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(). ... --- arch/arm/mach-versatile/spc.c | 590 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 590 insertions(+) create mode 100644 arch/arm/mach-versatile/spc.c (limited to 'arch/arm/mach-versatile/spc.c') diff --git a/arch/arm/mach-versatile/spc.c b/arch/arm/mach-versatile/spc.c new file mode 100644 index 000000000..5e44170e1 --- /dev/null +++ b/arch/arm/mach-versatile/spc.c @@ -0,0 +1,590 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Versatile Express Serial Power Controller (SPC) support + * + * Copyright (C) 2013 ARM Ltd. + * + * Authors: Sudeep KarkadaNagesha + * Achin Gupta + * Lorenzo Pieralisi + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "spc.h" + +#define SPCLOG "vexpress-spc: " + +#define PERF_LVL_A15 0x00 +#define PERF_REQ_A15 0x04 +#define PERF_LVL_A7 0x08 +#define PERF_REQ_A7 0x0c +#define COMMS 0x10 +#define COMMS_REQ 0x14 +#define PWC_STATUS 0x18 +#define PWC_FLAG 0x1c + +/* SPC wake-up IRQs status and mask */ +#define WAKE_INT_MASK 0x24 +#define WAKE_INT_RAW 0x28 +#define WAKE_INT_STAT 0x2c +/* SPC power down registers */ +#define A15_PWRDN_EN 0x30 +#define A7_PWRDN_EN 0x34 +/* SPC per-CPU mailboxes */ +#define A15_BX_ADDR0 0x68 +#define A7_BX_ADDR0 0x78 + +/* SPC CPU/cluster reset statue */ +#define STANDBYWFI_STAT 0x3c +#define STANDBYWFI_STAT_A15_CPU_MASK(cpu) (1 << (cpu)) +#define STANDBYWFI_STAT_A7_CPU_MASK(cpu) (1 << (3 + (cpu))) + +/* SPC system config interface registers */ +#define SYSCFG_WDATA 0x70 +#define SYSCFG_RDATA 0x74 + +/* A15/A7 OPP virtual register base */ +#define A15_PERFVAL_BASE 0xC10 +#define A7_PERFVAL_BASE 0xC30 + +/* Config interface control bits */ +#define SYSCFG_START BIT(31) +#define SYSCFG_SCC (6 << 20) +#define SYSCFG_STAT (14 << 20) + +/* wake-up interrupt masks */ +#define GBL_WAKEUP_INT_MSK (0x3 << 10) + +/* TC2 static dual-cluster configuration */ +#define MAX_CLUSTERS 2 + +/* + * Even though the SPC takes max 3-5 ms to complete any OPP/COMMS + * operation, the operation could start just before jiffie is about + * to be incremented. So setting timeout value of 20ms = 2jiffies@100Hz + */ +#define TIMEOUT_US 20000 + +#define MAX_OPPS 8 +#define CA15_DVFS 0 +#define CA7_DVFS 1 +#define SPC_SYS_CFG 2 +#define STAT_COMPLETE(type) ((1 << 0) << (type << 2)) +#define STAT_ERR(type) ((1 << 1) << (type << 2)) +#define RESPONSE_MASK(type) (STAT_COMPLETE(type) | STAT_ERR(type)) + +struct ve_spc_opp { + unsigned long freq; + unsigned long u_volt; +}; + +struct ve_spc_drvdata { + void __iomem *baseaddr; + /* + * A15s cluster identifier + * It corresponds to A15 processors MPIDR[15:8] bitfield + */ + u32 a15_clusid; + uint32_t cur_rsp_mask; + uint32_t cur_rsp_stat; + struct semaphore sem; + struct completion done; + struct ve_spc_opp *opps[MAX_CLUSTERS]; + int num_opps[MAX_CLUSTERS]; +}; + +static struct ve_spc_drvdata *info; + +static inline bool cluster_is_a15(u32 cluster) +{ + return cluster == info->a15_clusid; +} + +/** + * ve_spc_global_wakeup_irq() - sets/clears global wakeup IRQs + * + * @set: if true, global wake-up IRQs are set, if false they are cleared + * + * Function to set/clear global wakeup IRQs. Not protected by locking since + * it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. + */ +void ve_spc_global_wakeup_irq(bool set) +{ + u32 reg; + + reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK); + + if (set) + reg |= GBL_WAKEUP_INT_MSK; + else + reg &= ~GBL_WAKEUP_INT_MSK; + + writel_relaxed(reg, info->baseaddr + WAKE_INT_MASK); +} + +/** + * ve_spc_cpu_wakeup_irq() - sets/clears per-CPU wake-up IRQs + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @cpu: mpidr[7:0] bitfield describing cpu affinity level + * @set: if true, wake-up IRQs are set, if false they are cleared + * + * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since + * it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. + */ +void ve_spc_cpu_wakeup_irq(u32 cluster, u32 cpu, bool set) +{ + u32 mask, reg; + + if (cluster >= MAX_CLUSTERS) + return; + + mask = BIT(cpu); + + if (!cluster_is_a15(cluster)) + mask <<= 4; + + reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK); + + if (set) + reg |= mask; + else + reg &= ~mask; + + writel_relaxed(reg, info->baseaddr + WAKE_INT_MASK); +} + +/** + * ve_spc_set_resume_addr() - set the jump address used for warm boot + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @cpu: mpidr[7:0] bitfield describing cpu affinity level + * @addr: physical resume address + */ +void ve_spc_set_resume_addr(u32 cluster, u32 cpu, u32 addr) +{ + void __iomem *baseaddr; + + if (cluster >= MAX_CLUSTERS) + return; + + if (cluster_is_a15(cluster)) + baseaddr = info->baseaddr + A15_BX_ADDR0 + (cpu << 2); + else + baseaddr = info->baseaddr + A7_BX_ADDR0 + (cpu << 2); + + writel_relaxed(addr, baseaddr); +} + +/** + * ve_spc_powerdown() - enables/disables cluster powerdown + * + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * @enable: if true enables powerdown, if false disables it + * + * Function to enable/disable cluster powerdown. Not protected by locking + * since it might be used in code paths where normal cacheable locks are not + * working. Locking must be provided by the caller to ensure atomicity. + */ +void ve_spc_powerdown(u32 cluster, bool enable) +{ + u32 pwdrn_reg; + + if (cluster >= MAX_CLUSTERS) + return; + + pwdrn_reg = cluster_is_a15(cluster) ? A15_PWRDN_EN : A7_PWRDN_EN; + writel_relaxed(enable, info->baseaddr + pwdrn_reg); +} + +static u32 standbywfi_cpu_mask(u32 cpu, u32 cluster) +{ + return cluster_is_a15(cluster) ? + STANDBYWFI_STAT_A15_CPU_MASK(cpu) + : STANDBYWFI_STAT_A7_CPU_MASK(cpu); +} + +/** + * ve_spc_cpu_in_wfi() - Checks if the specified CPU is in WFI or not + * + * @cpu: mpidr[7:0] bitfield describing CPU affinity level within cluster + * @cluster: mpidr[15:8] bitfield describing cluster affinity level + * + * @return: non-zero if and only if the specified CPU is in WFI + * + * Take care when interpreting the result of this function: a CPU might + * be in WFI temporarily due to idle, and is not necessarily safely + * parked. + */ +int ve_spc_cpu_in_wfi(u32 cpu, u32 cluster) +{ + int ret; + u32 mask = standbywfi_cpu_mask(cpu, cluster); + + if (cluster >= MAX_CLUSTERS) + return 1; + + ret = readl_relaxed(info->baseaddr + STANDBYWFI_STAT); + + pr_debug("%s: PCFGREG[0x%X] = 0x%08X, mask = 0x%X\n", + __func__, STANDBYWFI_STAT, ret, mask); + + return ret & mask; +} + +static int ve_spc_get_performance(int cluster, u32 *freq) +{ + struct ve_spc_opp *opps = info->opps[cluster]; + u32 perf_cfg_reg = 0; + u32 perf; + + perf_cfg_reg = cluster_is_a15(cluster) ? PERF_LVL_A15 : PERF_LVL_A7; + + perf = readl_relaxed(info->baseaddr + perf_cfg_reg); + if (perf >= info->num_opps[cluster]) + return -EINVAL; + + opps += perf; + *freq = opps->freq; + + return 0; +} + +/* find closest match to given frequency in OPP table */ +static int ve_spc_round_performance(int cluster, u32 freq) +{ + int idx, max_opp = info->num_opps[cluster]; + struct ve_spc_opp *opps = info->opps[cluster]; + u32 fmin = 0, fmax = ~0, ftmp; + + freq /= 1000; /* OPP entries in kHz */ + for (idx = 0; idx < max_opp; idx++, opps++) { + ftmp = opps->freq; + if (ftmp >= freq) { + if (ftmp <= fmax) + fmax = ftmp; + } else { + if (ftmp >= fmin) + fmin = ftmp; + } + } + if (fmax != ~0) + return fmax * 1000; + else + return fmin * 1000; +} + +static int ve_spc_find_performance_index(int cluster, u32 freq) +{ + int idx, max_opp = info->num_opps[cluster]; + struct ve_spc_opp *opps = info->opps[cluster]; + + for (idx = 0; idx < max_opp; idx++, opps++) + if (opps->freq == freq) + break; + return (idx == max_opp) ? -EINVAL : idx; +} + +static int ve_spc_waitforcompletion(int req_type) +{ + int ret = wait_for_completion_interruptible_timeout( + &info->done, usecs_to_jiffies(TIMEOUT_US)); + if (ret == 0) + ret = -ETIMEDOUT; + else if (ret > 0) + ret = info->cur_rsp_stat & STAT_COMPLETE(req_type) ? 0 : -EIO; + return ret; +} + +static int ve_spc_set_performance(int cluster, u32 freq) +{ + u32 perf_cfg_reg; + int ret, perf, req_type; + + if (cluster_is_a15(cluster)) { + req_type = CA15_DVFS; + perf_cfg_reg = PERF_LVL_A15; + } else { + req_type = CA7_DVFS; + perf_cfg_reg = PERF_LVL_A7; + } + + perf = ve_spc_find_performance_index(cluster, freq); + + if (perf < 0) + return perf; + + if (down_timeout(&info->sem, usecs_to_jiffies(TIMEOUT_US))) + return -ETIME; + + init_completion(&info->done); + info->cur_rsp_mask = RESPONSE_MASK(req_type); + + writel(perf, info->baseaddr + perf_cfg_reg); + ret = ve_spc_waitforcompletion(req_type); + + info->cur_rsp_mask = 0; + up(&info->sem); + + return ret; +} + +static int ve_spc_read_sys_cfg(int func, int offset, uint32_t *data) +{ + int ret; + + if (down_timeout(&info->sem, usecs_to_jiffies(TIMEOUT_US))) + return -ETIME; + + init_completion(&info->done); + info->cur_rsp_mask = RESPONSE_MASK(SPC_SYS_CFG); + + /* Set the control value */ + writel(SYSCFG_START | func | offset >> 2, info->baseaddr + COMMS); + ret = ve_spc_waitforcompletion(SPC_SYS_CFG); + + if (ret == 0) + *data = readl(info->baseaddr + SYSCFG_RDATA); + + info->cur_rsp_mask = 0; + up(&info->sem); + + return ret; +} + +static irqreturn_t ve_spc_irq_handler(int irq, void *data) +{ + struct ve_spc_drvdata *drv_data = data; + uint32_t status = readl_relaxed(drv_data->baseaddr + PWC_STATUS); + + if (info->cur_rsp_mask & status) { + info->cur_rsp_stat = status; + complete(&drv_data->done); + } + + return IRQ_HANDLED; +} + +/* + * +--------------------------+ + * | 31 20 | 19 0 | + * +--------------------------+ + * | m_volt | freq(kHz) | + * +--------------------------+ + */ +#define MULT_FACTOR 20 +#define VOLT_SHIFT 20 +#define FREQ_MASK (0xFFFFF) +static int ve_spc_populate_opps(uint32_t cluster) +{ + uint32_t data = 0, off, ret, idx; + struct ve_spc_opp *opps; + + opps = kcalloc(MAX_OPPS, sizeof(*opps), GFP_KERNEL); + if (!opps) + return -ENOMEM; + + info->opps[cluster] = opps; + + off = cluster_is_a15(cluster) ? A15_PERFVAL_BASE : A7_PERFVAL_BASE; + for (idx = 0; idx < MAX_OPPS; idx++, off += 4, opps++) { + ret = ve_spc_read_sys_cfg(SYSCFG_SCC, off, &data); + if (!ret) { + opps->freq = (data & FREQ_MASK) * MULT_FACTOR; + opps->u_volt = (data >> VOLT_SHIFT) * 1000; + } else { + break; + } + } + info->num_opps[cluster] = idx; + + return ret; +} + +static int ve_init_opp_table(struct device *cpu_dev) +{ + int cluster; + int idx, ret = 0, max_opp; + struct ve_spc_opp *opps; + + cluster = topology_physical_package_id(cpu_dev->id); + cluster = cluster < 0 ? 0 : cluster; + + max_opp = info->num_opps[cluster]; + opps = info->opps[cluster]; + + for (idx = 0; idx < max_opp; idx++, opps++) { + ret = dev_pm_opp_add(cpu_dev, opps->freq * 1000, opps->u_volt); + if (ret) { + dev_warn(cpu_dev, "failed to add opp %lu %lu\n", + opps->freq, opps->u_volt); + return ret; + } + } + return ret; +} + +int __init ve_spc_init(void __iomem *baseaddr, u32 a15_clusid, int irq) +{ + int ret; + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->baseaddr = baseaddr; + info->a15_clusid = a15_clusid; + + if (irq <= 0) { + pr_err(SPCLOG "Invalid IRQ %d\n", irq); + kfree(info); + return -EINVAL; + } + + init_completion(&info->done); + + readl_relaxed(info->baseaddr + PWC_STATUS); + + ret = request_irq(irq, ve_spc_irq_handler, IRQF_TRIGGER_HIGH + | IRQF_ONESHOT, "vexpress-spc", info); + if (ret) { + pr_err(SPCLOG "IRQ %d request failed\n", irq); + kfree(info); + return -ENODEV; + } + + sema_init(&info->sem, 1); + /* + * Multi-cluster systems may need this data when non-coherent, during + * cluster power-up/power-down. Make sure driver info reaches main + * memory. + */ + sync_cache_w(info); + sync_cache_w(&info); + + return 0; +} + +struct clk_spc { + struct clk_hw hw; + int cluster; +}; + +#define to_clk_spc(spc) container_of(spc, struct clk_spc, hw) +static unsigned long spc_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_spc *spc = to_clk_spc(hw); + u32 freq; + + if (ve_spc_get_performance(spc->cluster, &freq)) + return -EIO; + + return freq * 1000; +} + +static long spc_round_rate(struct clk_hw *hw, unsigned long drate, + unsigned long *parent_rate) +{ + struct clk_spc *spc = to_clk_spc(hw); + + return ve_spc_round_performance(spc->cluster, drate); +} + +static int spc_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_spc *spc = to_clk_spc(hw); + + return ve_spc_set_performance(spc->cluster, rate / 1000); +} + +static struct clk_ops clk_spc_ops = { + .recalc_rate = spc_recalc_rate, + .round_rate = spc_round_rate, + .set_rate = spc_set_rate, +}; + +static struct clk *ve_spc_clk_register(struct device *cpu_dev) +{ + struct clk_init_data init; + struct clk_spc *spc; + + spc = kzalloc(sizeof(*spc), GFP_KERNEL); + if (!spc) + return ERR_PTR(-ENOMEM); + + spc->hw.init = &init; + spc->cluster = topology_physical_package_id(cpu_dev->id); + + spc->cluster = spc->cluster < 0 ? 0 : spc->cluster; + + init.name = dev_name(cpu_dev); + init.ops = &clk_spc_ops; + init.flags = CLK_GET_RATE_NOCACHE; + init.num_parents = 0; + + return devm_clk_register(cpu_dev, &spc->hw); +} + +static int __init ve_spc_clk_init(void) +{ + int cpu, cluster; + struct clk *clk; + bool init_opp_table[MAX_CLUSTERS] = { false }; + + if (!info) + return 0; /* Continue only if SPC is initialised */ + + if (ve_spc_populate_opps(0) || ve_spc_populate_opps(1)) { + pr_err("failed to build OPP table\n"); + return -ENODEV; + } + + for_each_possible_cpu(cpu) { + struct device *cpu_dev = get_cpu_device(cpu); + if (!cpu_dev) { + pr_warn("failed to get cpu%d device\n", cpu); + continue; + } + clk = ve_spc_clk_register(cpu_dev); + if (IS_ERR(clk)) { + pr_warn("failed to register cpu%d clock\n", cpu); + continue; + } + if (clk_register_clkdev(clk, NULL, dev_name(cpu_dev))) { + pr_warn("failed to register cpu%d clock lookup\n", cpu); + continue; + } + + cluster = topology_physical_package_id(cpu_dev->id); + if (cluster < 0 || init_opp_table[cluster]) + continue; + + if (ve_init_opp_table(cpu_dev)) + pr_warn("failed to initialise cpu%d opp table\n", cpu); + else if (dev_pm_opp_set_sharing_cpus(cpu_dev, + topology_core_cpumask(cpu_dev->id))) + pr_warn("failed to mark OPPs shared for cpu%d\n", cpu); + else + init_opp_table[cluster] = true; + } + + platform_device_register_simple("vexpress-spc-cpufreq", -1, NULL, 0); + return 0; +} +device_initcall(ve_spc_clk_init); -- cgit v1.2.3