aboutsummaryrefslogtreecommitdiff
path: root/drivers/powercap/dtpm_cpu.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/powercap/dtpm_cpu.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'drivers/powercap/dtpm_cpu.c')
-rw-r--r--drivers/powercap/dtpm_cpu.c297
1 files changed, 297 insertions, 0 deletions
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
new file mode 100644
index 000000000..2ff771753
--- /dev/null
+++ b/drivers/powercap/dtpm_cpu.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2020 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The DTPM CPU is based on the energy model. It hooks the CPU in the
+ * DTPM tree which in turns update the power number by propagating the
+ * power number from the CPU energy model information to the parents.
+ *
+ * The association between the power and the performance state, allows
+ * to set the power of the CPU at the OPP granularity.
+ *
+ * The CPU hotplug is supported and the power numbers will be updated
+ * if a CPU is hot plugged / unplugged.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpumask.h>
+#include <linux/cpufreq.h>
+#include <linux/cpuhotplug.h>
+#include <linux/dtpm.h>
+#include <linux/energy_model.h>
+#include <linux/of.h>
+#include <linux/pm_qos.h>
+#include <linux/slab.h>
+#include <linux/units.h>
+
+struct dtpm_cpu {
+ struct dtpm dtpm;
+ struct freq_qos_request qos_req;
+ int cpu;
+};
+
+static DEFINE_PER_CPU(struct dtpm_cpu *, dtpm_per_cpu);
+
+static struct dtpm_cpu *to_dtpm_cpu(struct dtpm *dtpm)
+{
+ return container_of(dtpm, struct dtpm_cpu, dtpm);
+}
+
+static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
+{
+ struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
+ struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu);
+ struct cpumask cpus;
+ unsigned long freq;
+ u64 power;
+ int i, nr_cpus;
+
+ cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
+ nr_cpus = cpumask_weight(&cpus);
+
+ for (i = 0; i < pd->nr_perf_states; i++) {
+
+ power = pd->table[i].power * nr_cpus;
+
+ if (power > power_limit)
+ break;
+ }
+
+ freq = pd->table[i - 1].frequency;
+
+ freq_qos_update_request(&dtpm_cpu->qos_req, freq);
+
+ power_limit = pd->table[i - 1].power * nr_cpus;
+
+ return power_limit;
+}
+
+static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
+{
+ unsigned long max, sum_util = 0;
+ int cpu;
+
+ /*
+ * The capacity is the same for all CPUs belonging to
+ * the same perf domain.
+ */
+ max = arch_scale_cpu_capacity(cpumask_first(pd_mask));
+
+ for_each_cpu_and(cpu, pd_mask, cpu_online_mask)
+ sum_util += sched_cpu_util(cpu);
+
+ return (power * ((sum_util << 10) / max)) >> 10;
+}
+
+static u64 get_pd_power_uw(struct dtpm *dtpm)
+{
+ struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
+ struct em_perf_domain *pd;
+ struct cpumask *pd_mask;
+ unsigned long freq;
+ int i;
+
+ pd = em_cpu_get(dtpm_cpu->cpu);
+
+ pd_mask = em_span_cpus(pd);
+
+ freq = cpufreq_quick_get(dtpm_cpu->cpu);
+
+ for (i = 0; i < pd->nr_perf_states; i++) {
+
+ if (pd->table[i].frequency < freq)
+ continue;
+
+ return scale_pd_power_uw(pd_mask, pd->table[i].power *
+ MICROWATT_PER_MILLIWATT);
+ }
+
+ return 0;
+}
+
+static int update_pd_power_uw(struct dtpm *dtpm)
+{
+ struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
+ struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu);
+ struct cpumask cpus;
+ int nr_cpus;
+
+ cpumask_and(&cpus, cpu_online_mask, to_cpumask(em->cpus));
+ nr_cpus = cpumask_weight(&cpus);
+
+ dtpm->power_min = em->table[0].power;
+ dtpm->power_min *= MICROWATT_PER_MILLIWATT;
+ dtpm->power_min *= nr_cpus;
+
+ dtpm->power_max = em->table[em->nr_perf_states - 1].power;
+ dtpm->power_max *= MICROWATT_PER_MILLIWATT;
+ dtpm->power_max *= nr_cpus;
+
+ return 0;
+}
+
+static void pd_release(struct dtpm *dtpm)
+{
+ struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
+ struct cpufreq_policy *policy;
+
+ if (freq_qos_request_active(&dtpm_cpu->qos_req))
+ freq_qos_remove_request(&dtpm_cpu->qos_req);
+
+ policy = cpufreq_cpu_get(dtpm_cpu->cpu);
+ if (policy) {
+ for_each_cpu(dtpm_cpu->cpu, policy->related_cpus)
+ per_cpu(dtpm_per_cpu, dtpm_cpu->cpu) = NULL;
+ }
+
+ kfree(dtpm_cpu);
+}
+
+static struct dtpm_ops dtpm_ops = {
+ .set_power_uw = set_pd_power_limit,
+ .get_power_uw = get_pd_power_uw,
+ .update_power_uw = update_pd_power_uw,
+ .release = pd_release,
+};
+
+static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
+{
+ struct dtpm_cpu *dtpm_cpu;
+
+ dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+ if (dtpm_cpu)
+ dtpm_update_power(&dtpm_cpu->dtpm);
+
+ return 0;
+}
+
+static int cpuhp_dtpm_cpu_online(unsigned int cpu)
+{
+ struct dtpm_cpu *dtpm_cpu;
+
+ dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+ if (dtpm_cpu)
+ return dtpm_update_power(&dtpm_cpu->dtpm);
+
+ return 0;
+}
+
+static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
+{
+ struct dtpm_cpu *dtpm_cpu;
+ struct cpufreq_policy *policy;
+ struct em_perf_domain *pd;
+ char name[CPUFREQ_NAME_LEN];
+ int ret = -ENOMEM;
+
+ dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+ if (dtpm_cpu)
+ return 0;
+
+ policy = cpufreq_cpu_get(cpu);
+ if (!policy)
+ return 0;
+
+ pd = em_cpu_get(cpu);
+ if (!pd || em_is_artificial(pd))
+ return -EINVAL;
+
+ dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL);
+ if (!dtpm_cpu)
+ return -ENOMEM;
+
+ dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops);
+ dtpm_cpu->cpu = cpu;
+
+ for_each_cpu(cpu, policy->related_cpus)
+ per_cpu(dtpm_per_cpu, cpu) = dtpm_cpu;
+
+ snprintf(name, sizeof(name), "cpu%d-cpufreq", dtpm_cpu->cpu);
+
+ ret = dtpm_register(name, &dtpm_cpu->dtpm, parent);
+ if (ret)
+ goto out_kfree_dtpm_cpu;
+
+ ret = freq_qos_add_request(&policy->constraints,
+ &dtpm_cpu->qos_req, FREQ_QOS_MAX,
+ pd->table[pd->nr_perf_states - 1].frequency);
+ if (ret)
+ goto out_dtpm_unregister;
+
+ return 0;
+
+out_dtpm_unregister:
+ dtpm_unregister(&dtpm_cpu->dtpm);
+ dtpm_cpu = NULL;
+
+out_kfree_dtpm_cpu:
+ for_each_cpu(cpu, policy->related_cpus)
+ per_cpu(dtpm_per_cpu, cpu) = NULL;
+ kfree(dtpm_cpu);
+
+ return ret;
+}
+
+static int dtpm_cpu_setup(struct dtpm *dtpm, struct device_node *np)
+{
+ int cpu;
+
+ cpu = of_cpu_node_to_id(np);
+ if (cpu < 0)
+ return 0;
+
+ return __dtpm_cpu_setup(cpu, dtpm);
+}
+
+static int dtpm_cpu_init(void)
+{
+ int ret;
+
+ /*
+ * The callbacks at CPU hotplug time are calling
+ * dtpm_update_power() which in turns calls update_pd_power().
+ *
+ * The function update_pd_power() uses the online mask to
+ * figure out the power consumption limits.
+ *
+ * At CPUHP_AP_ONLINE_DYN, the CPU is present in the CPU
+ * online mask when the cpuhp_dtpm_cpu_online function is
+ * called, but the CPU is still in the online mask for the
+ * tear down callback. So the power can not be updated when
+ * the CPU is unplugged.
+ *
+ * At CPUHP_AP_DTPM_CPU_DEAD, the situation is the opposite as
+ * above. The CPU online mask is not up to date when the CPU
+ * is plugged in.
+ *
+ * For this reason, we need to call the online and offline
+ * callbacks at different moments when the CPU online mask is
+ * consistent with the power numbers we want to update.
+ */
+ ret = cpuhp_setup_state(CPUHP_AP_DTPM_CPU_DEAD, "dtpm_cpu:offline",
+ NULL, cpuhp_dtpm_cpu_offline);
+ if (ret < 0)
+ return ret;
+
+ ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "dtpm_cpu:online",
+ cpuhp_dtpm_cpu_online, NULL);
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static void dtpm_cpu_exit(void)
+{
+ cpuhp_remove_state_nocalls(CPUHP_AP_ONLINE_DYN);
+ cpuhp_remove_state_nocalls(CPUHP_AP_DTPM_CPU_DEAD);
+}
+
+struct dtpm_subsys_ops dtpm_cpu_ops = {
+ .name = KBUILD_MODNAME,
+ .init = dtpm_cpu_init,
+ .exit = dtpm_cpu_exit,
+ .setup = dtpm_cpu_setup,
+};