aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/kernel/smp_twd.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 /arch/arm/kernel/smp_twd.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 'arch/arm/kernel/smp_twd.c')
-rw-r--r--arch/arm/kernel/smp_twd.c340
1 files changed, 340 insertions, 0 deletions
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
new file mode 100644
index 000000000..9a14f721a
--- /dev/null
+++ b/arch/arm/kernel/smp_twd.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/arch/arm/kernel/smp_twd.c
+ *
+ * Copyright (C) 2002 ARM Ltd.
+ * All Rights Reserved
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/smp.h>
+#include <linux/jiffies.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#include <asm/smp_twd.h>
+
+/* set up by the platform code */
+static void __iomem *twd_base;
+
+static struct clk *twd_clk;
+static unsigned long twd_timer_rate;
+static DEFINE_PER_CPU(bool, percpu_setup_called);
+
+static struct clock_event_device __percpu *twd_evt;
+static unsigned int twd_features =
+ CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+static int twd_ppi;
+
+static int twd_shutdown(struct clock_event_device *clk)
+{
+ writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
+ return 0;
+}
+
+static int twd_set_oneshot(struct clock_event_device *clk)
+{
+ /* period set, and timer enabled in 'next_event' hook */
+ writel_relaxed(TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_ONESHOT,
+ twd_base + TWD_TIMER_CONTROL);
+ return 0;
+}
+
+static int twd_set_periodic(struct clock_event_device *clk)
+{
+ unsigned long ctrl = TWD_TIMER_CONTROL_ENABLE |
+ TWD_TIMER_CONTROL_IT_ENABLE |
+ TWD_TIMER_CONTROL_PERIODIC;
+
+ writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
+ twd_base + TWD_TIMER_LOAD);
+ writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
+ return 0;
+}
+
+static int twd_set_next_event(unsigned long evt,
+ struct clock_event_device *unused)
+{
+ unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL);
+
+ ctrl |= TWD_TIMER_CONTROL_ENABLE;
+
+ writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER);
+ writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
+
+ return 0;
+}
+
+/*
+ * local_timer_ack: checks for a local timer interrupt.
+ *
+ * If a local timer interrupt has occurred, acknowledge and return 1.
+ * Otherwise, return 0.
+ */
+static int twd_timer_ack(void)
+{
+ if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) {
+ writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT);
+ return 1;
+ }
+
+ return 0;
+}
+
+static void twd_timer_stop(void)
+{
+ struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
+
+ twd_shutdown(clk);
+ disable_percpu_irq(clk->irq);
+}
+
+/*
+ * Updates clockevent frequency when the cpu frequency changes.
+ * Called on the cpu that is changing frequency with interrupts disabled.
+ */
+static void twd_update_frequency(void *new_rate)
+{
+ twd_timer_rate = *((unsigned long *) new_rate);
+
+ clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate);
+}
+
+static int twd_rate_change(struct notifier_block *nb,
+ unsigned long flags, void *data)
+{
+ struct clk_notifier_data *cnd = data;
+
+ /*
+ * The twd clock events must be reprogrammed to account for the new
+ * frequency. The timer is local to a cpu, so cross-call to the
+ * changing cpu.
+ */
+ if (flags == POST_RATE_CHANGE)
+ on_each_cpu(twd_update_frequency,
+ (void *)&cnd->new_rate, 1);
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block twd_clk_nb = {
+ .notifier_call = twd_rate_change,
+};
+
+static int twd_clk_init(void)
+{
+ if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk))
+ return clk_notifier_register(twd_clk, &twd_clk_nb);
+
+ return 0;
+}
+core_initcall(twd_clk_init);
+
+static void twd_calibrate_rate(void)
+{
+ unsigned long count;
+ u64 waitjiffies;
+
+ /*
+ * If this is the first time round, we need to work out how fast
+ * the timer ticks
+ */
+ if (twd_timer_rate == 0) {
+ pr_info("Calibrating local timer... ");
+
+ /* Wait for a tick to start */
+ waitjiffies = get_jiffies_64() + 1;
+
+ while (get_jiffies_64() < waitjiffies)
+ udelay(10);
+
+ /* OK, now the tick has started, let's get the timer going */
+ waitjiffies += 5;
+
+ /* enable, no interrupt or reload */
+ writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL);
+
+ /* maximum value */
+ writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
+
+ while (get_jiffies_64() < waitjiffies)
+ udelay(10);
+
+ count = readl_relaxed(twd_base + TWD_TIMER_COUNTER);
+
+ twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
+
+ pr_cont("%lu.%02luMHz.\n", twd_timer_rate / 1000000,
+ (twd_timer_rate / 10000) % 100);
+ }
+}
+
+static irqreturn_t twd_handler(int irq, void *dev_id)
+{
+ struct clock_event_device *evt = dev_id;
+
+ if (twd_timer_ack()) {
+ evt->event_handler(evt);
+ return IRQ_HANDLED;
+ }
+
+ return IRQ_NONE;
+}
+
+static void twd_get_clock(struct device_node *np)
+{
+ int err;
+
+ if (np)
+ twd_clk = of_clk_get(np, 0);
+ else
+ twd_clk = clk_get_sys("smp_twd", NULL);
+
+ if (IS_ERR(twd_clk)) {
+ pr_err("smp_twd: clock not found %d\n", (int) PTR_ERR(twd_clk));
+ return;
+ }
+
+ err = clk_prepare_enable(twd_clk);
+ if (err) {
+ pr_err("smp_twd: clock failed to prepare+enable: %d\n", err);
+ clk_put(twd_clk);
+ return;
+ }
+
+ twd_timer_rate = clk_get_rate(twd_clk);
+}
+
+/*
+ * Setup the local clock events for a CPU.
+ */
+static void twd_timer_setup(void)
+{
+ struct clock_event_device *clk = raw_cpu_ptr(twd_evt);
+ int cpu = smp_processor_id();
+
+ /*
+ * If the basic setup for this CPU has been done before don't
+ * bother with the below.
+ */
+ if (per_cpu(percpu_setup_called, cpu)) {
+ writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
+ clockevents_register_device(clk);
+ enable_percpu_irq(clk->irq, 0);
+ return;
+ }
+ per_cpu(percpu_setup_called, cpu) = true;
+
+ twd_calibrate_rate();
+
+ /*
+ * The following is done once per CPU the first time .setup() is
+ * called.
+ */
+ writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
+
+ clk->name = "local_timer";
+ clk->features = twd_features;
+ clk->rating = 350;
+ clk->set_state_shutdown = twd_shutdown;
+ clk->set_state_periodic = twd_set_periodic;
+ clk->set_state_oneshot = twd_set_oneshot;
+ clk->tick_resume = twd_shutdown;
+ clk->set_next_event = twd_set_next_event;
+ clk->irq = twd_ppi;
+ clk->cpumask = cpumask_of(cpu);
+
+ clockevents_config_and_register(clk, twd_timer_rate,
+ 0xf, 0xffffffff);
+ enable_percpu_irq(clk->irq, 0);
+}
+
+static int twd_timer_starting_cpu(unsigned int cpu)
+{
+ twd_timer_setup();
+ return 0;
+}
+
+static int twd_timer_dying_cpu(unsigned int cpu)
+{
+ twd_timer_stop();
+ return 0;
+}
+
+static int __init twd_local_timer_common_register(struct device_node *np)
+{
+ int err;
+
+ twd_evt = alloc_percpu(struct clock_event_device);
+ if (!twd_evt) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+
+ err = request_percpu_irq(twd_ppi, twd_handler, "twd", twd_evt);
+ if (err) {
+ pr_err("twd: can't register interrupt %d (%d)\n", twd_ppi, err);
+ goto out_free;
+ }
+
+ cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING,
+ "arm/timer/twd:starting",
+ twd_timer_starting_cpu, twd_timer_dying_cpu);
+
+ twd_get_clock(np);
+ if (!of_property_read_bool(np, "always-on"))
+ twd_features |= CLOCK_EVT_FEAT_C3STOP;
+
+ /*
+ * Immediately configure the timer on the boot CPU, unless we need
+ * jiffies to be incrementing to calibrate the rate in which case
+ * setup the timer in late_time_init.
+ */
+ if (twd_timer_rate)
+ twd_timer_setup();
+ else
+ late_time_init = twd_timer_setup;
+
+ return 0;
+
+out_free:
+ iounmap(twd_base);
+ twd_base = NULL;
+ free_percpu(twd_evt);
+
+ return err;
+}
+
+static int __init twd_local_timer_of_register(struct device_node *np)
+{
+ int err;
+
+ twd_ppi = irq_of_parse_and_map(np, 0);
+ if (!twd_ppi) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ twd_base = of_iomap(np, 0);
+ if (!twd_base) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = twd_local_timer_common_register(np);
+
+out:
+ WARN(err, "twd_local_timer_of_register failed (%d)\n", err);
+ return err;
+}
+TIMER_OF_DECLARE(arm_twd_a9, "arm,cortex-a9-twd-timer", twd_local_timer_of_register);
+TIMER_OF_DECLARE(arm_twd_a5, "arm,cortex-a5-twd-timer", twd_local_timer_of_register);
+TIMER_OF_DECLARE(arm_twd_11mp, "arm,arm11mp-twd-timer", twd_local_timer_of_register);