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, 356 insertions, 0 deletions

diff --git a/drivers/clk/spear/clk-vco-pll.c b/drivers/clk/spear/clk-vco-pll.c
new file mode 100644
index 000000000..348eeab0a
--- /dev/null
+++ b/drivers/clk/spear/clk-vco-pll.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 ST Microelectronics
+ * Viresh Kumar <vireshk@kernel.org>
+ *
+ * VCO-PLL clock implementation
+ */
+
+#define pr_fmt(fmt) "clk-vco-pll: " fmt
+
+#include <linux/clk-provider.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include "clk.h"
+
+/*
+ * DOC: VCO-PLL clock
+ *
+ * VCO and PLL rate are derived from following equations:
+ *
+ * In normal mode
+ * vco = (2 * M[15:8] * Fin)/N
+ *
+ * In Dithered mode
+ * vco = (2 * M[15:0] * Fin)/(256 * N)
+ *
+ * pll_rate = pll/2^p
+ *
+ * vco and pll are very closely bound to each other, "vco needs to program:
+ * mode, m & n" and "pll needs to program p", both share common enable/disable
+ * logic.
+ *
+ * clk_register_vco_pll() registers instances of both vco & pll.
+ * CLK_SET_RATE_PARENT flag is forced for pll, as it will always pass its
+ * set_rate to vco. A single rate table exists for both the clocks, which
+ * configures m, n and p.
+ */
+
+/* PLL_CTR register masks */
+#define PLL_MODE_NORMAL		0
+#define PLL_MODE_FRACTION	1
+#define PLL_MODE_DITH_DSM	2
+#define PLL_MODE_DITH_SSM	3
+#define PLL_MODE_MASK		3
+#define PLL_MODE_SHIFT		3
+#define PLL_ENABLE		2
+
+#define PLL_LOCK_SHIFT		0
+#define PLL_LOCK_MASK		1
+
+/* PLL FRQ register masks */
+#define PLL_NORM_FDBK_M_MASK	0xFF
+#define PLL_NORM_FDBK_M_SHIFT	24
+#define PLL_DITH_FDBK_M_MASK	0xFFFF
+#define PLL_DITH_FDBK_M_SHIFT	16
+#define PLL_DIV_P_MASK		0x7
+#define PLL_DIV_P_SHIFT		8
+#define PLL_DIV_N_MASK		0xFF
+#define PLL_DIV_N_SHIFT		0
+
+#define to_clk_vco(_hw) container_of(_hw, struct clk_vco, hw)
+#define to_clk_pll(_hw) container_of(_hw, struct clk_pll, hw)
+
+/* Calculates pll clk rate for specific value of mode, m, n and p */
+static unsigned long pll_calc_rate(struct pll_rate_tbl *rtbl,
+		unsigned long prate, int index, unsigned long *pll_rate)
+{
+	unsigned long rate = prate;
+	unsigned int mode;
+
+	mode = rtbl[index].mode ? 256 : 1;
+	rate = (((2 * rate / 10000) * rtbl[index].m) / (mode * rtbl[index].n));
+
+	if (pll_rate)
+		*pll_rate = (rate / (1 << rtbl[index].p)) * 10000;
+
+	return rate * 10000;
+}
+
+static long clk_pll_round_rate_index(struct clk_hw *hw, unsigned long drate,
+				unsigned long *prate, int *index)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	unsigned long prev_rate, vco_prev_rate, rate = 0;
+	unsigned long vco_parent_rate =
+		clk_hw_get_rate(clk_hw_get_parent(clk_hw_get_parent(hw)));
+
+	if (!prate) {
+		pr_err("%s: prate is must for pll clk\n", __func__);
+		return -EINVAL;
+	}
+
+	for (*index = 0; *index < pll->vco->rtbl_cnt; (*index)++) {
+		prev_rate = rate;
+		vco_prev_rate = *prate;
+		*prate = pll_calc_rate(pll->vco->rtbl, vco_parent_rate, *index,
+				&rate);
+		if (drate < rate) {
+			/* previous clock was best */
+			if (*index) {
+				rate = prev_rate;
+				*prate = vco_prev_rate;
+				(*index)--;
+			}
+			break;
+		}
+	}
+
+	return rate;
+}
+
+static long clk_pll_round_rate(struct clk_hw *hw, unsigned long drate,
+				unsigned long *prate)
+{
+	int unused;
+
+	return clk_pll_round_rate_index(hw, drate, prate, &unused);
+}
+
+static unsigned long clk_pll_recalc_rate(struct clk_hw *hw, unsigned long
+		parent_rate)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	unsigned long flags = 0;
+	unsigned int p;
+
+	if (pll->vco->lock)
+		spin_lock_irqsave(pll->vco->lock, flags);
+
+	p = readl_relaxed(pll->vco->cfg_reg);
+
+	if (pll->vco->lock)
+		spin_unlock_irqrestore(pll->vco->lock, flags);
+
+	p = (p >> PLL_DIV_P_SHIFT) & PLL_DIV_P_MASK;
+
+	return parent_rate / (1 << p);
+}
+
+static int clk_pll_set_rate(struct clk_hw *hw, unsigned long drate,
+				unsigned long prate)
+{
+	struct clk_pll *pll = to_clk_pll(hw);
+	struct pll_rate_tbl *rtbl = pll->vco->rtbl;
+	unsigned long flags = 0, val;
+	int i = 0;
+
+	clk_pll_round_rate_index(hw, drate, NULL, &i);
+
+	if (pll->vco->lock)
+		spin_lock_irqsave(pll->vco->lock, flags);
+
+	val = readl_relaxed(pll->vco->cfg_reg);
+	val &= ~(PLL_DIV_P_MASK << PLL_DIV_P_SHIFT);
+	val |= (rtbl[i].p & PLL_DIV_P_MASK) << PLL_DIV_P_SHIFT;
+	writel_relaxed(val, pll->vco->cfg_reg);
+
+	if (pll->vco->lock)
+		spin_unlock_irqrestore(pll->vco->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops clk_pll_ops = {
+	.recalc_rate = clk_pll_recalc_rate,
+	.round_rate = clk_pll_round_rate,
+	.set_rate = clk_pll_set_rate,
+};
+
+static inline unsigned long vco_calc_rate(struct clk_hw *hw,
+		unsigned long prate, int index)
+{
+	struct clk_vco *vco = to_clk_vco(hw);
+
+	return pll_calc_rate(vco->rtbl, prate, index, NULL);
+}
+
+static long clk_vco_round_rate(struct clk_hw *hw, unsigned long drate,
+		unsigned long *prate)
+{
+	struct clk_vco *vco = to_clk_vco(hw);
+	int unused;
+
+	return clk_round_rate_index(hw, drate, *prate, vco_calc_rate,
+			vco->rtbl_cnt, &unused);
+}
+
+static unsigned long clk_vco_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct clk_vco *vco = to_clk_vco(hw);
+	unsigned long flags = 0;
+	unsigned int num = 2, den = 0, val, mode = 0;
+
+	if (vco->lock)
+		spin_lock_irqsave(vco->lock, flags);
+
+	mode = (readl_relaxed(vco->mode_reg) >> PLL_MODE_SHIFT) & PLL_MODE_MASK;
+
+	val = readl_relaxed(vco->cfg_reg);
+
+	if (vco->lock)
+		spin_unlock_irqrestore(vco->lock, flags);
+
+	den = (val >> PLL_DIV_N_SHIFT) & PLL_DIV_N_MASK;
+
+	/* calculate numerator & denominator */
+	if (!mode) {
+		/* Normal mode */
+		num *= (val >> PLL_NORM_FDBK_M_SHIFT) & PLL_NORM_FDBK_M_MASK;
+	} else {
+		/* Dithered mode */
+		num *= (val >> PLL_DITH_FDBK_M_SHIFT) & PLL_DITH_FDBK_M_MASK;
+		den *= 256;
+	}
+
+	if (!den) {
+		WARN(1, "%s: denominator can't be zero\n", __func__);
+		return 0;
+	}
+
+	return (((parent_rate / 10000) * num) / den) * 10000;
+}
+
+/* Configures new clock rate of vco */
+static int clk_vco_set_rate(struct clk_hw *hw, unsigned long drate,
+				unsigned long prate)
+{
+	struct clk_vco *vco = to_clk_vco(hw);
+	struct pll_rate_tbl *rtbl = vco->rtbl;
+	unsigned long flags = 0, val;
+	int i;
+
+	clk_round_rate_index(hw, drate, prate, vco_calc_rate, vco->rtbl_cnt,
+			&i);
+
+	if (vco->lock)
+		spin_lock_irqsave(vco->lock, flags);
+
+	val = readl_relaxed(vco->mode_reg);
+	val &= ~(PLL_MODE_MASK << PLL_MODE_SHIFT);
+	val |= (rtbl[i].mode & PLL_MODE_MASK) << PLL_MODE_SHIFT;
+	writel_relaxed(val, vco->mode_reg);
+
+	val = readl_relaxed(vco->cfg_reg);
+	val &= ~(PLL_DIV_N_MASK << PLL_DIV_N_SHIFT);
+	val |= (rtbl[i].n & PLL_DIV_N_MASK) << PLL_DIV_N_SHIFT;
+
+	val &= ~(PLL_DITH_FDBK_M_MASK << PLL_DITH_FDBK_M_SHIFT);
+	if (rtbl[i].mode)
+		val |= (rtbl[i].m & PLL_DITH_FDBK_M_MASK) <<
+			PLL_DITH_FDBK_M_SHIFT;
+	else
+		val |= (rtbl[i].m & PLL_NORM_FDBK_M_MASK) <<
+			PLL_NORM_FDBK_M_SHIFT;
+
+	writel_relaxed(val, vco->cfg_reg);
+
+	if (vco->lock)
+		spin_unlock_irqrestore(vco->lock, flags);
+
+	return 0;
+}
+
+static const struct clk_ops clk_vco_ops = {
+	.recalc_rate = clk_vco_recalc_rate,
+	.round_rate = clk_vco_round_rate,
+	.set_rate = clk_vco_set_rate,
+};
+
+struct clk *clk_register_vco_pll(const char *vco_name, const char *pll_name,
+		const char *vco_gate_name, const char *parent_name,
+		unsigned long flags, void __iomem *mode_reg, void __iomem
+		*cfg_reg, struct pll_rate_tbl *rtbl, u8 rtbl_cnt,
+		spinlock_t *lock, struct clk **pll_clk,
+		struct clk **vco_gate_clk)
+{
+	struct clk_vco *vco;
+	struct clk_pll *pll;
+	struct clk *vco_clk, *tpll_clk, *tvco_gate_clk;
+	struct clk_init_data vco_init, pll_init;
+	const char **vco_parent_name;
+
+	if (!vco_name || !pll_name || !parent_name || !mode_reg || !cfg_reg ||
+			!rtbl || !rtbl_cnt) {
+		pr_err("Invalid arguments passed");
+		return ERR_PTR(-EINVAL);
+	}
+
+	vco = kzalloc(sizeof(*vco), GFP_KERNEL);
+	if (!vco)
+		return ERR_PTR(-ENOMEM);
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (!pll)
+		goto free_vco;
+
+	/* struct clk_vco assignments */
+	vco->mode_reg = mode_reg;
+	vco->cfg_reg = cfg_reg;
+	vco->rtbl = rtbl;
+	vco->rtbl_cnt = rtbl_cnt;
+	vco->lock = lock;
+	vco->hw.init = &vco_init;
+
+	pll->vco = vco;
+	pll->hw.init = &pll_init;
+
+	if (vco_gate_name) {
+		tvco_gate_clk = clk_register_gate(NULL, vco_gate_name,
+				parent_name, 0, mode_reg, PLL_ENABLE, 0, lock);
+		if (IS_ERR_OR_NULL(tvco_gate_clk))
+			goto free_pll;
+
+		if (vco_gate_clk)
+			*vco_gate_clk = tvco_gate_clk;
+		vco_parent_name = &vco_gate_name;
+	} else {
+		vco_parent_name = &parent_name;
+	}
+
+	vco_init.name = vco_name;
+	vco_init.ops = &clk_vco_ops;
+	vco_init.flags = flags;
+	vco_init.parent_names = vco_parent_name;
+	vco_init.num_parents = 1;
+
+	pll_init.name = pll_name;
+	pll_init.ops = &clk_pll_ops;
+	pll_init.flags = CLK_SET_RATE_PARENT;
+	pll_init.parent_names = &vco_name;
+	pll_init.num_parents = 1;
+
+	vco_clk = clk_register(NULL, &vco->hw);
+	if (IS_ERR_OR_NULL(vco_clk))
+		goto free_pll;
+
+	tpll_clk = clk_register(NULL, &pll->hw);
+	if (IS_ERR_OR_NULL(tpll_clk))
+		goto free_pll;
+
+	if (pll_clk)
+		*pll_clk = tpll_clk;
+
+	return vco_clk;
+
+free_pll:
+	kfree(pll);
+free_vco:
+	kfree(vco);
+
+	pr_err("Failed to register vco pll clock\n");
+
+	return ERR_PTR(-ENOMEM);
+}