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/cpufreq/armada-37xx-cpufreq.c | 564 ++++++++++++++++++++++++++++++++++ 1 file changed, 564 insertions(+) create mode 100644 drivers/cpufreq/armada-37xx-cpufreq.c (limited to 'drivers/cpufreq/armada-37xx-cpufreq.c') diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c new file mode 100644 index 000000000..b74289a95 --- /dev/null +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -0,0 +1,564 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * CPU frequency scaling support for Armada 37xx platform. + * + * Copyright (C) 2017 Marvell + * + * Gregory CLEMENT + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "cpufreq-dt.h" + +/* Clk register set */ +#define ARMADA_37XX_CLK_TBG_SEL 0 +#define ARMADA_37XX_CLK_TBG_SEL_CPU_OFF 22 + +/* Power management in North Bridge register set */ +#define ARMADA_37XX_NB_L0L1 0x18 +#define ARMADA_37XX_NB_L2L3 0x1C +#define ARMADA_37XX_NB_TBG_DIV_OFF 13 +#define ARMADA_37XX_NB_TBG_DIV_MASK 0x7 +#define ARMADA_37XX_NB_CLK_SEL_OFF 11 +#define ARMADA_37XX_NB_CLK_SEL_MASK 0x1 +#define ARMADA_37XX_NB_CLK_SEL_TBG 0x1 +#define ARMADA_37XX_NB_TBG_SEL_OFF 9 +#define ARMADA_37XX_NB_TBG_SEL_MASK 0x3 +#define ARMADA_37XX_NB_VDD_SEL_OFF 6 +#define ARMADA_37XX_NB_VDD_SEL_MASK 0x3 +#define ARMADA_37XX_NB_CONFIG_SHIFT 16 +#define ARMADA_37XX_NB_DYN_MOD 0x24 +#define ARMADA_37XX_NB_CLK_SEL_EN BIT(26) +#define ARMADA_37XX_NB_TBG_EN BIT(28) +#define ARMADA_37XX_NB_DIV_EN BIT(29) +#define ARMADA_37XX_NB_VDD_EN BIT(30) +#define ARMADA_37XX_NB_DFS_EN BIT(31) +#define ARMADA_37XX_NB_CPU_LOAD 0x30 +#define ARMADA_37XX_NB_CPU_LOAD_MASK 0x3 +#define ARMADA_37XX_DVFS_LOAD_0 0 +#define ARMADA_37XX_DVFS_LOAD_1 1 +#define ARMADA_37XX_DVFS_LOAD_2 2 +#define ARMADA_37XX_DVFS_LOAD_3 3 + +/* AVS register set */ +#define ARMADA_37XX_AVS_CTL0 0x0 +#define ARMADA_37XX_AVS_ENABLE BIT(30) +#define ARMADA_37XX_AVS_HIGH_VDD_LIMIT 16 +#define ARMADA_37XX_AVS_LOW_VDD_LIMIT 22 +#define ARMADA_37XX_AVS_VDD_MASK 0x3F +#define ARMADA_37XX_AVS_CTL2 0x8 +#define ARMADA_37XX_AVS_LOW_VDD_EN BIT(6) +#define ARMADA_37XX_AVS_VSET(x) (0x1C + 4 * (x)) + +/* + * On Armada 37xx the Power management manages 4 level of CPU load, + * each level can be associated with a CPU clock source, a CPU + * divider, a VDD level, etc... + */ +#define LOAD_LEVEL_NR 4 + +#define MIN_VOLT_MV 1000 +#define MIN_VOLT_MV_FOR_L1_1000MHZ 1108 +#define MIN_VOLT_MV_FOR_L1_1200MHZ 1155 + +/* AVS value for the corresponding voltage (in mV) */ +static int avs_map[] = { + 747, 758, 770, 782, 793, 805, 817, 828, 840, 852, 863, 875, 887, 898, + 910, 922, 933, 945, 957, 968, 980, 992, 1003, 1015, 1027, 1038, 1050, + 1062, 1073, 1085, 1097, 1108, 1120, 1132, 1143, 1155, 1167, 1178, 1190, + 1202, 1213, 1225, 1237, 1248, 1260, 1272, 1283, 1295, 1307, 1318, 1330, + 1342 +}; + +struct armada37xx_cpufreq_state { + struct platform_device *pdev; + struct device *cpu_dev; + struct regmap *regmap; + u32 nb_l0l1; + u32 nb_l2l3; + u32 nb_dyn_mod; + u32 nb_cpu_load; +}; + +static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state; + +struct armada_37xx_dvfs { + u32 cpu_freq_max; + u8 divider[LOAD_LEVEL_NR]; + u32 avs[LOAD_LEVEL_NR]; +}; + +static struct armada_37xx_dvfs armada_37xx_dvfs[] = { + /* + * The cpufreq scaling for 1.2 GHz variant of the SOC is currently + * unstable because we do not know how to configure it properly. + */ + /* {.cpu_freq_max = 1200*1000*1000, .divider = {1, 2, 4, 6} }, */ + {.cpu_freq_max = 1000*1000*1000, .divider = {1, 2, 4, 5} }, + {.cpu_freq_max = 800*1000*1000, .divider = {1, 2, 3, 4} }, + {.cpu_freq_max = 600*1000*1000, .divider = {2, 4, 5, 6} }, +}; + +static struct armada_37xx_dvfs *armada_37xx_cpu_freq_info_get(u32 freq) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(armada_37xx_dvfs); i++) { + if (freq == armada_37xx_dvfs[i].cpu_freq_max) + return &armada_37xx_dvfs[i]; + } + + pr_err("Unsupported CPU frequency %d MHz\n", freq/1000000); + return NULL; +} + +/* + * Setup the four level managed by the hardware. Once the four level + * will be configured then the DVFS will be enabled. + */ +static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base, + struct regmap *clk_base, u8 *divider) +{ + u32 cpu_tbg_sel; + int load_lvl; + + /* Determine to which TBG clock is CPU connected */ + regmap_read(clk_base, ARMADA_37XX_CLK_TBG_SEL, &cpu_tbg_sel); + cpu_tbg_sel >>= ARMADA_37XX_CLK_TBG_SEL_CPU_OFF; + cpu_tbg_sel &= ARMADA_37XX_NB_TBG_SEL_MASK; + + for (load_lvl = 0; load_lvl < LOAD_LEVEL_NR; load_lvl++) { + unsigned int reg, mask, val, offset = 0; + + if (load_lvl <= ARMADA_37XX_DVFS_LOAD_1) + reg = ARMADA_37XX_NB_L0L1; + else + reg = ARMADA_37XX_NB_L2L3; + + if (load_lvl == ARMADA_37XX_DVFS_LOAD_0 || + load_lvl == ARMADA_37XX_DVFS_LOAD_2) + offset += ARMADA_37XX_NB_CONFIG_SHIFT; + + /* Set cpu clock source, for all the level we use TBG */ + val = ARMADA_37XX_NB_CLK_SEL_TBG << ARMADA_37XX_NB_CLK_SEL_OFF; + mask = (ARMADA_37XX_NB_CLK_SEL_MASK + << ARMADA_37XX_NB_CLK_SEL_OFF); + + /* Set TBG index, for all levels we use the same TBG */ + val = cpu_tbg_sel << ARMADA_37XX_NB_TBG_SEL_OFF; + mask = (ARMADA_37XX_NB_TBG_SEL_MASK + << ARMADA_37XX_NB_TBG_SEL_OFF); + + /* + * Set cpu divider based on the pre-computed array in + * order to have balanced step. + */ + val |= divider[load_lvl] << ARMADA_37XX_NB_TBG_DIV_OFF; + mask |= (ARMADA_37XX_NB_TBG_DIV_MASK + << ARMADA_37XX_NB_TBG_DIV_OFF); + + /* Set VDD divider which is actually the load level. */ + val |= load_lvl << ARMADA_37XX_NB_VDD_SEL_OFF; + mask |= (ARMADA_37XX_NB_VDD_SEL_MASK + << ARMADA_37XX_NB_VDD_SEL_OFF); + + val <<= offset; + mask <<= offset; + + regmap_update_bits(base, reg, mask, val); + } +} + +/* + * Find out the armada 37x supported AVS value whose voltage value is + * the round-up closest to the target voltage value. + */ +static u32 armada_37xx_avs_val_match(int target_vm) +{ + u32 avs; + + /* Find out the round-up closest supported voltage value */ + for (avs = 0; avs < ARRAY_SIZE(avs_map); avs++) + if (avs_map[avs] >= target_vm) + break; + + /* + * If all supported voltages are smaller than target one, + * choose the largest supported voltage + */ + if (avs == ARRAY_SIZE(avs_map)) + avs = ARRAY_SIZE(avs_map) - 1; + + return avs; +} + +/* + * For Armada 37xx soc, L0(VSET0) VDD AVS value is set to SVC revision + * value or a default value when SVC is not supported. + * - L0 can be read out from the register of AVS_CTRL_0 and L0 voltage + * can be got from the mapping table of avs_map. + * - L1 voltage should be about 100mv smaller than L0 voltage + * - L2 & L3 voltage should be about 150mv smaller than L0 voltage. + * This function calculates L1 & L2 & L3 AVS values dynamically based + * on L0 voltage and fill all AVS values to the AVS value table. + * When base CPU frequency is 1000 or 1200 MHz then there is additional + * minimal avs value for load L1. + */ +static void __init armada37xx_cpufreq_avs_configure(struct regmap *base, + struct armada_37xx_dvfs *dvfs) +{ + unsigned int target_vm; + int load_level = 0; + u32 l0_vdd_min; + + if (base == NULL) + return; + + /* Get L0 VDD min value */ + regmap_read(base, ARMADA_37XX_AVS_CTL0, &l0_vdd_min); + l0_vdd_min = (l0_vdd_min >> ARMADA_37XX_AVS_LOW_VDD_LIMIT) & + ARMADA_37XX_AVS_VDD_MASK; + if (l0_vdd_min >= ARRAY_SIZE(avs_map)) { + pr_err("L0 VDD MIN %d is not correct.\n", l0_vdd_min); + return; + } + dvfs->avs[0] = l0_vdd_min; + + if (avs_map[l0_vdd_min] <= MIN_VOLT_MV) { + /* + * If L0 voltage is smaller than 1000mv, then all VDD sets + * use L0 voltage; + */ + u32 avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV); + + for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) + dvfs->avs[load_level] = avs_min; + + /* + * Set the avs values for load L0 and L1 when base CPU frequency + * is 1000/1200 MHz to its typical initial values according to + * the Armada 3700 Hardware Specifications. + */ + if (dvfs->cpu_freq_max >= 1000*1000*1000) { + if (dvfs->cpu_freq_max >= 1200*1000*1000) + avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1200MHZ); + else + avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1000MHZ); + dvfs->avs[0] = dvfs->avs[1] = avs_min; + } + + return; + } + + /* + * L1 voltage is equal to L0 voltage - 100mv and it must be + * larger than 1000mv + */ + + target_vm = avs_map[l0_vdd_min] - 100; + target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV; + dvfs->avs[1] = armada_37xx_avs_val_match(target_vm); + + /* + * L2 & L3 voltage is equal to L0 voltage - 150mv and it must + * be larger than 1000mv + */ + target_vm = avs_map[l0_vdd_min] - 150; + target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV; + dvfs->avs[2] = dvfs->avs[3] = armada_37xx_avs_val_match(target_vm); + + /* + * Fix the avs value for load L1 when base CPU frequency is 1000/1200 MHz, + * otherwise the CPU gets stuck when switching from load L1 to load L0. + * Also ensure that avs value for load L1 is not higher than for L0. + */ + if (dvfs->cpu_freq_max >= 1000*1000*1000) { + u32 avs_min_l1; + + if (dvfs->cpu_freq_max >= 1200*1000*1000) + avs_min_l1 = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1200MHZ); + else + avs_min_l1 = armada_37xx_avs_val_match(MIN_VOLT_MV_FOR_L1_1000MHZ); + + if (avs_min_l1 > dvfs->avs[0]) + avs_min_l1 = dvfs->avs[0]; + + if (dvfs->avs[1] < avs_min_l1) + dvfs->avs[1] = avs_min_l1; + } +} + +static void __init armada37xx_cpufreq_avs_setup(struct regmap *base, + struct armada_37xx_dvfs *dvfs) +{ + unsigned int avs_val = 0; + int load_level = 0; + + if (base == NULL) + return; + + /* Disable AVS before the configuration */ + regmap_update_bits(base, ARMADA_37XX_AVS_CTL0, + ARMADA_37XX_AVS_ENABLE, 0); + + + /* Enable low voltage mode */ + regmap_update_bits(base, ARMADA_37XX_AVS_CTL2, + ARMADA_37XX_AVS_LOW_VDD_EN, + ARMADA_37XX_AVS_LOW_VDD_EN); + + + for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) { + avs_val = dvfs->avs[load_level]; + regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1), + ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT | + ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_LOW_VDD_LIMIT, + avs_val << ARMADA_37XX_AVS_HIGH_VDD_LIMIT | + avs_val << ARMADA_37XX_AVS_LOW_VDD_LIMIT); + } + + /* Enable AVS after the configuration */ + regmap_update_bits(base, ARMADA_37XX_AVS_CTL0, + ARMADA_37XX_AVS_ENABLE, + ARMADA_37XX_AVS_ENABLE); + +} + +static void armada37xx_cpufreq_disable_dvfs(struct regmap *base) +{ + unsigned int reg = ARMADA_37XX_NB_DYN_MOD, + mask = ARMADA_37XX_NB_DFS_EN; + + regmap_update_bits(base, reg, mask, 0); +} + +static void __init armada37xx_cpufreq_enable_dvfs(struct regmap *base) +{ + unsigned int val, reg = ARMADA_37XX_NB_CPU_LOAD, + mask = ARMADA_37XX_NB_CPU_LOAD_MASK; + + /* Start with the highest load (0) */ + val = ARMADA_37XX_DVFS_LOAD_0; + regmap_update_bits(base, reg, mask, val); + + /* Now enable DVFS for the CPUs */ + reg = ARMADA_37XX_NB_DYN_MOD; + mask = ARMADA_37XX_NB_CLK_SEL_EN | ARMADA_37XX_NB_TBG_EN | + ARMADA_37XX_NB_DIV_EN | ARMADA_37XX_NB_VDD_EN | + ARMADA_37XX_NB_DFS_EN; + + regmap_update_bits(base, reg, mask, mask); +} + +static int armada37xx_cpufreq_suspend(struct cpufreq_policy *policy) +{ + struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state; + + regmap_read(state->regmap, ARMADA_37XX_NB_L0L1, &state->nb_l0l1); + regmap_read(state->regmap, ARMADA_37XX_NB_L2L3, &state->nb_l2l3); + regmap_read(state->regmap, ARMADA_37XX_NB_CPU_LOAD, + &state->nb_cpu_load); + regmap_read(state->regmap, ARMADA_37XX_NB_DYN_MOD, &state->nb_dyn_mod); + + return 0; +} + +static int armada37xx_cpufreq_resume(struct cpufreq_policy *policy) +{ + struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state; + + /* Ensure DVFS is disabled otherwise the following registers are RO */ + armada37xx_cpufreq_disable_dvfs(state->regmap); + + regmap_write(state->regmap, ARMADA_37XX_NB_L0L1, state->nb_l0l1); + regmap_write(state->regmap, ARMADA_37XX_NB_L2L3, state->nb_l2l3); + regmap_write(state->regmap, ARMADA_37XX_NB_CPU_LOAD, + state->nb_cpu_load); + + /* + * NB_DYN_MOD register is the one that actually enable back DVFS if it + * was enabled before the suspend operation. This must be done last + * otherwise other registers are not writable. + */ + regmap_write(state->regmap, ARMADA_37XX_NB_DYN_MOD, state->nb_dyn_mod); + + return 0; +} + +static int __init armada37xx_cpufreq_driver_init(void) +{ + struct cpufreq_dt_platform_data pdata; + struct armada_37xx_dvfs *dvfs; + struct platform_device *pdev; + unsigned long freq; + unsigned int base_frequency; + struct regmap *nb_clk_base, *nb_pm_base, *avs_base; + struct device *cpu_dev; + int load_lvl, ret; + struct clk *clk, *parent; + + nb_clk_base = + syscon_regmap_lookup_by_compatible("marvell,armada-3700-periph-clock-nb"); + if (IS_ERR(nb_clk_base)) + return -ENODEV; + + nb_pm_base = + syscon_regmap_lookup_by_compatible("marvell,armada-3700-nb-pm"); + + if (IS_ERR(nb_pm_base)) + return -ENODEV; + + avs_base = + syscon_regmap_lookup_by_compatible("marvell,armada-3700-avs"); + + /* if AVS is not present don't use it but still try to setup dvfs */ + if (IS_ERR(avs_base)) { + pr_info("Syscon failed for Adapting Voltage Scaling: skip it\n"); + avs_base = NULL; + } + /* Before doing any configuration on the DVFS first, disable it */ + armada37xx_cpufreq_disable_dvfs(nb_pm_base); + + /* + * On CPU 0 register the operating points supported (which are + * the nominal CPU frequency and full integer divisions of + * it). + */ + cpu_dev = get_cpu_device(0); + if (!cpu_dev) { + dev_err(cpu_dev, "Cannot get CPU\n"); + return -ENODEV; + } + + clk = clk_get(cpu_dev, NULL); + if (IS_ERR(clk)) { + dev_err(cpu_dev, "Cannot get clock for CPU0\n"); + return PTR_ERR(clk); + } + + parent = clk_get_parent(clk); + if (IS_ERR(parent)) { + dev_err(cpu_dev, "Cannot get parent clock for CPU0\n"); + clk_put(clk); + return PTR_ERR(parent); + } + + /* Get parent CPU frequency */ + base_frequency = clk_get_rate(parent); + + if (!base_frequency) { + dev_err(cpu_dev, "Failed to get parent clock rate for CPU\n"); + clk_put(clk); + return -EINVAL; + } + + dvfs = armada_37xx_cpu_freq_info_get(base_frequency); + if (!dvfs) { + clk_put(clk); + return -EINVAL; + } + + armada37xx_cpufreq_state = kmalloc(sizeof(*armada37xx_cpufreq_state), + GFP_KERNEL); + if (!armada37xx_cpufreq_state) { + clk_put(clk); + return -ENOMEM; + } + + armada37xx_cpufreq_state->regmap = nb_pm_base; + + armada37xx_cpufreq_avs_configure(avs_base, dvfs); + armada37xx_cpufreq_avs_setup(avs_base, dvfs); + + armada37xx_cpufreq_dvfs_setup(nb_pm_base, nb_clk_base, dvfs->divider); + clk_put(clk); + + for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR; + load_lvl++) { + unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000; + freq = base_frequency / dvfs->divider[load_lvl]; + ret = dev_pm_opp_add(cpu_dev, freq, u_volt); + if (ret) + goto remove_opp; + + + } + + /* Now that everything is setup, enable the DVFS at hardware level */ + armada37xx_cpufreq_enable_dvfs(nb_pm_base); + + memset(&pdata, 0, sizeof(pdata)); + pdata.suspend = armada37xx_cpufreq_suspend; + pdata.resume = armada37xx_cpufreq_resume; + + pdev = platform_device_register_data(NULL, "cpufreq-dt", -1, &pdata, + sizeof(pdata)); + ret = PTR_ERR_OR_ZERO(pdev); + if (ret) + goto disable_dvfs; + + armada37xx_cpufreq_state->cpu_dev = cpu_dev; + armada37xx_cpufreq_state->pdev = pdev; + platform_set_drvdata(pdev, dvfs); + return 0; + +disable_dvfs: + armada37xx_cpufreq_disable_dvfs(nb_pm_base); +remove_opp: + /* clean-up the already added opp before leaving */ + while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) { + freq = base_frequency / dvfs->divider[load_lvl]; + dev_pm_opp_remove(cpu_dev, freq); + } + + kfree(armada37xx_cpufreq_state); + + return ret; +} +/* late_initcall, to guarantee the driver is loaded after A37xx clock driver */ +late_initcall(armada37xx_cpufreq_driver_init); + +static void __exit armada37xx_cpufreq_driver_exit(void) +{ + struct platform_device *pdev = armada37xx_cpufreq_state->pdev; + struct armada_37xx_dvfs *dvfs = platform_get_drvdata(pdev); + unsigned long freq; + int load_lvl; + + platform_device_unregister(pdev); + + armada37xx_cpufreq_disable_dvfs(armada37xx_cpufreq_state->regmap); + + for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR; load_lvl++) { + freq = dvfs->cpu_freq_max / dvfs->divider[load_lvl]; + dev_pm_opp_remove(armada37xx_cpufreq_state->cpu_dev, freq); + } + + kfree(armada37xx_cpufreq_state); +} +module_exit(armada37xx_cpufreq_driver_exit); + +static const struct of_device_id __maybe_unused armada37xx_cpufreq_of_match[] = { + { .compatible = "marvell,armada-3700-nb-pm" }, + { }, +}; +MODULE_DEVICE_TABLE(of, armada37xx_cpufreq_of_match); + +MODULE_AUTHOR("Gregory CLEMENT "); +MODULE_DESCRIPTION("Armada 37xx cpufreq driver"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3