/* * x86 SMP booting functions * * (c) 1995 Alan Cox, Building #3 * (c) 1998, 1999, 2000 Ingo Molnar * * Much of the core SMP work is based on previous work by Thomas Radke, to * whom a great many thanks are extended. * * Thanks to Intel for making available several different Pentium, * Pentium Pro and Pentium-II/Xeon MP machines. * Original development of Linux SMP code supported by Caldera. * * This code is released under the GNU General Public License version 2 or * later. * * Fixes * Felix Koop : NR_CPUS used properly * Jose Renau : Handle single CPU case. * Alan Cox : By repeated request 8) - Total BogoMIPS report. * Greg Wright : Fix for kernel stacks panic. * Erich Boleyn : MP v1.4 and additional changes. * Matthias Sattler : Changes for 2.1 kernel map. * Michel Lespinasse : Changes for 2.1 kernel map. * Michael Chastain : Change trampoline.S to gnu as. * Alan Cox : Dumb bug: 'B' step PPro's are fine * Ingo Molnar : Added APIC timers, based on code * from Jose Renau * Ingo Molnar : various cleanups and rewrites * Tigran Aivazian : fixed "0.00 in /proc/uptime on SMP" bug. * Maciej W. Rozycki : Bits for genuine 82489DX APICs * Martin J. Bligh : Added support for multi-quad systems * Dave Jones : Report invalid combinations of Athlon CPUs. * Rusty Russell : Hacked into shape for new "hotplug" boot process. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include /* which logical CPU number maps to which CPU (physical APIC ID) */ u16 x86_cpu_to_apicid_init[NR_CPUS] __initdata = { [0 ... NR_CPUS-1] = BAD_APICID }; void *x86_cpu_to_apicid_early_ptr; DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID; EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); u16 x86_bios_cpu_apicid_init[NR_CPUS] __initdata = { [0 ... NR_CPUS-1] = BAD_APICID }; void *x86_bios_cpu_apicid_early_ptr; DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID; EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid); u8 apicid_2_node[MAX_APICID]; extern void map_cpu_to_logical_apicid(void); extern void unmap_cpu_to_logical_apicid(int cpu); /* State of each CPU. */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; /* Store all idle threads, this can be reused instead of creating * a new thread. Also avoids complicated thread destroy functionality * for idle threads. */ #ifdef CONFIG_HOTPLUG_CPU /* * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is * removed after init for !CONFIG_HOTPLUG_CPU. */ static DEFINE_PER_CPU(struct task_struct *, idle_thread_array); #define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x)) #define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p)) #else struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ; #define get_idle_for_cpu(x) (idle_thread_array[(x)]) #define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p)) #endif static atomic_t init_deasserted; static void __cpuinit smp_callin(void) { int cpuid, phys_id; unsigned long timeout; /* * If waken up by an INIT in an 82489DX configuration * we may get here before an INIT-deassert IPI reaches * our local APIC. We have to wait for the IPI or we'll * lock up on an APIC access. */ wait_for_init_deassert(&init_deasserted); /* * (This works even if the APIC is not enabled.) */ phys_id = GET_APIC_ID(apic_read(APIC_ID)); cpuid = smp_processor_id(); if (cpu_isset(cpuid, cpu_callin_map)) { printk("huh, phys CPU#%d, CPU#%d already present??\n", phys_id, cpuid); BUG(); } Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id); /* * STARTUP IPIs are fragile beasts as they might sometimes * trigger some glue motherboard logic. Complete APIC bus * silence for 1 second, this overestimates the time the * boot CPU is spending to send the up to 2 STARTUP IPIs * by a factor of two. This should be enough. */ /* * Waiting 2s total for startup (udelay is not yet working) */ timeout = jiffies + 2*HZ; while (time_before(jiffies, timeout)) { /* * Has the boot CPU finished it's STARTUP sequence? */ if (cpu_isset(cpuid, cpu_callout_map)) break; cpu_relax(); } if (!time_before(jiffies, timeout)) { printk("BUG: CPU%d started up but did not get a callout!\n", cpuid); BUG(); } /* * the boot CPU has finished the init stage and is spinning * on callin_map until we finish. We are free to set up this * CPU, first the APIC. (this is probably redundant on most * boards) */ Dprintk("CALLIN, before setup_local_APIC().\n"); smp_callin_clear_local_apic(); setup_local_APIC(); end_local_APIC_setup(); map_cpu_to_logical_apicid(); /* * Get our bogomips. */ local_irq_enable(); calibrate_delay(); local_irq_disable(); Dprintk("Stack at about %p\n",&cpuid); /* * Save our processor parameters */ smp_store_cpu_info(cpuid); /* * Allow the master to continue. */ cpu_set(cpuid, cpu_callin_map); } /* * Activate a secondary processor. */ static void __cpuinit start_secondary(void *unused) { /* * Don't put *anything* before cpu_init(), SMP booting is too * fragile that we want to limit the things done here to the * most necessary things. */ #ifdef CONFIG_VMI vmi_bringup(); #endif cpu_init(); preempt_disable(); smp_callin(); /* otherwise gcc will move up smp_processor_id before the cpu_init */ barrier(); /* * Check TSC synchronization with the BP: */ check_tsc_sync_target(); if (nmi_watchdog == NMI_IO_APIC) { disable_8259A_irq(0); enable_NMI_through_LVT0(); enable_8259A_irq(0); } /* This must be done before setting cpu_online_map */ set_cpu_sibling_map(raw_smp_processor_id()); wmb(); /* * We need to hold call_lock, so there is no inconsistency * between the time smp_call_function() determines number of * IPI recipients, and the time when the determination is made * for which cpus receive the IPI. Holding this * lock helps us to not include this cpu in a currently in progress * smp_call_function(). */ lock_ipi_call_lock(); cpu_set(smp_processor_id(), cpu_online_map); unlock_ipi_call_lock(); per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; setup_secondary_clock(); wmb(); cpu_idle(); } /* * Everything has been set up for the secondary * CPUs - they just need to reload everything * from the task structure * This function must not return. */ void __devinit initialize_secondary(void) { /* * We don't actually need to load the full TSS, * basically just the stack pointer and the ip. */ asm volatile( "movl %0,%%esp\n\t" "jmp *%1" : :"m" (current->thread.sp),"m" (current->thread.ip)); } static inline void __inquire_remote_apic(int apicid) { unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; char *names[] = { "ID", "VERSION", "SPIV" }; int timeout; u32 status; printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid); for (i = 0; i < ARRAY_SIZE(regs); i++) { printk(KERN_INFO "... APIC #%d %s: ", apicid, names[i]); /* * Wait for idle. */ status = safe_apic_wait_icr_idle(); if (status) printk(KERN_CONT "a previous APIC delivery may have failed\n"); apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid)); apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]); timeout = 0; do { udelay(100); status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK; } while (status == APIC_ICR_RR_INPROG && timeout++ < 1000); switch (status) { case APIC_ICR_RR_VALID: status = apic_read(APIC_RRR); printk(KERN_CONT "%08x\n", status); break; default: printk(KERN_CONT "failed\n"); } } } #ifdef WAKE_SECONDARY_VIA_NMI /* * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this * won't ... remember to clear down the APIC, etc later. */ static int __devinit wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; int maxlvt; /* Target chip */ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid)); /* Boot on the stack */ /* Kick the second */ apic_write_around(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL); Dprintk("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); /* * Give the other CPU some time to accept the IPI. */ udelay(200); /* * Due to the Pentium erratum 3AP. */ maxlvt = lapic_get_maxlvt(); if (maxlvt > 3) { apic_read_around(APIC_SPIV); apic_write(APIC_ESR, 0); } accept_status = (apic_read(APIC_ESR) & 0xEF); Dprintk("NMI sent.\n"); if (send_status) printk("APIC never delivered???\n"); if (accept_status) printk("APIC delivery error (%lx).\n", accept_status); return (send_status | accept_status); } #endif /* WAKE_SECONDARY_VIA_NMI */ #ifdef WAKE_SECONDARY_VIA_INIT static int __devinit wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; int maxlvt, num_starts, j; /* * Be paranoid about clearing APIC errors. */ if (APIC_INTEGRATED(apic_version[phys_apicid])) { apic_read_around(APIC_SPIV); apic_write(APIC_ESR, 0); apic_read(APIC_ESR); } Dprintk("Asserting INIT.\n"); /* * Turn INIT on target chip */ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); /* * Send IPI */ apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT); Dprintk("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); mdelay(10); Dprintk("Deasserting INIT.\n"); /* Target chip */ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); /* Send IPI */ apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT); Dprintk("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); mb(); atomic_set(&init_deasserted, 1); /* * Should we send STARTUP IPIs ? * * Determine this based on the APIC version. * If we don't have an integrated APIC, don't send the STARTUP IPIs. */ if (APIC_INTEGRATED(apic_version[phys_apicid])) num_starts = 2; else num_starts = 0; /* * Paravirt / VMI wants a startup IPI hook here to set up the * target processor state. */ startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, (unsigned long) stack_start.sp); /* * Run STARTUP IPI loop. */ Dprintk("#startup loops: %d.\n", num_starts); maxlvt = lapic_get_maxlvt(); for (j = 1; j <= num_starts; j++) { Dprintk("Sending STARTUP #%d.\n",j); apic_read_around(APIC_SPIV); apic_write(APIC_ESR, 0); apic_read(APIC_ESR); Dprintk("After apic_write.\n"); /* * STARTUP IPI */ /* Target chip */ apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); /* Boot on the stack */ /* Kick the second */ apic_write_around(APIC_ICR, APIC_DM_STARTUP | (start_eip >> 12)); /* * Give the other CPU some time to accept the IPI. */ udelay(300); Dprintk("Startup point 1.\n"); Dprintk("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); /* * Give the other CPU some time to accept the IPI. */ udelay(200); /* * Due to the Pentium erratum 3AP. */ if (maxlvt > 3) { apic_read_around(APIC_SPIV); apic_write(APIC_ESR, 0); } accept_status = (apic_read(APIC_ESR) & 0xEF); if (send_status || accept_status) break; } Dprintk("After Startup.\n"); if (send_status) printk("APIC never delivered???\n"); if (accept_status) printk("APIC delivery error (%lx).\n", accept_status); return (send_status | accept_status); } #endif /* WAKE_SECONDARY_VIA_INIT */ extern cpumask_t cpu_initialized; struct create_idle { struct work_struct work; struct task_struct *idle; struct completion done; int cpu; }; static void __cpuinit do_fork_idle(struct work_struct *work) { struct create_idle *c_idle = container_of(work, struct create_idle, work); c_idle->idle = fork_idle(c_idle->cpu); complete(&c_idle->done); } static int __cpuinit do_boot_cpu(int apicid, int cpu) /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu. */ { unsigned long boot_error = 0; int timeout; unsigned long start_eip; unsigned short nmi_high = 0, nmi_low = 0; struct create_idle c_idle = { .cpu = cpu, .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), }; INIT_WORK(&c_idle.work, do_fork_idle); alternatives_smp_switch(1); c_idle.idle = get_idle_for_cpu(cpu); /* * We can't use kernel_thread since we must avoid to * reschedule the child. */ if (c_idle.idle) { c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *) (THREAD_SIZE + task_stack_page(c_idle.idle))) - 1); init_idle(c_idle.idle, cpu); goto do_rest; } if (!keventd_up() || current_is_keventd()) c_idle.work.func(&c_idle.work); else { schedule_work(&c_idle.work); wait_for_completion(&c_idle.done); } if (IS_ERR(c_idle.idle)) { printk(KERN_ERR "failed fork for CPU %d\n", cpu); return PTR_ERR(c_idle.idle); } set_idle_for_cpu(cpu, c_idle.idle); do_rest: per_cpu(current_task, cpu) = c_idle.idle; init_gdt(cpu); early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); c_idle.idle->thread.ip = (unsigned long) start_secondary; /* start_eip had better be page-aligned! */ start_eip = setup_trampoline(); /* So we see what's up */ printk("Booting processor %d/%d ip %lx\n", cpu, apicid, start_eip); /* Stack for startup_32 can be just as for start_secondary onwards */ stack_start.sp = (void *) c_idle.idle->thread.sp; irq_ctx_init(cpu); /* * This grunge runs the startup process for * the targeted processor. */ atomic_set(&init_deasserted, 0); Dprintk("Setting warm reset code and vector.\n"); store_NMI_vector(&nmi_high, &nmi_low); smpboot_setup_warm_reset_vector(start_eip); /* * Be paranoid about clearing APIC errors. */ apic_write(APIC_ESR, 0); apic_read(APIC_ESR); /* * Starting actual IPI sequence... */ boot_error = wakeup_secondary_cpu(apicid, start_eip); if (!boot_error) { /* * allow APs to start initializing. */ Dprintk("Before Callout %d.\n", cpu); cpu_set(cpu, cpu_callout_map); Dprintk("After Callout %d.\n", cpu); /* * Wait 5s total for a response */ for (timeout = 0; timeout < 50000; timeout++) { if (cpu_isset(cpu, cpu_callin_map)) break; /* It has booted */ udelay(100); } if (cpu_isset(cpu, cpu_callin_map)) { /* number CPUs logically, starting from 1 (BSP is 0) */ Dprintk("OK.\n"); printk("CPU%d: ", cpu); print_cpu_info(&cpu_data(cpu)); Dprintk("CPU has booted.\n"); } else { boot_error= 1; if (*((volatile unsigned char *)trampoline_base) == 0xA5) /* trampoline started but...? */ printk("Stuck ??\n"); else /* trampoline code not run */ printk("Not responding.\n"); inquire_remote_apic(apicid); } } if (boot_error) { /* Try to put things back the way they were before ... */ unmap_cpu_to_logical_apicid(cpu); cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */ cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ cpu_clear(cpu, cpu_possible_map); per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; } /* mark "stuck" area as not stuck */ *((volatile unsigned long *)trampoline_base) = 0; return boot_error; } #ifdef CONFIG_HOTPLUG_CPU void cpu_exit_clear(void) { int cpu = raw_smp_processor_id(); idle_task_exit(); cpu_uninit(); irq_ctx_exit(cpu); cpu_clear(cpu, cpu_callout_map); cpu_clear(cpu, cpu_callin_map); unmap_cpu_to_logical_apicid(cpu); } #endif static int boot_cpu_logical_apicid; /* Where the IO area was mapped on multiquad, always 0 otherwise */ void *xquad_portio; #ifdef CONFIG_X86_NUMAQ EXPORT_SYMBOL(xquad_portio); #endif static void __init disable_smp(void) { cpu_possible_map = cpumask_of_cpu(0); cpu_present_map = cpumask_of_cpu(0); smpboot_clear_io_apic_irqs(); phys_cpu_present_map = physid_mask_of_physid(0); map_cpu_to_logical_apicid(); cpu_set(0, per_cpu(cpu_sibling_map, 0)); cpu_set(0, per_cpu(cpu_core_map, 0)); } static int __init smp_sanity_check(unsigned max_cpus) { /* * If we couldn't find an SMP configuration at boot time, * get out of here now! */ if (!smp_found_config && !acpi_lapic) { printk(KERN_NOTICE "SMP motherboard not detected.\n"); disable_smp(); if (APIC_init_uniprocessor()) printk(KERN_NOTICE "Local APIC not detected." " Using dummy APIC emulation.\n"); return -1; } /* * Should not be necessary because the MP table should list the boot * CPU too, but we do it for the sake of robustness anyway. * Makes no sense to do this check in clustered apic mode, so skip it */ if (!check_phys_apicid_present(boot_cpu_physical_apicid)) { printk("weird, boot CPU (#%d) not listed by the BIOS.\n", boot_cpu_physical_apicid); physid_set(hard_smp_processor_id(), phys_cpu_present_map); } /* * If we couldn't find a local APIC, then get out of here now! */ if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && !cpu_has_apic) { printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n", boot_cpu_physical_apicid); printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n"); return -1; } verify_local_APIC(); /* * If SMP should be disabled, then really disable it! */ if (!max_cpus) { smp_found_config = 0; printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n"); if (nmi_watchdog == NMI_LOCAL_APIC) { printk(KERN_INFO "activating minimal APIC for NMI watchdog use.\n"); connect_bsp_APIC(); setup_local_APIC(); end_local_APIC_setup(); } return -1; } return 0; } /* * Cycle through the processors sending APIC IPIs to boot each. */ static void __init smp_boot_cpus(unsigned int max_cpus) { /* * Setup boot CPU information */ smp_store_cpu_info(0); /* Final full version of the data */ printk(KERN_INFO "CPU%d: ", 0); print_cpu_info(&cpu_data(0)); boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); boot_cpu_logical_apicid = logical_smp_processor_id(); current_thread_info()->cpu = 0; set_cpu_sibling_map(0); if (smp_sanity_check(max_cpus) < 0) { printk(KERN_INFO "SMP disabled\n"); disable_smp(); return; } connect_bsp_APIC(); setup_local_APIC(); end_local_APIC_setup(); map_cpu_to_logical_apicid(); setup_portio_remap(); smpboot_setup_io_apic(); setup_boot_clock(); } /* These are wrappers to interface to the new boot process. Someone who understands all this stuff should rewrite it properly. --RR 15/Jul/02 */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { nmi_watchdog_default(); cpu_callin_map = cpumask_of_cpu(0); mb(); smp_boot_cpus(max_cpus); } void __init native_smp_prepare_boot_cpu(void) { unsigned int cpu = smp_processor_id(); init_gdt(cpu); switch_to_new_gdt(); cpu_set(cpu, cpu_callout_map); __get_cpu_var(cpu_state) = CPU_ONLINE; } int __cpuinit native_cpu_up(unsigned int cpu) { int apicid = cpu_present_to_apicid(cpu); unsigned long flags; int err; WARN_ON(irqs_disabled()); Dprintk("++++++++++++++++++++=_---CPU UP %u\n", cpu); if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid || !physid_isset(apicid, phys_cpu_present_map)) { printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu); return -EINVAL; } /* * Already booted CPU? */ if (cpu_isset(cpu, cpu_callin_map)) { Dprintk("do_boot_cpu %d Already started\n", cpu); return -ENOSYS; } /* * Save current MTRR state in case it was changed since early boot * (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync: */ mtrr_save_state(); per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; /* init low mem mapping */ clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS, min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS)); flush_tlb_all(); err = do_boot_cpu(apicid, cpu); if (err < 0) { Dprintk("do_boot_cpu failed %d\n", err); return err; } /* * Check TSC synchronization with the AP (keep irqs disabled * while doing so): */ local_irq_save(flags); check_tsc_sync_source(cpu); local_irq_restore(flags); while (!cpu_isset(cpu, cpu_online_map)) { cpu_relax(); touch_nmi_watchdog(); } return 0; } extern void impress_friends(void); extern void smp_checks(void); void __init native_smp_cpus_done(unsigned int max_cpus) { /* * Cleanup possible dangling ends... */ smpboot_restore_warm_reset_vector(); Dprintk("Boot done.\n"); impress_friends(); smp_checks(); #ifdef CONFIG_X86_IO_APIC setup_ioapic_dest(); #endif check_nmi_watchdog(); zap_low_mappings(); }