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/cpufreq_governor.c | 579 +++++++++++++++++++++++++++++++++++++ 1 file changed, 579 insertions(+) create mode 100644 drivers/cpufreq/cpufreq_governor.c (limited to 'drivers/cpufreq/cpufreq_governor.c') diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c new file mode 100644 index 000000000..85da677c4 --- /dev/null +++ b/drivers/cpufreq/cpufreq_governor.c @@ -0,0 +1,579 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * drivers/cpufreq/cpufreq_governor.c + * + * CPUFREQ governors common code + * + * Copyright (C) 2001 Russell King + * (C) 2003 Venkatesh Pallipadi . + * (C) 2003 Jun Nakajima + * (C) 2009 Alexander Clouter + * (c) 2012 Viresh Kumar + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +#include "cpufreq_governor.h" + +#define CPUFREQ_DBS_MIN_SAMPLING_INTERVAL (2 * TICK_NSEC / NSEC_PER_USEC) + +static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs); + +static DEFINE_MUTEX(gov_dbs_data_mutex); + +/* Common sysfs tunables */ +/* + * sampling_rate_store - update sampling rate effective immediately if needed. + * + * If new rate is smaller than the old, simply updating + * dbs.sampling_rate might not be appropriate. For example, if the + * original sampling_rate was 1 second and the requested new sampling rate is 10 + * ms because the user needs immediate reaction from ondemand governor, but not + * sure if higher frequency will be required or not, then, the governor may + * change the sampling rate too late; up to 1 second later. Thus, if we are + * reducing the sampling rate, we need to make the new value effective + * immediately. + * + * This must be called with dbs_data->mutex held, otherwise traversing + * policy_dbs_list isn't safe. + */ +ssize_t sampling_rate_store(struct gov_attr_set *attr_set, const char *buf, + size_t count) +{ + struct dbs_data *dbs_data = to_dbs_data(attr_set); + struct policy_dbs_info *policy_dbs; + unsigned int sampling_interval; + int ret; + + ret = sscanf(buf, "%u", &sampling_interval); + if (ret != 1 || sampling_interval < CPUFREQ_DBS_MIN_SAMPLING_INTERVAL) + return -EINVAL; + + dbs_data->sampling_rate = sampling_interval; + + /* + * We are operating under dbs_data->mutex and so the list and its + * entries can't be freed concurrently. + */ + list_for_each_entry(policy_dbs, &attr_set->policy_list, list) { + mutex_lock(&policy_dbs->update_mutex); + /* + * On 32-bit architectures this may race with the + * sample_delay_ns read in dbs_update_util_handler(), but that + * really doesn't matter. If the read returns a value that's + * too big, the sample will be skipped, but the next invocation + * of dbs_update_util_handler() (when the update has been + * completed) will take a sample. + * + * If this runs in parallel with dbs_work_handler(), we may end + * up overwriting the sample_delay_ns value that it has just + * written, but it will be corrected next time a sample is + * taken, so it shouldn't be significant. + */ + gov_update_sample_delay(policy_dbs, 0); + mutex_unlock(&policy_dbs->update_mutex); + } + + return count; +} +EXPORT_SYMBOL_GPL(sampling_rate_store); + +/** + * gov_update_cpu_data - Update CPU load data. + * @dbs_data: Top-level governor data pointer. + * + * Update CPU load data for all CPUs in the domain governed by @dbs_data + * (that may be a single policy or a bunch of them if governor tunables are + * system-wide). + * + * Call under the @dbs_data mutex. + */ +void gov_update_cpu_data(struct dbs_data *dbs_data) +{ + struct policy_dbs_info *policy_dbs; + + list_for_each_entry(policy_dbs, &dbs_data->attr_set.policy_list, list) { + unsigned int j; + + for_each_cpu(j, policy_dbs->policy->cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + + j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time, + dbs_data->io_is_busy); + if (dbs_data->ignore_nice_load) + j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); + } + } +} +EXPORT_SYMBOL_GPL(gov_update_cpu_data); + +unsigned int dbs_update(struct cpufreq_policy *policy) +{ + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + unsigned int ignore_nice = dbs_data->ignore_nice_load; + unsigned int max_load = 0, idle_periods = UINT_MAX; + unsigned int sampling_rate, io_busy, j; + + /* + * Sometimes governors may use an additional multiplier to increase + * sample delays temporarily. Apply that multiplier to sampling_rate + * so as to keep the wake-up-from-idle detection logic a bit + * conservative. + */ + sampling_rate = dbs_data->sampling_rate * policy_dbs->rate_mult; + /* + * For the purpose of ondemand, waiting for disk IO is an indication + * that you're performance critical, and not that the system is actually + * idle, so do not add the iowait time to the CPU idle time then. + */ + io_busy = dbs_data->io_is_busy; + + /* Get Absolute Load */ + for_each_cpu(j, policy->cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + u64 update_time, cur_idle_time; + unsigned int idle_time, time_elapsed; + unsigned int load; + + cur_idle_time = get_cpu_idle_time(j, &update_time, io_busy); + + time_elapsed = update_time - j_cdbs->prev_update_time; + j_cdbs->prev_update_time = update_time; + + idle_time = cur_idle_time - j_cdbs->prev_cpu_idle; + j_cdbs->prev_cpu_idle = cur_idle_time; + + if (ignore_nice) { + u64 cur_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); + + idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC); + j_cdbs->prev_cpu_nice = cur_nice; + } + + if (unlikely(!time_elapsed)) { + /* + * That can only happen when this function is called + * twice in a row with a very short interval between the + * calls, so the previous load value can be used then. + */ + load = j_cdbs->prev_load; + } else if (unlikely((int)idle_time > 2 * sampling_rate && + j_cdbs->prev_load)) { + /* + * If the CPU had gone completely idle and a task has + * just woken up on this CPU now, it would be unfair to + * calculate 'load' the usual way for this elapsed + * time-window, because it would show near-zero load, + * irrespective of how CPU intensive that task actually + * was. This is undesirable for latency-sensitive bursty + * workloads. + * + * To avoid this, reuse the 'load' from the previous + * time-window and give this task a chance to start with + * a reasonably high CPU frequency. However, that + * shouldn't be over-done, lest we get stuck at a high + * load (high frequency) for too long, even when the + * current system load has actually dropped down, so + * clear prev_load to guarantee that the load will be + * computed again next time. + * + * Detecting this situation is easy: an unusually large + * 'idle_time' (as compared to the sampling rate) + * indicates this scenario. + */ + load = j_cdbs->prev_load; + j_cdbs->prev_load = 0; + } else { + if (time_elapsed >= idle_time) { + load = 100 * (time_elapsed - idle_time) / time_elapsed; + } else { + /* + * That can happen if idle_time is returned by + * get_cpu_idle_time_jiffy(). In that case + * idle_time is roughly equal to the difference + * between time_elapsed and "busy time" obtained + * from CPU statistics. Then, the "busy time" + * can end up being greater than time_elapsed + * (for example, if jiffies_64 and the CPU + * statistics are updated by different CPUs), + * so idle_time may in fact be negative. That + * means, though, that the CPU was busy all + * the time (on the rough average) during the + * last sampling interval and 100 can be + * returned as the load. + */ + load = (int)idle_time < 0 ? 100 : 0; + } + j_cdbs->prev_load = load; + } + + if (unlikely((int)idle_time > 2 * sampling_rate)) { + unsigned int periods = idle_time / sampling_rate; + + if (periods < idle_periods) + idle_periods = periods; + } + + if (load > max_load) + max_load = load; + } + + policy_dbs->idle_periods = idle_periods; + + return max_load; +} +EXPORT_SYMBOL_GPL(dbs_update); + +static void dbs_work_handler(struct work_struct *work) +{ + struct policy_dbs_info *policy_dbs; + struct cpufreq_policy *policy; + struct dbs_governor *gov; + + policy_dbs = container_of(work, struct policy_dbs_info, work); + policy = policy_dbs->policy; + gov = dbs_governor_of(policy); + + /* + * Make sure cpufreq_governor_limits() isn't evaluating load or the + * ondemand governor isn't updating the sampling rate in parallel. + */ + mutex_lock(&policy_dbs->update_mutex); + gov_update_sample_delay(policy_dbs, gov->gov_dbs_update(policy)); + mutex_unlock(&policy_dbs->update_mutex); + + /* Allow the utilization update handler to queue up more work. */ + atomic_set(&policy_dbs->work_count, 0); + /* + * If the update below is reordered with respect to the sample delay + * modification, the utilization update handler may end up using a stale + * sample delay value. + */ + smp_wmb(); + policy_dbs->work_in_progress = false; +} + +static void dbs_irq_work(struct irq_work *irq_work) +{ + struct policy_dbs_info *policy_dbs; + + policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work); + schedule_work_on(smp_processor_id(), &policy_dbs->work); +} + +static void dbs_update_util_handler(struct update_util_data *data, u64 time, + unsigned int flags) +{ + struct cpu_dbs_info *cdbs = container_of(data, struct cpu_dbs_info, update_util); + struct policy_dbs_info *policy_dbs = cdbs->policy_dbs; + u64 delta_ns, lst; + + if (!cpufreq_this_cpu_can_update(policy_dbs->policy)) + return; + + /* + * The work may not be allowed to be queued up right now. + * Possible reasons: + * - Work has already been queued up or is in progress. + * - It is too early (too little time from the previous sample). + */ + if (policy_dbs->work_in_progress) + return; + + /* + * If the reads below are reordered before the check above, the value + * of sample_delay_ns used in the computation may be stale. + */ + smp_rmb(); + lst = READ_ONCE(policy_dbs->last_sample_time); + delta_ns = time - lst; + if ((s64)delta_ns < policy_dbs->sample_delay_ns) + return; + + /* + * If the policy is not shared, the irq_work may be queued up right away + * at this point. Otherwise, we need to ensure that only one of the + * CPUs sharing the policy will do that. + */ + if (policy_dbs->is_shared) { + if (!atomic_add_unless(&policy_dbs->work_count, 1, 1)) + return; + + /* + * If another CPU updated last_sample_time in the meantime, we + * shouldn't be here, so clear the work counter and bail out. + */ + if (unlikely(lst != READ_ONCE(policy_dbs->last_sample_time))) { + atomic_set(&policy_dbs->work_count, 0); + return; + } + } + + policy_dbs->last_sample_time = time; + policy_dbs->work_in_progress = true; + irq_work_queue(&policy_dbs->irq_work); +} + +static void gov_set_update_util(struct policy_dbs_info *policy_dbs, + unsigned int delay_us) +{ + struct cpufreq_policy *policy = policy_dbs->policy; + int cpu; + + gov_update_sample_delay(policy_dbs, delay_us); + policy_dbs->last_sample_time = 0; + + for_each_cpu(cpu, policy->cpus) { + struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu); + + cpufreq_add_update_util_hook(cpu, &cdbs->update_util, + dbs_update_util_handler); + } +} + +static inline void gov_clear_update_util(struct cpufreq_policy *policy) +{ + int i; + + for_each_cpu(i, policy->cpus) + cpufreq_remove_update_util_hook(i); + + synchronize_rcu(); +} + +static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy, + struct dbs_governor *gov) +{ + struct policy_dbs_info *policy_dbs; + int j; + + /* Allocate memory for per-policy governor data. */ + policy_dbs = gov->alloc(); + if (!policy_dbs) + return NULL; + + policy_dbs->policy = policy; + mutex_init(&policy_dbs->update_mutex); + atomic_set(&policy_dbs->work_count, 0); + init_irq_work(&policy_dbs->irq_work, dbs_irq_work); + INIT_WORK(&policy_dbs->work, dbs_work_handler); + + /* Set policy_dbs for all CPUs, online+offline */ + for_each_cpu(j, policy->related_cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + + j_cdbs->policy_dbs = policy_dbs; + } + return policy_dbs; +} + +static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs, + struct dbs_governor *gov) +{ + int j; + + mutex_destroy(&policy_dbs->update_mutex); + + for_each_cpu(j, policy_dbs->policy->related_cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + + j_cdbs->policy_dbs = NULL; + j_cdbs->update_util.func = NULL; + } + gov->free(policy_dbs); +} + +static void cpufreq_dbs_data_release(struct kobject *kobj) +{ + struct dbs_data *dbs_data = to_dbs_data(to_gov_attr_set(kobj)); + struct dbs_governor *gov = dbs_data->gov; + + gov->exit(dbs_data); + kfree(dbs_data); +} + +int cpufreq_dbs_governor_init(struct cpufreq_policy *policy) +{ + struct dbs_governor *gov = dbs_governor_of(policy); + struct dbs_data *dbs_data; + struct policy_dbs_info *policy_dbs; + int ret = 0; + + /* State should be equivalent to EXIT */ + if (policy->governor_data) + return -EBUSY; + + policy_dbs = alloc_policy_dbs_info(policy, gov); + if (!policy_dbs) + return -ENOMEM; + + /* Protect gov->gdbs_data against concurrent updates. */ + mutex_lock(&gov_dbs_data_mutex); + + dbs_data = gov->gdbs_data; + if (dbs_data) { + if (WARN_ON(have_governor_per_policy())) { + ret = -EINVAL; + goto free_policy_dbs_info; + } + policy_dbs->dbs_data = dbs_data; + policy->governor_data = policy_dbs; + + gov_attr_set_get(&dbs_data->attr_set, &policy_dbs->list); + goto out; + } + + dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL); + if (!dbs_data) { + ret = -ENOMEM; + goto free_policy_dbs_info; + } + + dbs_data->gov = gov; + gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list); + + ret = gov->init(dbs_data); + if (ret) + goto free_policy_dbs_info; + + /* + * The sampling interval should not be less than the transition latency + * of the CPU and it also cannot be too small for dbs_update() to work + * correctly. + */ + dbs_data->sampling_rate = max_t(unsigned int, + CPUFREQ_DBS_MIN_SAMPLING_INTERVAL, + cpufreq_policy_transition_delay_us(policy)); + + if (!have_governor_per_policy()) + gov->gdbs_data = dbs_data; + + policy_dbs->dbs_data = dbs_data; + policy->governor_data = policy_dbs; + + gov->kobj_type.sysfs_ops = &governor_sysfs_ops; + gov->kobj_type.release = cpufreq_dbs_data_release; + ret = kobject_init_and_add(&dbs_data->attr_set.kobj, &gov->kobj_type, + get_governor_parent_kobj(policy), + "%s", gov->gov.name); + if (!ret) + goto out; + + /* Failure, so roll back. */ + pr_err("initialization failed (dbs_data kobject init error %d)\n", ret); + + kobject_put(&dbs_data->attr_set.kobj); + + policy->governor_data = NULL; + + if (!have_governor_per_policy()) + gov->gdbs_data = NULL; + gov->exit(dbs_data); + kfree(dbs_data); + +free_policy_dbs_info: + free_policy_dbs_info(policy_dbs, gov); + +out: + mutex_unlock(&gov_dbs_data_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_init); + +void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy) +{ + struct dbs_governor *gov = dbs_governor_of(policy); + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + unsigned int count; + + /* Protect gov->gdbs_data against concurrent updates. */ + mutex_lock(&gov_dbs_data_mutex); + + count = gov_attr_set_put(&dbs_data->attr_set, &policy_dbs->list); + + policy->governor_data = NULL; + + if (!count && !have_governor_per_policy()) + gov->gdbs_data = NULL; + + free_policy_dbs_info(policy_dbs, gov); + + mutex_unlock(&gov_dbs_data_mutex); +} +EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_exit); + +int cpufreq_dbs_governor_start(struct cpufreq_policy *policy) +{ + struct dbs_governor *gov = dbs_governor_of(policy); + struct policy_dbs_info *policy_dbs = policy->governor_data; + struct dbs_data *dbs_data = policy_dbs->dbs_data; + unsigned int sampling_rate, ignore_nice, j; + unsigned int io_busy; + + if (!policy->cur) + return -EINVAL; + + policy_dbs->is_shared = policy_is_shared(policy); + policy_dbs->rate_mult = 1; + + sampling_rate = dbs_data->sampling_rate; + ignore_nice = dbs_data->ignore_nice_load; + io_busy = dbs_data->io_is_busy; + + for_each_cpu(j, policy->cpus) { + struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j); + + j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time, io_busy); + /* + * Make the first invocation of dbs_update() compute the load. + */ + j_cdbs->prev_load = 0; + + if (ignore_nice) + j_cdbs->prev_cpu_nice = kcpustat_field(&kcpustat_cpu(j), CPUTIME_NICE, j); + } + + gov->start(policy); + + gov_set_update_util(policy_dbs, sampling_rate); + return 0; +} +EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_start); + +void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy) +{ + struct policy_dbs_info *policy_dbs = policy->governor_data; + + gov_clear_update_util(policy_dbs->policy); + irq_work_sync(&policy_dbs->irq_work); + cancel_work_sync(&policy_dbs->work); + atomic_set(&policy_dbs->work_count, 0); + policy_dbs->work_in_progress = false; +} +EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop); + +void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy) +{ + struct policy_dbs_info *policy_dbs; + + /* Protect gov->gdbs_data against cpufreq_dbs_governor_exit() */ + mutex_lock(&gov_dbs_data_mutex); + policy_dbs = policy->governor_data; + if (!policy_dbs) + goto out; + + mutex_lock(&policy_dbs->update_mutex); + cpufreq_policy_apply_limits(policy); + gov_update_sample_delay(policy_dbs, 0); + mutex_unlock(&policy_dbs->update_mutex); + +out: + mutex_unlock(&gov_dbs_data_mutex); +} +EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_limits); -- cgit v1.2.3