From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- drivers/clk/ingenic/cgu.c | 851 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 851 insertions(+) create mode 100644 drivers/clk/ingenic/cgu.c (limited to 'drivers/clk/ingenic/cgu.c') diff --git a/drivers/clk/ingenic/cgu.c b/drivers/clk/ingenic/cgu.c new file mode 100644 index 000000000..1f7ba30f5 --- /dev/null +++ b/drivers/clk/ingenic/cgu.c @@ -0,0 +1,851 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Ingenic SoC CGU driver + * + * Copyright (c) 2013-2015 Imagination Technologies + * Author: Paul Burton + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cgu.h" + +#define MHZ (1000 * 1000) + +static inline const struct ingenic_cgu_clk_info * +to_clk_info(struct ingenic_clk *clk) +{ + return &clk->cgu->clock_info[clk->idx]; +} + +/** + * ingenic_cgu_gate_get() - get the value of clock gate register bit + * @cgu: reference to the CGU whose registers should be read + * @info: info struct describing the gate bit + * + * Retrieves the state of the clock gate bit described by info. The + * caller must hold cgu->lock. + * + * Return: true if the gate bit is set, else false. + */ +static inline bool +ingenic_cgu_gate_get(struct ingenic_cgu *cgu, + const struct ingenic_cgu_gate_info *info) +{ + return !!(readl(cgu->base + info->reg) & BIT(info->bit)) + ^ info->clear_to_gate; +} + +/** + * ingenic_cgu_gate_set() - set the value of clock gate register bit + * @cgu: reference to the CGU whose registers should be modified + * @info: info struct describing the gate bit + * @val: non-zero to gate a clock, otherwise zero + * + * Sets the given gate bit in order to gate or ungate a clock. + * + * The caller must hold cgu->lock. + */ +static inline void +ingenic_cgu_gate_set(struct ingenic_cgu *cgu, + const struct ingenic_cgu_gate_info *info, bool val) +{ + u32 clkgr = readl(cgu->base + info->reg); + + if (val ^ info->clear_to_gate) + clkgr |= BIT(info->bit); + else + clkgr &= ~BIT(info->bit); + + writel(clkgr, cgu->base + info->reg); +} + +/* + * PLL operations + */ + +static unsigned long +ingenic_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_pll_info *pll_info; + unsigned m, n, od, od_enc = 0; + bool bypass; + u32 ctl; + + BUG_ON(clk_info->type != CGU_CLK_PLL); + pll_info = &clk_info->pll; + + ctl = readl(cgu->base + pll_info->reg); + + m = (ctl >> pll_info->m_shift) & GENMASK(pll_info->m_bits - 1, 0); + m += pll_info->m_offset; + n = (ctl >> pll_info->n_shift) & GENMASK(pll_info->n_bits - 1, 0); + n += pll_info->n_offset; + + if (pll_info->od_bits > 0) { + od_enc = ctl >> pll_info->od_shift; + od_enc &= GENMASK(pll_info->od_bits - 1, 0); + } + + if (pll_info->bypass_bit >= 0) { + ctl = readl(cgu->base + pll_info->bypass_reg); + + bypass = !!(ctl & BIT(pll_info->bypass_bit)); + + if (bypass) + return parent_rate; + } + + for (od = 0; od < pll_info->od_max; od++) + if (pll_info->od_encoding[od] == od_enc) + break; + + /* if od_max = 0, od_bits should be 0 and od is fixed to 1. */ + if (pll_info->od_max == 0) + BUG_ON(pll_info->od_bits != 0); + else + BUG_ON(od == pll_info->od_max); + od++; + + return div_u64((u64)parent_rate * m * pll_info->rate_multiplier, + n * od); +} + +static void +ingenic_pll_calc_m_n_od(const struct ingenic_cgu_pll_info *pll_info, + unsigned long rate, unsigned long parent_rate, + unsigned int *pm, unsigned int *pn, unsigned int *pod) +{ + unsigned int m, n, od = 1; + + /* + * The frequency after the input divider must be between 10 and 50 MHz. + * The highest divider yields the best resolution. + */ + n = parent_rate / (10 * MHZ); + n = min_t(unsigned int, n, 1 << pll_info->n_bits); + n = max_t(unsigned int, n, pll_info->n_offset); + + m = (rate / MHZ) * od * n / (parent_rate / MHZ); + m = min_t(unsigned int, m, 1 << pll_info->m_bits); + m = max_t(unsigned int, m, pll_info->m_offset); + + *pm = m; + *pn = n; + *pod = od; +} + +static unsigned long +ingenic_pll_calc(const struct ingenic_cgu_clk_info *clk_info, + unsigned long rate, unsigned long parent_rate, + unsigned int *pm, unsigned int *pn, unsigned int *pod) +{ + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + unsigned int m, n, od; + + if (pll_info->calc_m_n_od) + (*pll_info->calc_m_n_od)(pll_info, rate, parent_rate, &m, &n, &od); + else + ingenic_pll_calc_m_n_od(pll_info, rate, parent_rate, &m, &n, &od); + + if (pm) + *pm = m; + if (pn) + *pn = n; + if (pod) + *pod = od; + + return div_u64((u64)parent_rate * m * pll_info->rate_multiplier, + n * od); +} + +static long +ingenic_pll_round_rate(struct clk_hw *hw, unsigned long req_rate, + unsigned long *prate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + + return ingenic_pll_calc(clk_info, req_rate, *prate, NULL, NULL, NULL); +} + +static inline int ingenic_pll_check_stable(struct ingenic_cgu *cgu, + const struct ingenic_cgu_pll_info *pll_info) +{ + u32 ctl; + + if (pll_info->stable_bit < 0) + return 0; + + return readl_poll_timeout(cgu->base + pll_info->reg, ctl, + ctl & BIT(pll_info->stable_bit), + 0, 100 * USEC_PER_MSEC); +} + +static int +ingenic_pll_set_rate(struct clk_hw *hw, unsigned long req_rate, + unsigned long parent_rate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + unsigned long rate, flags; + unsigned int m, n, od; + int ret = 0; + u32 ctl; + + rate = ingenic_pll_calc(clk_info, req_rate, parent_rate, + &m, &n, &od); + if (rate != req_rate) + pr_info("ingenic-cgu: request '%s' rate %luHz, actual %luHz\n", + clk_info->name, req_rate, rate); + + spin_lock_irqsave(&cgu->lock, flags); + ctl = readl(cgu->base + pll_info->reg); + + ctl &= ~(GENMASK(pll_info->m_bits - 1, 0) << pll_info->m_shift); + ctl |= (m - pll_info->m_offset) << pll_info->m_shift; + + ctl &= ~(GENMASK(pll_info->n_bits - 1, 0) << pll_info->n_shift); + ctl |= (n - pll_info->n_offset) << pll_info->n_shift; + + if (pll_info->od_bits > 0) { + ctl &= ~(GENMASK(pll_info->od_bits - 1, 0) << pll_info->od_shift); + ctl |= pll_info->od_encoding[od - 1] << pll_info->od_shift; + } + + writel(ctl, cgu->base + pll_info->reg); + + if (pll_info->set_rate_hook) + pll_info->set_rate_hook(pll_info, rate, parent_rate); + + /* If the PLL is enabled, verify that it's stable */ + if (pll_info->enable_bit >= 0 && (ctl & BIT(pll_info->enable_bit))) + ret = ingenic_pll_check_stable(cgu, pll_info); + + spin_unlock_irqrestore(&cgu->lock, flags); + + return ret; +} + +static int ingenic_pll_enable(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + unsigned long flags; + int ret; + u32 ctl; + + if (pll_info->enable_bit < 0) + return 0; + + spin_lock_irqsave(&cgu->lock, flags); + if (pll_info->bypass_bit >= 0) { + ctl = readl(cgu->base + pll_info->bypass_reg); + + ctl &= ~BIT(pll_info->bypass_bit); + + writel(ctl, cgu->base + pll_info->bypass_reg); + } + + ctl = readl(cgu->base + pll_info->reg); + + ctl |= BIT(pll_info->enable_bit); + + writel(ctl, cgu->base + pll_info->reg); + + ret = ingenic_pll_check_stable(cgu, pll_info); + spin_unlock_irqrestore(&cgu->lock, flags); + + return ret; +} + +static void ingenic_pll_disable(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + unsigned long flags; + u32 ctl; + + if (pll_info->enable_bit < 0) + return; + + spin_lock_irqsave(&cgu->lock, flags); + ctl = readl(cgu->base + pll_info->reg); + + ctl &= ~BIT(pll_info->enable_bit); + + writel(ctl, cgu->base + pll_info->reg); + spin_unlock_irqrestore(&cgu->lock, flags); +} + +static int ingenic_pll_is_enabled(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + u32 ctl; + + if (pll_info->enable_bit < 0) + return true; + + ctl = readl(cgu->base + pll_info->reg); + + return !!(ctl & BIT(pll_info->enable_bit)); +} + +static const struct clk_ops ingenic_pll_ops = { + .recalc_rate = ingenic_pll_recalc_rate, + .round_rate = ingenic_pll_round_rate, + .set_rate = ingenic_pll_set_rate, + + .enable = ingenic_pll_enable, + .disable = ingenic_pll_disable, + .is_enabled = ingenic_pll_is_enabled, +}; + +/* + * Operations for all non-PLL clocks + */ + +static u8 ingenic_clk_get_parent(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + u32 reg; + u8 i, hw_idx, idx = 0; + + if (clk_info->type & CGU_CLK_MUX) { + reg = readl(cgu->base + clk_info->mux.reg); + hw_idx = (reg >> clk_info->mux.shift) & + GENMASK(clk_info->mux.bits - 1, 0); + + /* + * Convert the hardware index to the parent index by skipping + * over any -1's in the parents array. + */ + for (i = 0; i < hw_idx; i++) { + if (clk_info->parents[i] != -1) + idx++; + } + } + + return idx; +} + +static int ingenic_clk_set_parent(struct clk_hw *hw, u8 idx) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + unsigned long flags; + u8 curr_idx, hw_idx, num_poss; + u32 reg, mask; + + if (clk_info->type & CGU_CLK_MUX) { + /* + * Convert the parent index to the hardware index by adding + * 1 for any -1 in the parents array preceding the given + * index. That is, we want the index of idx'th entry in + * clk_info->parents which does not equal -1. + */ + hw_idx = curr_idx = 0; + num_poss = 1 << clk_info->mux.bits; + for (; hw_idx < num_poss; hw_idx++) { + if (clk_info->parents[hw_idx] == -1) + continue; + if (curr_idx == idx) + break; + curr_idx++; + } + + /* idx should always be a valid parent */ + BUG_ON(curr_idx != idx); + + mask = GENMASK(clk_info->mux.bits - 1, 0); + mask <<= clk_info->mux.shift; + + spin_lock_irqsave(&cgu->lock, flags); + + /* write the register */ + reg = readl(cgu->base + clk_info->mux.reg); + reg &= ~mask; + reg |= hw_idx << clk_info->mux.shift; + writel(reg, cgu->base + clk_info->mux.reg); + + spin_unlock_irqrestore(&cgu->lock, flags); + return 0; + } + + return idx ? -EINVAL : 0; +} + +static unsigned long +ingenic_clk_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + unsigned long rate = parent_rate; + u32 div_reg, div; + u8 parent; + + if (clk_info->type & CGU_CLK_DIV) { + parent = ingenic_clk_get_parent(hw); + + if (!(clk_info->div.bypass_mask & BIT(parent))) { + div_reg = readl(cgu->base + clk_info->div.reg); + div = (div_reg >> clk_info->div.shift) & + GENMASK(clk_info->div.bits - 1, 0); + + if (clk_info->div.div_table) + div = clk_info->div.div_table[div]; + else + div = (div + 1) * clk_info->div.div; + + rate /= div; + } + } else if (clk_info->type & CGU_CLK_FIXDIV) { + rate /= clk_info->fixdiv.div; + } + + return rate; +} + +static unsigned int +ingenic_clk_calc_hw_div(const struct ingenic_cgu_clk_info *clk_info, + unsigned int div) +{ + unsigned int i, best_i = 0, best = (unsigned int)-1; + + for (i = 0; i < (1 << clk_info->div.bits) + && clk_info->div.div_table[i]; i++) { + if (clk_info->div.div_table[i] >= div && + clk_info->div.div_table[i] < best) { + best = clk_info->div.div_table[i]; + best_i = i; + + if (div == best) + break; + } + } + + return best_i; +} + +static unsigned +ingenic_clk_calc_div(struct clk_hw *hw, + const struct ingenic_cgu_clk_info *clk_info, + unsigned long parent_rate, unsigned long req_rate) +{ + unsigned int div, hw_div; + u8 parent; + + parent = ingenic_clk_get_parent(hw); + if (clk_info->div.bypass_mask & BIT(parent)) + return 1; + + /* calculate the divide */ + div = DIV_ROUND_UP(parent_rate, req_rate); + + if (clk_info->div.div_table) { + hw_div = ingenic_clk_calc_hw_div(clk_info, div); + + return clk_info->div.div_table[hw_div]; + } + + /* Impose hardware constraints */ + div = clamp_t(unsigned int, div, clk_info->div.div, + clk_info->div.div << clk_info->div.bits); + + /* + * If the divider value itself must be divided before being written to + * the divider register, we must ensure we don't have any bits set that + * would be lost as a result of doing so. + */ + div = DIV_ROUND_UP(div, clk_info->div.div); + div *= clk_info->div.div; + + return div; +} + +static long +ingenic_clk_round_rate(struct clk_hw *hw, unsigned long req_rate, + unsigned long *parent_rate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + unsigned int div = 1; + + if (clk_info->type & CGU_CLK_DIV) + div = ingenic_clk_calc_div(hw, clk_info, *parent_rate, req_rate); + else if (clk_info->type & CGU_CLK_FIXDIV) + div = clk_info->fixdiv.div; + else if (clk_hw_can_set_rate_parent(hw)) + *parent_rate = req_rate; + + return DIV_ROUND_UP(*parent_rate, div); +} + +static inline int ingenic_clk_check_stable(struct ingenic_cgu *cgu, + const struct ingenic_cgu_clk_info *clk_info) +{ + u32 reg; + + return readl_poll_timeout(cgu->base + clk_info->div.reg, reg, + !(reg & BIT(clk_info->div.busy_bit)), + 0, 100 * USEC_PER_MSEC); +} + +static int +ingenic_clk_set_rate(struct clk_hw *hw, unsigned long req_rate, + unsigned long parent_rate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + unsigned long rate, flags; + unsigned int hw_div, div; + u32 reg, mask; + int ret = 0; + + if (clk_info->type & CGU_CLK_DIV) { + div = ingenic_clk_calc_div(hw, clk_info, parent_rate, req_rate); + rate = DIV_ROUND_UP(parent_rate, div); + + if (rate != req_rate) + return -EINVAL; + + if (clk_info->div.div_table) + hw_div = ingenic_clk_calc_hw_div(clk_info, div); + else + hw_div = ((div / clk_info->div.div) - 1); + + spin_lock_irqsave(&cgu->lock, flags); + reg = readl(cgu->base + clk_info->div.reg); + + /* update the divide */ + mask = GENMASK(clk_info->div.bits - 1, 0); + reg &= ~(mask << clk_info->div.shift); + reg |= hw_div << clk_info->div.shift; + + /* clear the stop bit */ + if (clk_info->div.stop_bit != -1) + reg &= ~BIT(clk_info->div.stop_bit); + + /* set the change enable bit */ + if (clk_info->div.ce_bit != -1) + reg |= BIT(clk_info->div.ce_bit); + + /* update the hardware */ + writel(reg, cgu->base + clk_info->div.reg); + + /* wait for the change to take effect */ + if (clk_info->div.busy_bit != -1) + ret = ingenic_clk_check_stable(cgu, clk_info); + + spin_unlock_irqrestore(&cgu->lock, flags); + return ret; + } + + return -EINVAL; +} + +static int ingenic_clk_enable(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + unsigned long flags; + + if (clk_info->type & CGU_CLK_GATE) { + /* ungate the clock */ + spin_lock_irqsave(&cgu->lock, flags); + ingenic_cgu_gate_set(cgu, &clk_info->gate, false); + spin_unlock_irqrestore(&cgu->lock, flags); + + if (clk_info->gate.delay_us) + udelay(clk_info->gate.delay_us); + } + + return 0; +} + +static void ingenic_clk_disable(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + unsigned long flags; + + if (clk_info->type & CGU_CLK_GATE) { + /* gate the clock */ + spin_lock_irqsave(&cgu->lock, flags); + ingenic_cgu_gate_set(cgu, &clk_info->gate, true); + spin_unlock_irqrestore(&cgu->lock, flags); + } +} + +static int ingenic_clk_is_enabled(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + int enabled = 1; + + if (clk_info->type & CGU_CLK_GATE) + enabled = !ingenic_cgu_gate_get(cgu, &clk_info->gate); + + return enabled; +} + +static const struct clk_ops ingenic_clk_ops = { + .get_parent = ingenic_clk_get_parent, + .set_parent = ingenic_clk_set_parent, + + .recalc_rate = ingenic_clk_recalc_rate, + .round_rate = ingenic_clk_round_rate, + .set_rate = ingenic_clk_set_rate, + + .enable = ingenic_clk_enable, + .disable = ingenic_clk_disable, + .is_enabled = ingenic_clk_is_enabled, +}; + +/* + * Setup functions. + */ + +static int ingenic_register_clock(struct ingenic_cgu *cgu, unsigned idx) +{ + const struct ingenic_cgu_clk_info *clk_info = &cgu->clock_info[idx]; + struct clk_init_data clk_init; + struct ingenic_clk *ingenic_clk = NULL; + struct clk *clk, *parent; + const char *parent_names[4]; + unsigned caps, i, num_possible; + int err = -EINVAL; + + BUILD_BUG_ON(ARRAY_SIZE(clk_info->parents) > ARRAY_SIZE(parent_names)); + + if (clk_info->type == CGU_CLK_EXT) { + clk = of_clk_get_by_name(cgu->np, clk_info->name); + if (IS_ERR(clk)) { + pr_err("%s: no external clock '%s' provided\n", + __func__, clk_info->name); + err = -ENODEV; + goto out; + } + err = clk_register_clkdev(clk, clk_info->name, NULL); + if (err) { + clk_put(clk); + goto out; + } + cgu->clocks.clks[idx] = clk; + return 0; + } + + if (!clk_info->type) { + pr_err("%s: no clock type specified for '%s'\n", __func__, + clk_info->name); + goto out; + } + + ingenic_clk = kzalloc(sizeof(*ingenic_clk), GFP_KERNEL); + if (!ingenic_clk) { + err = -ENOMEM; + goto out; + } + + ingenic_clk->hw.init = &clk_init; + ingenic_clk->cgu = cgu; + ingenic_clk->idx = idx; + + clk_init.name = clk_info->name; + clk_init.flags = clk_info->flags; + clk_init.parent_names = parent_names; + + caps = clk_info->type; + + if (caps & CGU_CLK_DIV) { + caps &= ~CGU_CLK_DIV; + } else if (!(caps & CGU_CLK_CUSTOM)) { + /* pass rate changes to the parent clock */ + clk_init.flags |= CLK_SET_RATE_PARENT; + } + + if (caps & (CGU_CLK_MUX | CGU_CLK_CUSTOM)) { + clk_init.num_parents = 0; + + if (caps & CGU_CLK_MUX) + num_possible = 1 << clk_info->mux.bits; + else + num_possible = ARRAY_SIZE(clk_info->parents); + + for (i = 0; i < num_possible; i++) { + if (clk_info->parents[i] == -1) + continue; + + parent = cgu->clocks.clks[clk_info->parents[i]]; + parent_names[clk_init.num_parents] = + __clk_get_name(parent); + clk_init.num_parents++; + } + + BUG_ON(!clk_init.num_parents); + BUG_ON(clk_init.num_parents > ARRAY_SIZE(parent_names)); + } else { + BUG_ON(clk_info->parents[0] == -1); + clk_init.num_parents = 1; + parent = cgu->clocks.clks[clk_info->parents[0]]; + parent_names[0] = __clk_get_name(parent); + } + + if (caps & CGU_CLK_CUSTOM) { + clk_init.ops = clk_info->custom.clk_ops; + + caps &= ~CGU_CLK_CUSTOM; + + if (caps) { + pr_err("%s: custom clock may not be combined with type 0x%x\n", + __func__, caps); + goto out; + } + } else if (caps & CGU_CLK_PLL) { + clk_init.ops = &ingenic_pll_ops; + + caps &= ~CGU_CLK_PLL; + + if (caps) { + pr_err("%s: PLL may not be combined with type 0x%x\n", + __func__, caps); + goto out; + } + } else { + clk_init.ops = &ingenic_clk_ops; + } + + /* nothing to do for gates or fixed dividers */ + caps &= ~(CGU_CLK_GATE | CGU_CLK_FIXDIV); + + if (caps & CGU_CLK_MUX) { + if (!(caps & CGU_CLK_MUX_GLITCHFREE)) + clk_init.flags |= CLK_SET_PARENT_GATE; + + caps &= ~(CGU_CLK_MUX | CGU_CLK_MUX_GLITCHFREE); + } + + if (caps) { + pr_err("%s: unknown clock type 0x%x\n", __func__, caps); + goto out; + } + + clk = clk_register(NULL, &ingenic_clk->hw); + if (IS_ERR(clk)) { + pr_err("%s: failed to register clock '%s'\n", __func__, + clk_info->name); + err = PTR_ERR(clk); + goto out; + } + + err = clk_register_clkdev(clk, clk_info->name, NULL); + if (err) + goto out; + + cgu->clocks.clks[idx] = clk; +out: + if (err) + kfree(ingenic_clk); + return err; +} + +struct ingenic_cgu * +ingenic_cgu_new(const struct ingenic_cgu_clk_info *clock_info, + unsigned num_clocks, struct device_node *np) +{ + struct ingenic_cgu *cgu; + + cgu = kzalloc(sizeof(*cgu), GFP_KERNEL); + if (!cgu) + goto err_out; + + cgu->base = of_iomap(np, 0); + if (!cgu->base) { + pr_err("%s: failed to map CGU registers\n", __func__); + goto err_out_free; + } + + cgu->np = np; + cgu->clock_info = clock_info; + cgu->clocks.clk_num = num_clocks; + + spin_lock_init(&cgu->lock); + + return cgu; + +err_out_free: + kfree(cgu); +err_out: + return NULL; +} + +int ingenic_cgu_register_clocks(struct ingenic_cgu *cgu) +{ + unsigned i; + int err; + + cgu->clocks.clks = kcalloc(cgu->clocks.clk_num, sizeof(struct clk *), + GFP_KERNEL); + if (!cgu->clocks.clks) { + err = -ENOMEM; + goto err_out; + } + + for (i = 0; i < cgu->clocks.clk_num; i++) { + err = ingenic_register_clock(cgu, i); + if (err) + goto err_out_unregister; + } + + err = of_clk_add_provider(cgu->np, of_clk_src_onecell_get, + &cgu->clocks); + if (err) + goto err_out_unregister; + + return 0; + +err_out_unregister: + for (i = 0; i < cgu->clocks.clk_num; i++) { + if (!cgu->clocks.clks[i]) + continue; + if (cgu->clock_info[i].type & CGU_CLK_EXT) + clk_put(cgu->clocks.clks[i]); + else + clk_unregister(cgu->clocks.clks[i]); + } + kfree(cgu->clocks.clks); +err_out: + return err; +} -- cgit v1.2.3