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, 489 insertions, 0 deletions

diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c
new file mode 100644
index 000000000..3e62ade12
--- /dev/null
+++ b/drivers/clk/samsung/clk-cpu.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Thomas Abraham <thomas.ab@samsung.com>
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
+ *
+ * This file contains the utility function to register CPU clock for Samsung
+ * Exynos platforms. A CPU clock is defined as a clock supplied to a CPU or a
+ * group of CPUs. The CPU clock is typically derived from a hierarchy of clock
+ * blocks which includes mux and divider blocks. There are a number of other
+ * auxiliary clocks supplied to the CPU domain such as the debug blocks and AXI
+ * clock for CPU domain. The rates of these auxiliary clocks are related to the
+ * CPU clock rate and this relation is usually specified in the hardware manual
+ * of the SoC or supplied after the SoC characterization.
+ *
+ * The below implementation of the CPU clock allows the rate changes of the CPU
+ * clock and the corresponding rate changes of the auxillary clocks of the CPU
+ * domain. The platform clock driver provides a clock register configuration
+ * for each configurable rate which is then used to program the clock hardware
+ * registers to acheive a fast co-oridinated rate change for all the CPU domain
+ * clocks.
+ *
+ * On a rate change request for the CPU clock, the rate change is propagated
+ * upto the PLL supplying the clock to the CPU domain clock blocks. While the
+ * CPU domain PLL is reconfigured, the CPU domain clocks are driven using an
+ * alternate clock source. If required, the alternate clock source is divided
+ * down in order to keep the output clock rate within the previous OPP limits.
+*/
+
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include "clk-cpu.h"
+
+#define E4210_SRC_CPU		0x0
+#define E4210_STAT_CPU		0x200
+#define E4210_DIV_CPU0		0x300
+#define E4210_DIV_CPU1		0x304
+#define E4210_DIV_STAT_CPU0	0x400
+#define E4210_DIV_STAT_CPU1	0x404
+
+#define E5433_MUX_SEL2		0x008
+#define E5433_MUX_STAT2		0x208
+#define E5433_DIV_CPU0		0x400
+#define E5433_DIV_CPU1		0x404
+#define E5433_DIV_STAT_CPU0	0x500
+#define E5433_DIV_STAT_CPU1	0x504
+
+#define E4210_DIV0_RATIO0_MASK	0x7
+#define E4210_DIV1_HPM_MASK	(0x7 << 4)
+#define E4210_DIV1_COPY_MASK	(0x7 << 0)
+#define E4210_MUX_HPM_MASK	(1 << 20)
+#define E4210_DIV0_ATB_SHIFT	16
+#define E4210_DIV0_ATB_MASK	(DIV_MASK << E4210_DIV0_ATB_SHIFT)
+
+#define MAX_DIV			8
+#define DIV_MASK		7
+#define DIV_MASK_ALL		0xffffffff
+#define MUX_MASK		7
+
+/*
+ * Helper function to wait until divider(s) have stabilized after the divider
+ * value has changed.
+ */
+static void wait_until_divider_stable(void __iomem *div_reg, unsigned long mask)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(10);
+
+	do {
+		if (!(readl(div_reg) & mask))
+			return;
+	} while (time_before(jiffies, timeout));
+
+	if (!(readl(div_reg) & mask))
+		return;
+
+	pr_err("%s: timeout in divider stablization\n", __func__);
+}
+
+/*
+ * Helper function to wait until mux has stabilized after the mux selection
+ * value was changed.
+ */
+static void wait_until_mux_stable(void __iomem *mux_reg, u32 mux_pos,
+					unsigned long mux_value)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(10);
+
+	do {
+		if (((readl(mux_reg) >> mux_pos) & MUX_MASK) == mux_value)
+			return;
+	} while (time_before(jiffies, timeout));
+
+	if (((readl(mux_reg) >> mux_pos) & MUX_MASK) == mux_value)
+		return;
+
+	pr_err("%s: re-parenting mux timed-out\n", __func__);
+}
+
+/* common round rate callback useable for all types of CPU clocks */
+static long exynos_cpuclk_round_rate(struct clk_hw *hw,
+			unsigned long drate, unsigned long *prate)
+{
+	struct clk_hw *parent = clk_hw_get_parent(hw);
+	*prate = clk_hw_round_rate(parent, drate);
+	return *prate;
+}
+
+/* common recalc rate callback useable for all types of CPU clocks */
+static unsigned long exynos_cpuclk_recalc_rate(struct clk_hw *hw,
+			unsigned long parent_rate)
+{
+	/*
+	 * The CPU clock output (armclk) rate is the same as its parent
+	 * rate. Although there exist certain dividers inside the CPU
+	 * clock block that could be used to divide the parent clock,
+	 * the driver does not make use of them currently, except during
+	 * frequency transitions.
+	 */
+	return parent_rate;
+}
+
+static const struct clk_ops exynos_cpuclk_clk_ops = {
+	.recalc_rate = exynos_cpuclk_recalc_rate,
+	.round_rate = exynos_cpuclk_round_rate,
+};
+
+/*
+ * Helper function to set the 'safe' dividers for the CPU clock. The parameters
+ * div and mask contain the divider value and the register bit mask of the
+ * dividers to be programmed.
+ */
+static void exynos_set_safe_div(void __iomem *base, unsigned long div,
+					unsigned long mask)
+{
+	unsigned long div0;
+
+	div0 = readl(base + E4210_DIV_CPU0);
+	div0 = (div0 & ~mask) | (div & mask);
+	writel(div0, base + E4210_DIV_CPU0);
+	wait_until_divider_stable(base + E4210_DIV_STAT_CPU0, mask);
+}
+
+/* handler for pre-rate change notification from parent clock */
+static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg;
+	unsigned long alt_prate = clk_hw_get_rate(cpuclk->alt_parent);
+	unsigned long alt_div = 0, alt_div_mask = DIV_MASK;
+	unsigned long div0, div1 = 0, mux_reg;
+	unsigned long flags;
+
+	/* find out the divider values to use for clock data */
+	while ((cfg_data->prate * 1000) != ndata->new_rate) {
+		if (cfg_data->prate == 0)
+			return -EINVAL;
+		cfg_data++;
+	}
+
+	spin_lock_irqsave(cpuclk->lock, flags);
+
+	/*
+	 * For the selected PLL clock frequency, get the pre-defined divider
+	 * values. If the clock for sclk_hpm is not sourced from apll, then
+	 * the values for DIV_COPY and DIV_HPM dividers need not be set.
+	 */
+	div0 = cfg_data->div0;
+	if (cpuclk->flags & CLK_CPU_HAS_DIV1) {
+		div1 = cfg_data->div1;
+		if (readl(base + E4210_SRC_CPU) & E4210_MUX_HPM_MASK)
+			div1 = readl(base + E4210_DIV_CPU1) &
+				(E4210_DIV1_HPM_MASK | E4210_DIV1_COPY_MASK);
+	}
+
+	/*
+	 * If the old parent clock speed is less than the clock speed of
+	 * the alternate parent, then it should be ensured that at no point
+	 * the armclk speed is more than the old_prate until the dividers are
+	 * set.  Also workaround the issue of the dividers being set to lower
+	 * values before the parent clock speed is set to new lower speed
+	 * (this can result in too high speed of armclk output clocks).
+	 */
+	if (alt_prate > ndata->old_rate || ndata->old_rate > ndata->new_rate) {
+		unsigned long tmp_rate = min(ndata->old_rate, ndata->new_rate);
+
+		alt_div = DIV_ROUND_UP(alt_prate, tmp_rate) - 1;
+		WARN_ON(alt_div >= MAX_DIV);
+
+		if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) {
+			/*
+			 * In Exynos4210, ATB clock parent is also mout_core. So
+			 * ATB clock also needs to be mantained at safe speed.
+			 */
+			alt_div |= E4210_DIV0_ATB_MASK;
+			alt_div_mask |= E4210_DIV0_ATB_MASK;
+		}
+		exynos_set_safe_div(base, alt_div, alt_div_mask);
+		div0 |= alt_div;
+	}
+
+	/* select sclk_mpll as the alternate parent */
+	mux_reg = readl(base + E4210_SRC_CPU);
+	writel(mux_reg | (1 << 16), base + E4210_SRC_CPU);
+	wait_until_mux_stable(base + E4210_STAT_CPU, 16, 2);
+
+	/* alternate parent is active now. set the dividers */
+	writel(div0, base + E4210_DIV_CPU0);
+	wait_until_divider_stable(base + E4210_DIV_STAT_CPU0, DIV_MASK_ALL);
+
+	if (cpuclk->flags & CLK_CPU_HAS_DIV1) {
+		writel(div1, base + E4210_DIV_CPU1);
+		wait_until_divider_stable(base + E4210_DIV_STAT_CPU1,
+				DIV_MASK_ALL);
+	}
+
+	spin_unlock_irqrestore(cpuclk->lock, flags);
+	return 0;
+}
+
+/* handler for post-rate change notification from parent clock */
+static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg;
+	unsigned long div = 0, div_mask = DIV_MASK;
+	unsigned long mux_reg;
+	unsigned long flags;
+
+	/* find out the divider values to use for clock data */
+	if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) {
+		while ((cfg_data->prate * 1000) != ndata->new_rate) {
+			if (cfg_data->prate == 0)
+				return -EINVAL;
+			cfg_data++;
+		}
+	}
+
+	spin_lock_irqsave(cpuclk->lock, flags);
+
+	/* select mout_apll as the alternate parent */
+	mux_reg = readl(base + E4210_SRC_CPU);
+	writel(mux_reg & ~(1 << 16), base + E4210_SRC_CPU);
+	wait_until_mux_stable(base + E4210_STAT_CPU, 16, 1);
+
+	if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) {
+		div |= (cfg_data->div0 & E4210_DIV0_ATB_MASK);
+		div_mask |= E4210_DIV0_ATB_MASK;
+	}
+
+	exynos_set_safe_div(base, div, div_mask);
+	spin_unlock_irqrestore(cpuclk->lock, flags);
+	return 0;
+}
+
+/*
+ * Helper function to set the 'safe' dividers for the CPU clock. The parameters
+ * div and mask contain the divider value and the register bit mask of the
+ * dividers to be programmed.
+ */
+static void exynos5433_set_safe_div(void __iomem *base, unsigned long div,
+					unsigned long mask)
+{
+	unsigned long div0;
+
+	div0 = readl(base + E5433_DIV_CPU0);
+	div0 = (div0 & ~mask) | (div & mask);
+	writel(div0, base + E5433_DIV_CPU0);
+	wait_until_divider_stable(base + E5433_DIV_STAT_CPU0, mask);
+}
+
+/* handler for pre-rate change notification from parent clock */
+static int exynos5433_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg;
+	unsigned long alt_prate = clk_hw_get_rate(cpuclk->alt_parent);
+	unsigned long alt_div = 0, alt_div_mask = DIV_MASK;
+	unsigned long div0, div1 = 0, mux_reg;
+	unsigned long flags;
+
+	/* find out the divider values to use for clock data */
+	while ((cfg_data->prate * 1000) != ndata->new_rate) {
+		if (cfg_data->prate == 0)
+			return -EINVAL;
+		cfg_data++;
+	}
+
+	spin_lock_irqsave(cpuclk->lock, flags);
+
+	/*
+	 * For the selected PLL clock frequency, get the pre-defined divider
+	 * values.
+	 */
+	div0 = cfg_data->div0;
+	div1 = cfg_data->div1;
+
+	/*
+	 * If the old parent clock speed is less than the clock speed of
+	 * the alternate parent, then it should be ensured that at no point
+	 * the armclk speed is more than the old_prate until the dividers are
+	 * set.  Also workaround the issue of the dividers being set to lower
+	 * values before the parent clock speed is set to new lower speed
+	 * (this can result in too high speed of armclk output clocks).
+	 */
+	if (alt_prate > ndata->old_rate || ndata->old_rate > ndata->new_rate) {
+		unsigned long tmp_rate = min(ndata->old_rate, ndata->new_rate);
+
+		alt_div = DIV_ROUND_UP(alt_prate, tmp_rate) - 1;
+		WARN_ON(alt_div >= MAX_DIV);
+
+		exynos5433_set_safe_div(base, alt_div, alt_div_mask);
+		div0 |= alt_div;
+	}
+
+	/* select the alternate parent */
+	mux_reg = readl(base + E5433_MUX_SEL2);
+	writel(mux_reg | 1, base + E5433_MUX_SEL2);
+	wait_until_mux_stable(base + E5433_MUX_STAT2, 0, 2);
+
+	/* alternate parent is active now. set the dividers */
+	writel(div0, base + E5433_DIV_CPU0);
+	wait_until_divider_stable(base + E5433_DIV_STAT_CPU0, DIV_MASK_ALL);
+
+	writel(div1, base + E5433_DIV_CPU1);
+	wait_until_divider_stable(base + E5433_DIV_STAT_CPU1, DIV_MASK_ALL);
+
+	spin_unlock_irqrestore(cpuclk->lock, flags);
+	return 0;
+}
+
+/* handler for post-rate change notification from parent clock */
+static int exynos5433_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
+			struct exynos_cpuclk *cpuclk, void __iomem *base)
+{
+	unsigned long div = 0, div_mask = DIV_MASK;
+	unsigned long mux_reg;
+	unsigned long flags;
+
+	spin_lock_irqsave(cpuclk->lock, flags);
+
+	/* select apll as the alternate parent */
+	mux_reg = readl(base + E5433_MUX_SEL2);
+	writel(mux_reg & ~1, base + E5433_MUX_SEL2);
+	wait_until_mux_stable(base + E5433_MUX_STAT2, 0, 1);
+
+	exynos5433_set_safe_div(base, div, div_mask);
+	spin_unlock_irqrestore(cpuclk->lock, flags);
+	return 0;
+}
+
+/*
+ * This notifier function is called for the pre-rate and post-rate change
+ * notifications of the parent clock of cpuclk.
+ */
+static int exynos_cpuclk_notifier_cb(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct exynos_cpuclk *cpuclk;
+	void __iomem *base;
+	int err = 0;
+
+	cpuclk = container_of(nb, struct exynos_cpuclk, clk_nb);
+	base = cpuclk->ctrl_base;
+
+	if (event == PRE_RATE_CHANGE)
+		err = exynos_cpuclk_pre_rate_change(ndata, cpuclk, base);
+	else if (event == POST_RATE_CHANGE)
+		err = exynos_cpuclk_post_rate_change(ndata, cpuclk, base);
+
+	return notifier_from_errno(err);
+}
+
+/*
+ * This notifier function is called for the pre-rate and post-rate change
+ * notifications of the parent clock of cpuclk.
+ */
+static int exynos5433_cpuclk_notifier_cb(struct notifier_block *nb,
+				unsigned long event, void *data)
+{
+	struct clk_notifier_data *ndata = data;
+	struct exynos_cpuclk *cpuclk;
+	void __iomem *base;
+	int err = 0;
+
+	cpuclk = container_of(nb, struct exynos_cpuclk, clk_nb);
+	base = cpuclk->ctrl_base;
+
+	if (event == PRE_RATE_CHANGE)
+		err = exynos5433_cpuclk_pre_rate_change(ndata, cpuclk, base);
+	else if (event == POST_RATE_CHANGE)
+		err = exynos5433_cpuclk_post_rate_change(ndata, cpuclk, base);
+
+	return notifier_from_errno(err);
+}
+
+/* helper function to register a CPU clock */
+static int __init exynos_register_cpu_clock(struct samsung_clk_provider *ctx,
+		unsigned int lookup_id, const char *name,
+		const struct clk_hw *parent, const struct clk_hw *alt_parent,
+		unsigned long offset, const struct exynos_cpuclk_cfg_data *cfg,
+		unsigned long num_cfgs, unsigned long flags)
+{
+	struct exynos_cpuclk *cpuclk;
+	struct clk_init_data init;
+	const char *parent_name;
+	int ret = 0;
+
+	if (IS_ERR(parent) || IS_ERR(alt_parent)) {
+		pr_err("%s: invalid parent clock(s)\n", __func__);
+		return -EINVAL;
+	}
+
+	cpuclk = kzalloc(sizeof(*cpuclk), GFP_KERNEL);
+	if (!cpuclk)
+		return -ENOMEM;
+
+	parent_name = clk_hw_get_name(parent);
+
+	init.name = name;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	init.ops = &exynos_cpuclk_clk_ops;
+
+	cpuclk->alt_parent = alt_parent;
+	cpuclk->hw.init = &init;
+	cpuclk->ctrl_base = ctx->reg_base + offset;
+	cpuclk->lock = &ctx->lock;
+	cpuclk->flags = flags;
+	if (flags & CLK_CPU_HAS_E5433_REGS_LAYOUT)
+		cpuclk->clk_nb.notifier_call = exynos5433_cpuclk_notifier_cb;
+	else
+		cpuclk->clk_nb.notifier_call = exynos_cpuclk_notifier_cb;
+
+
+	ret = clk_notifier_register(parent->clk, &cpuclk->clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for %s\n",
+				__func__, name);
+		goto free_cpuclk;
+	}
+
+	cpuclk->cfg = kmemdup(cfg, sizeof(*cfg) * num_cfgs, GFP_KERNEL);
+	if (!cpuclk->cfg) {
+		ret = -ENOMEM;
+		goto unregister_clk_nb;
+	}
+
+	ret = clk_hw_register(NULL, &cpuclk->hw);
+	if (ret) {
+		pr_err("%s: could not register cpuclk %s\n", __func__,	name);
+		goto free_cpuclk_data;
+	}
+
+	samsung_clk_add_lookup(ctx, &cpuclk->hw, lookup_id);
+	return 0;
+
+free_cpuclk_data:
+	kfree(cpuclk->cfg);
+unregister_clk_nb:
+	clk_notifier_unregister(parent->clk, &cpuclk->clk_nb);
+free_cpuclk:
+	kfree(cpuclk);
+	return ret;
+}
+
+void __init samsung_clk_register_cpu(struct samsung_clk_provider *ctx,
+		const struct samsung_cpu_clock *list, unsigned int nr_clk)
+{
+	unsigned int idx;
+	unsigned int num_cfgs;
+	struct clk_hw **hws = ctx->clk_data.hws;
+
+	for (idx = 0; idx < nr_clk; idx++, list++) {
+		/* find count of configuration rates in cfg */
+		for (num_cfgs = 0; list->cfg[num_cfgs].prate != 0; )
+			num_cfgs++;
+
+		exynos_register_cpu_clock(ctx, list->id, list->name, hws[list->parent_id],
+				hws[list->alt_parent_id], list->offset, list->cfg, num_cfgs,
+				list->flags);
+	}
+}