONFIG) {
+		dev_err(dev, "Partial reconfiguration is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	spi = priv->spi;
+
+	ret = mpf_spi_write_then_read(spi, isc_en_command, sizeof(isc_en_command),
+				      &isc_ret, sizeof(isc_ret));
+	if (ret || isc_ret) {
+		dev_err(dev, "Failed to enable ISC: spi_ret %d, isc_ret %u\n",
+			ret, isc_ret);
+		return -EFAULT;
+	}
+
+	ret = mpf_spi_write(spi, program_mode, sizeof(program_mode));
+	if (ret) {
+		dev_err(dev, "Failed to enter program mode: %d\n", ret);
+		return ret;
+	}
+
+	priv->program_mode = true;
+
+	return 0;
+}
+
+static int mpf_ops_write(struct fpga_manager *mgr, const char *buf, size_t count)
+{
+	u8 spi_frame_command[] = { MPF_SPI_FRAME };
+	struct spi_transfer xfers[2] = { 0 };
+	struct mpf_priv *priv = mgr->priv;
+	struct device *dev = &mgr->dev;
+	struct spi_device *spi;
+	int ret, i;
+
+	if (count % MPF_SPI_FRAME_SIZE) {
+		dev_err(dev, "Bitstream size is not a multiple of %d\n",
+			MPF_SPI_FRAME_SIZE);
+		return -EINVAL;
+	}
+
+	spi = priv->spi;
+
+	xfers[0].tx_buf = spi_frame_command;
+	xfers[0].len = sizeof(spi_frame_command);
+
+	for (i = 0; i < count / MPF_SPI_FRAME_SIZE; i++) {
+		xfers[1].tx_buf = buf + i * MPF_SPI_FRAME_SIZE;
+		xfers[1].len = MPF_SPI_FRAME_SIZE;
+
+		ret = mpf_poll_status(spi, 0);
+		if (ret >= 0)
+			ret = spi_sync_transfer(spi, xfers, ARRAY_SIZE(xfers));
+
+		if (ret) {
+			dev_err(dev, "Failed to write bitstream frame %d/%zu\n",
+				i, count / MPF_SPI_FRAME_SIZE);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int mpf_ops_write_complete(struct fpga_manager *mgr,
+				  struct fpga_image_info *info)
+{
+	const u8 isc_dis_command[] = { MPF_SPI_ISC_DISABLE };
+	const u8 release_command[] = { MPF_SPI_RELEASE };
+	struct mpf_priv *priv = mgr->priv;
+	struct device *dev = &mgr->dev;
+	struct spi_device *spi;
+	int ret;
+
+	spi = priv->spi;
+
+	ret = mpf_spi_write(spi, isc_dis_command, sizeof(isc_dis_command));
+	if (ret) {
+		dev_err(dev, "Failed to disable ISC: %d\n", ret);
+		return ret;
+	}
+
+	usleep_range(1000, 2000);
+
+	ret = mpf_spi_write(spi, release_command, sizeof(release_command));
+	if (ret) {
+		dev_err(dev, "Failed to exit program mode: %d\n", ret);
+		return ret;
+	}
+
+	priv->program_mode = false;
+
+	return 0;
+}
+
+static const struct fpga_manager_ops mpf_ops = {
+	.state = mpf_ops_state,
+	.initial_header_size = 71,
+	.skip_header = true,
+	.parse_header = mpf_ops_parse_header,
+	.write_init = mpf_ops_write_init,
+	.write = mpf_ops_write,
+	.write_complete = mpf_ops_write_complete,
+};
+
+static int mpf_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct fpga_manager *mgr;
+	struct mpf_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->spi = spi;
+
+	mgr = devm_fpga_mgr_register(dev, "Microchip Polarfire SPI FPGA Manager",
+				     &mpf_ops, priv);
+
+	return PTR_ERR_OR_ZERO(mgr);
+}
+
+static const struct spi_device_id mpf_spi_ids[] = {
+	{ .name = "mpf-spi-fpga-mgr", },
+	{},
+};
+MODULE_DEVICE_TABLE(spi, mpf_spi_ids);
+
+#if IS_ENABLED(CONFIG_OF)
+static const struct of_device_id mpf_of_ids[] = {
+	{ .compatible = "microchip,mpf-spi-fpga-mgr" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mpf_of_ids);
+#endif /* IS_ENABLED(CONFIG_OF) */
+
+static struct spi_driver mpf_driver = {
+	.probe = mpf_probe,
+	.id_table = mpf_spi_ids,
+	.driver = {
+		.name = "microchip_mpf_spi_fpga_mgr",
+		.of_match_table = of_match_ptr(mpf_of_ids),
+	},
+};
+
+module_spi_driver(mpf_driver);
+
+MODULE_DESCRIPTION("Microchip Polarfire SPI FPGA Manager");
+MODULE_AUTHOR("Ivan Bornyakov <i.bornyakov@metrotek.ru>");
+MODULE_LICENSE("GPL");