aboutsummaryrefslogtreecommitdiff
path: root/arch/parisc/kernel/smp.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/parisc/kernel/smp.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/parisc/kernel/smp.c')
-rw-r--r--arch/parisc/kernel/smp.c515
1 files changed, 515 insertions, 0 deletions
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
new file mode 100644
index 000000000..7dbd92caf
--- /dev/null
+++ b/arch/parisc/kernel/smp.c
@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+** SMP Support
+**
+** Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+** Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com>
+** Copyright (C) 2001,2004 Grant Grundler <grundler@parisc-linux.org>
+**
+** Lots of stuff stolen from arch/alpha/kernel/smp.c
+** ...and then parisc stole from arch/ia64/kernel/smp.c. Thanks David! :^)
+**
+** Thanks to John Curry and Ullas Ponnadi. I learned a lot from their work.
+** -grant (1/12/2001)
+**
+*/
+#include <linux/types.h>
+#include <linux/spinlock.h>
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched/mm.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/kernel_stat.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/bitops.h>
+#include <linux/ftrace.h>
+#include <linux/cpu.h>
+#include <linux/kgdb.h>
+#include <linux/sched/hotplug.h>
+
+#include <linux/atomic.h>
+#include <asm/current.h>
+#include <asm/delay.h>
+#include <asm/tlbflush.h>
+
+#include <asm/io.h>
+#include <asm/irq.h> /* for CPU_IRQ_REGION and friends */
+#include <asm/mmu_context.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+
+#undef DEBUG_SMP
+#ifdef DEBUG_SMP
+static int smp_debug_lvl = 0;
+#define smp_debug(lvl, printargs...) \
+ if (lvl >= smp_debug_lvl) \
+ printk(printargs);
+#else
+#define smp_debug(lvl, ...) do { } while(0)
+#endif /* DEBUG_SMP */
+
+volatile struct task_struct *smp_init_current_idle_task;
+
+/* track which CPU is booting */
+static volatile int cpu_now_booting;
+
+static DEFINE_PER_CPU(spinlock_t, ipi_lock);
+
+enum ipi_message_type {
+ IPI_NOP=0,
+ IPI_RESCHEDULE=1,
+ IPI_CALL_FUNC,
+ IPI_CPU_START,
+ IPI_CPU_STOP,
+ IPI_CPU_TEST,
+#ifdef CONFIG_KGDB
+ IPI_ENTER_KGDB,
+#endif
+};
+
+
+/********** SMP inter processor interrupt and communication routines */
+
+#undef PER_CPU_IRQ_REGION
+#ifdef PER_CPU_IRQ_REGION
+/* XXX REVISIT Ignore for now.
+** *May* need this "hook" to register IPI handler
+** once we have perCPU ExtIntr switch tables.
+*/
+static void
+ipi_init(int cpuid)
+{
+#error verify IRQ_OFFSET(IPI_IRQ) is ipi_interrupt() in new IRQ region
+
+ if(cpu_online(cpuid) )
+ {
+ switch_to_idle_task(current);
+ }
+
+ return;
+}
+#endif
+
+
+/*
+** Yoink this CPU from the runnable list...
+**
+*/
+static void
+halt_processor(void)
+{
+ /* REVISIT : redirect I/O Interrupts to another CPU? */
+ /* REVISIT : does PM *know* this CPU isn't available? */
+ set_cpu_online(smp_processor_id(), false);
+ local_irq_disable();
+ __pdc_cpu_rendezvous();
+ for (;;)
+ ;
+}
+
+
+irqreturn_t __irq_entry
+ipi_interrupt(int irq, void *dev_id)
+{
+ int this_cpu = smp_processor_id();
+ struct cpuinfo_parisc *p = &per_cpu(cpu_data, this_cpu);
+ unsigned long ops;
+ unsigned long flags;
+
+ for (;;) {
+ spinlock_t *lock = &per_cpu(ipi_lock, this_cpu);
+ spin_lock_irqsave(lock, flags);
+ ops = p->pending_ipi;
+ p->pending_ipi = 0;
+ spin_unlock_irqrestore(lock, flags);
+
+ mb(); /* Order bit clearing and data access. */
+
+ if (!ops)
+ break;
+
+ while (ops) {
+ unsigned long which = ffz(~ops);
+
+ ops &= ~(1 << which);
+
+ switch (which) {
+ case IPI_NOP:
+ smp_debug(100, KERN_DEBUG "CPU%d IPI_NOP\n", this_cpu);
+ break;
+
+ case IPI_RESCHEDULE:
+ smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu);
+ inc_irq_stat(irq_resched_count);
+ scheduler_ipi();
+ break;
+
+ case IPI_CALL_FUNC:
+ smp_debug(100, KERN_DEBUG "CPU%d IPI_CALL_FUNC\n", this_cpu);
+ inc_irq_stat(irq_call_count);
+ generic_smp_call_function_interrupt();
+ break;
+
+ case IPI_CPU_START:
+ smp_debug(100, KERN_DEBUG "CPU%d IPI_CPU_START\n", this_cpu);
+ break;
+
+ case IPI_CPU_STOP:
+ smp_debug(100, KERN_DEBUG "CPU%d IPI_CPU_STOP\n", this_cpu);
+ halt_processor();
+ break;
+
+ case IPI_CPU_TEST:
+ smp_debug(100, KERN_DEBUG "CPU%d is alive!\n", this_cpu);
+ break;
+#ifdef CONFIG_KGDB
+ case IPI_ENTER_KGDB:
+ smp_debug(100, KERN_DEBUG "CPU%d ENTER_KGDB\n", this_cpu);
+ kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+ break;
+#endif
+ default:
+ printk(KERN_CRIT "Unknown IPI num on CPU%d: %lu\n",
+ this_cpu, which);
+ return IRQ_NONE;
+ } /* Switch */
+
+ /* before doing more, let in any pending interrupts */
+ if (ops) {
+ local_irq_enable();
+ local_irq_disable();
+ }
+ } /* while (ops) */
+ }
+ return IRQ_HANDLED;
+}
+
+
+static inline void
+ipi_send(int cpu, enum ipi_message_type op)
+{
+ struct cpuinfo_parisc *p = &per_cpu(cpu_data, cpu);
+ spinlock_t *lock = &per_cpu(ipi_lock, cpu);
+ unsigned long flags;
+
+ spin_lock_irqsave(lock, flags);
+ p->pending_ipi |= 1 << op;
+ gsc_writel(IPI_IRQ - CPU_IRQ_BASE, p->hpa);
+ spin_unlock_irqrestore(lock, flags);
+}
+
+static void
+send_IPI_mask(const struct cpumask *mask, enum ipi_message_type op)
+{
+ int cpu;
+
+ for_each_cpu(cpu, mask)
+ ipi_send(cpu, op);
+}
+
+static inline void
+send_IPI_single(int dest_cpu, enum ipi_message_type op)
+{
+ BUG_ON(dest_cpu == NO_PROC_ID);
+
+ ipi_send(dest_cpu, op);
+}
+
+static inline void
+send_IPI_allbutself(enum ipi_message_type op)
+{
+ int i;
+
+ preempt_disable();
+ for_each_online_cpu(i) {
+ if (i != smp_processor_id())
+ send_IPI_single(i, op);
+ }
+ preempt_enable();
+}
+
+#ifdef CONFIG_KGDB
+void kgdb_roundup_cpus(void)
+{
+ send_IPI_allbutself(IPI_ENTER_KGDB);
+}
+#endif
+
+inline void
+smp_send_stop(void) { send_IPI_allbutself(IPI_CPU_STOP); }
+
+void
+smp_send_reschedule(int cpu) { send_IPI_single(cpu, IPI_RESCHEDULE); }
+
+void
+smp_send_all_nop(void)
+{
+ send_IPI_allbutself(IPI_NOP);
+}
+
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
+{
+ send_IPI_mask(mask, IPI_CALL_FUNC);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+ send_IPI_single(cpu, IPI_CALL_FUNC);
+}
+
+/*
+ * Called by secondaries to update state and initialize CPU registers.
+ */
+static void
+smp_cpu_init(int cpunum)
+{
+ extern void init_IRQ(void); /* arch/parisc/kernel/irq.c */
+ extern void start_cpu_itimer(void); /* arch/parisc/kernel/time.c */
+
+ /* Set modes and Enable floating point coprocessor */
+ init_per_cpu(cpunum);
+
+ disable_sr_hashing();
+
+ mb();
+
+ /* Well, support 2.4 linux scheme as well. */
+ if (cpu_online(cpunum)) {
+ extern void machine_halt(void); /* arch/parisc.../process.c */
+
+ printk(KERN_CRIT "CPU#%d already initialized!\n", cpunum);
+ machine_halt();
+ }
+
+ notify_cpu_starting(cpunum);
+
+ set_cpu_online(cpunum, true);
+
+ /* Initialise the idle task for this CPU */
+ mmgrab(&init_mm);
+ current->active_mm = &init_mm;
+ BUG_ON(current->mm);
+ enter_lazy_tlb(&init_mm, current);
+
+ init_IRQ(); /* make sure no IRQs are enabled or pending */
+ start_cpu_itimer();
+}
+
+
+/*
+ * Slaves start using C here. Indirectly called from smp_slave_stext.
+ * Do what start_kernel() and main() do for boot strap processor (aka monarch)
+ */
+void smp_callin(unsigned long pdce_proc)
+{
+ int slave_id = cpu_now_booting;
+
+#ifdef CONFIG_64BIT
+ WARN_ON(((unsigned long)(PAGE0->mem_pdc_hi) << 32
+ | PAGE0->mem_pdc) != pdce_proc);
+#endif
+
+ smp_cpu_init(slave_id);
+
+ flush_cache_all_local(); /* start with known state */
+ flush_tlb_all_local(NULL);
+
+ local_irq_enable(); /* Interrupts have been off until now */
+
+ cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
+
+ /* NOTREACHED */
+ panic("smp_callin() AAAAaaaaahhhh....\n");
+}
+
+/*
+ * Bring one cpu online.
+ */
+static int smp_boot_one_cpu(int cpuid, struct task_struct *idle)
+{
+ const struct cpuinfo_parisc *p = &per_cpu(cpu_data, cpuid);
+ long timeout;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ int i;
+
+ /* reset irq statistics for this CPU */
+ memset(&per_cpu(irq_stat, cpuid), 0, sizeof(irq_cpustat_t));
+ for (i = 0; i < NR_IRQS; i++) {
+ struct irq_desc *desc = irq_to_desc(i);
+
+ if (desc && desc->kstat_irqs)
+ *per_cpu_ptr(desc->kstat_irqs, cpuid) = 0;
+ }
+#endif
+
+ /* wait until last booting CPU has started. */
+ while (cpu_now_booting)
+ ;
+
+ /* Let _start know what logical CPU we're booting
+ ** (offset into init_tasks[],cpu_data[])
+ */
+ cpu_now_booting = cpuid;
+
+ /*
+ ** boot strap code needs to know the task address since
+ ** it also contains the process stack.
+ */
+ smp_init_current_idle_task = idle ;
+ mb();
+
+ printk(KERN_INFO "Releasing cpu %d now, hpa=%lx\n", cpuid, p->hpa);
+
+ /*
+ ** This gets PDC to release the CPU from a very tight loop.
+ **
+ ** From the PA-RISC 2.0 Firmware Architecture Reference Specification:
+ ** "The MEM_RENDEZ vector specifies the location of OS_RENDEZ which
+ ** is executed after receiving the rendezvous signal (an interrupt to
+ ** EIR{0}). MEM_RENDEZ is valid only when it is nonzero and the
+ ** contents of memory are valid."
+ */
+ gsc_writel(TIMER_IRQ - CPU_IRQ_BASE, p->hpa);
+ mb();
+
+ /*
+ * OK, wait a bit for that CPU to finish staggering about.
+ * Slave will set a bit when it reaches smp_cpu_init().
+ * Once the "monarch CPU" sees the bit change, it can move on.
+ */
+ for (timeout = 0; timeout < 10000; timeout++) {
+ if(cpu_online(cpuid)) {
+ /* Which implies Slave has started up */
+ cpu_now_booting = 0;
+ goto alive ;
+ }
+ udelay(100);
+ barrier();
+ }
+ printk(KERN_CRIT "SMP: CPU:%d is stuck.\n", cpuid);
+ return -1;
+
+alive:
+ /* Remember the Slave data */
+ smp_debug(100, KERN_DEBUG "SMP: CPU:%d came alive after %ld _us\n",
+ cpuid, timeout * 100);
+ return 0;
+}
+
+void __init smp_prepare_boot_cpu(void)
+{
+ int bootstrap_processor = per_cpu(cpu_data, 0).cpuid;
+
+ /* Setup BSP mappings */
+ printk(KERN_INFO "SMP: bootstrap CPU ID is %d\n", bootstrap_processor);
+
+ set_cpu_online(bootstrap_processor, true);
+ set_cpu_present(bootstrap_processor, true);
+}
+
+
+
+/*
+** inventory.c:do_inventory() hasn't yet been run and thus we
+** don't 'discover' the additional CPUs until later.
+*/
+void __init smp_prepare_cpus(unsigned int max_cpus)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ spin_lock_init(&per_cpu(ipi_lock, cpu));
+
+ init_cpu_present(cpumask_of(0));
+}
+
+
+void __init smp_cpus_done(unsigned int cpu_max)
+{
+}
+
+
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+{
+ if (cpu_online(cpu))
+ return 0;
+
+ if (num_online_cpus() < setup_max_cpus && smp_boot_one_cpu(cpu, tidle))
+ return -EIO;
+
+ return cpu_online(cpu) ? 0 : -EIO;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ unsigned int cpu = smp_processor_id();
+
+ remove_cpu_topology(cpu);
+
+ /*
+ * Take this CPU offline. Once we clear this, we can't return,
+ * and we must not schedule until we're ready to give up the cpu.
+ */
+ set_cpu_online(cpu, false);
+
+ /* Find a new timesync master */
+ if (cpu == time_keeper_id) {
+ time_keeper_id = cpumask_first(cpu_online_mask);
+ pr_info("CPU %d is now promoted to time-keeper master\n", time_keeper_id);
+ }
+
+ disable_percpu_irq(IPI_IRQ);
+
+ irq_migrate_all_off_this_cpu();
+
+ flush_cache_all_local();
+ flush_tlb_all_local(NULL);
+
+ /* disable all irqs, including timer irq */
+ local_irq_disable();
+
+ /* wait for next timer irq ... */
+ mdelay(1000/HZ+100);
+
+ /* ... and then clear all pending external irqs */
+ set_eiem(0);
+ mtctl(~0UL, CR_EIRR);
+ mfctl(CR_EIRR);
+ mtctl(0, CR_EIRR);
+#endif
+ return 0;
+}
+
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpu_die(unsigned int cpu)
+{
+ pdc_cpu_rendezvous_lock();
+
+ if (!cpu_wait_death(cpu, 5)) {
+ pr_crit("CPU%u: cpu didn't die\n", cpu);
+ return;
+ }
+ pr_info("CPU%u: is shutting down\n", cpu);
+
+ /* set task's state to interruptible sleep */
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout((IS_ENABLED(CONFIG_64BIT) ? 8:2) * HZ);
+
+ pdc_cpu_rendezvous_unlock();
+}