diff options
Diffstat (limited to 'arch/x86/kernel/smpboot.c')
| -rw-r--r-- | arch/x86/kernel/smpboot.c | 1795 |
1 files changed, 508 insertions, 1287 deletions
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9320285a5e29..5cd6950ab672 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -53,12 +53,18 @@ #include <linux/tboot.h> #include <linux/gfp.h> #include <linux/cpuidle.h> +#include <linux/kexec.h> #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> -#include <linux/syscore_ops.h> +#include <linux/stackprotector.h> +#include <linux/cpuhotplug.h> +#include <linux/mc146818rtc.h> +#include <linux/acpi.h> #include <asm/acpi.h> +#include <asm/cacheinfo.h> +#include <asm/cpuid/api.h> #include <asm/desc.h> #include <asm/nmi.h> #include <asm/irq.h> @@ -70,10 +76,10 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> -#include <asm/fpu/internal.h> +#include <asm/fpu/api.h> #include <asm/setup.h> #include <asm/uv/uv.h> -#include <linux/mc146818rtc.h> +#include <asm/microcode.h> #include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> @@ -82,10 +88,8 @@ #include <asm/spec-ctrl.h> #include <asm/hw_irq.h> #include <asm/stackprotector.h> - -#ifdef CONFIG_ACPI_CPPC_LIB -#include <acpi/cppc_acpi.h> -#endif +#include <asm/sev.h> +#include <asm/spec-ctrl.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -99,17 +103,22 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); EXPORT_PER_CPU_SYMBOL(cpu_die_map); -DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); +/* Representing CPUs for which sibling maps can be computed */ +static cpumask_var_t cpu_sibling_setup_mask; -/* Per CPU bogomips and other parameters */ -DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); -EXPORT_PER_CPU_SYMBOL(cpu_info); +struct mwait_cpu_dead { + unsigned int control; + unsigned int status; +}; -/* Logical package management. We might want to allocate that dynamically */ -unsigned int __max_logical_packages __read_mostly; -EXPORT_SYMBOL(__max_logical_packages); -static unsigned int logical_packages __read_mostly; -static unsigned int logical_die __read_mostly; +#define CPUDEAD_MWAIT_WAIT 0xDEADBEEF +#define CPUDEAD_MWAIT_KEXEC_HLT 0x4A17DEAD + +/* + * Cache line aligned data for mwait_play_dead(). Separate on purpose so + * that it's unlikely to be touched by other CPUs. + */ +static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); /* Maximum number of SMT threads on any online core */ int __read_mostly __max_smt_threads = 1; @@ -125,17 +134,19 @@ int arch_update_cpu_topology(void) return retval; } +static unsigned int smpboot_warm_reset_vector_count; + static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; spin_lock_irqsave(&rtc_lock, flags); - CMOS_WRITE(0xa, 0xf); + if (!smpboot_warm_reset_vector_count++) { + CMOS_WRITE(0xa, 0xf); + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4; + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf; + } spin_unlock_irqrestore(&rtc_lock, flags); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = - start_eip >> 4; - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = - start_eip & 0xf; } static inline void smpboot_restore_warm_reset_vector(void) @@ -147,78 +158,75 @@ static inline void smpboot_restore_warm_reset_vector(void) * to default values. */ spin_lock_irqsave(&rtc_lock, flags); - CMOS_WRITE(0, 0xf); + if (!--smpboot_warm_reset_vector_count) { + CMOS_WRITE(0, 0xf); + *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; + } spin_unlock_irqrestore(&rtc_lock, flags); - *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } -static void init_freq_invariance(bool secondary, bool cppc_ready); - -/* - * Report back to the Boot Processor during boot time or to the caller processor - * during CPU online. - */ -static void smp_callin(void) +/* Run the next set of setup steps for the upcoming CPU */ +static void ap_starting(void) { - int cpuid; + int cpuid = smp_processor_id(); - /* - * If waken up by an INIT in an 82489DX configuration - * cpu_callout_mask guarantees we don't get here before - * an INIT_deassert IPI reaches our local APIC, so it is - * now safe to touch our local APIC. - */ - cpuid = smp_processor_id(); + /* Mop up eventual mwait_play_dead() wreckage */ + this_cpu_write(mwait_cpu_dead.status, 0); + this_cpu_write(mwait_cpu_dead.control, 0); /* - * 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) + * If woken up by an INIT in an 82489DX configuration the alive + * synchronization guarantees that the CPU does not reach this + * point before an INIT_deassert IPI reaches the local APIC, so it + * is now safe to touch the local APIC. + * + * Set up this CPU, first the APIC, which is probably redundant on + * most boards. */ apic_ap_setup(); - /* - * Save our processor parameters. Note: this information - * is needed for clock calibration. - */ - smp_store_cpu_info(cpuid); + /* Save the processor parameters. */ + identify_secondary_cpu(cpuid); /* * The topology information must be up to date before - * calibrate_delay() and notify_cpu_starting(). + * notify_cpu_starting(). */ - set_cpu_sibling_map(raw_smp_processor_id()); + set_cpu_sibling_map(cpuid); - init_freq_invariance(true, false); + ap_init_aperfmperf(); - /* - * Get our bogomips. - * Update loops_per_jiffy in cpu_data. Previous call to - * smp_store_cpu_info() stored a value that is close but not as - * accurate as the value just calculated. - */ - calibrate_delay(); - cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy; pr_debug("Stack at about %p\n", &cpuid); wmb(); + /* + * This runs the AP through all the cpuhp states to its target + * state CPUHP_ONLINE. + */ notify_cpu_starting(cpuid); +} +static void ap_calibrate_delay(void) +{ /* - * Allow the master to continue. + * Calibrate the delay loop and update loops_per_jiffy in cpu_data. + * identify_secondary_cpu() stored a value that is close but not as + * accurate as the value just calculated. + * + * As this is invoked after the TSC synchronization check, + * calibrate_delay_is_known() will skip the calibration routine + * when TSC is synchronized across sockets. */ - cpumask_set_cpu(cpuid, cpu_callin_mask); + calibrate_delay(); + cpu_data(smp_processor_id()).loops_per_jiffy = loops_per_jiffy; } -static int cpu0_logical_apicid; -static int enable_start_cpu0; /* * Activate a secondary processor. */ -static void notrace start_secondary(void *unused) +static void notrace __noendbr start_secondary(void *unused) { /* * Don't put *anything* except direct CPU state initialization @@ -227,25 +235,60 @@ static void notrace start_secondary(void *unused) */ cr4_init(); -#ifdef CONFIG_X86_32 - /* switch away from the initial page table */ - load_cr3(swapper_pg_dir); - __flush_tlb_all(); -#endif - cpu_init_secondary(); - rcu_cpu_starting(raw_smp_processor_id()); - x86_cpuinit.early_percpu_clock_init(); - smp_callin(); + /* + * 32-bit specific. 64-bit reaches this code with the correct page + * table established. Yet another historical divergence. + */ + if (IS_ENABLED(CONFIG_X86_32)) { + /* switch away from the initial page table */ + load_cr3(swapper_pg_dir); + __flush_tlb_all(); + } - enable_start_cpu0 = 0; + cpu_init_exception_handling(false); - /* otherwise gcc will move up smp_processor_id before the cpu_init */ - barrier(); /* - * Check TSC synchronization with the boot CPU: + * Load the microcode before reaching the AP alive synchronization + * point below so it is not part of the full per CPU serialized + * bringup part when "parallel" bringup is enabled. + * + * That's even safe when hyperthreading is enabled in the CPU as + * the core code starts the primary threads first and leaves the + * secondary threads waiting for SIPI. Loading microcode on + * physical cores concurrently is a safe operation. + * + * This covers both the Intel specific issue that concurrent + * microcode loading on SMT siblings must be prohibited and the + * vendor independent issue`that microcode loading which changes + * CPUID, MSRs etc. must be strictly serialized to maintain + * software state correctness. */ + load_ucode_ap(); + + /* + * Synchronization point with the hotplug core. Sets this CPUs + * synchronization state to ALIVE and spin-waits for the control CPU to + * release this CPU for further bringup. + */ + cpuhp_ap_sync_alive(); + + cpu_init(); + fpu__init_cpu(); + rcutree_report_cpu_starting(raw_smp_processor_id()); + x86_cpuinit.early_percpu_clock_init(); + + ap_starting(); + + /* Check TSC synchronization with the control CPU. */ check_tsc_sync_target(); + /* + * Calibrate the delay loop after the TSC synchronization check. + * This allows to skip the calibration when TSC is synchronized + * across sockets. + */ + ap_calibrate_delay(); + speculative_store_bypass_ht_init(); /* @@ -258,7 +301,6 @@ static void notrace start_secondary(void *unused) set_cpu_online(smp_processor_id(), true); lapic_online(); unlock_vector_lock(); - cpu_set_state_online(smp_processor_id()); x86_platform.nmi_init(); /* enable local interrupts */ @@ -269,141 +311,7 @@ static void notrace start_secondary(void *unused) wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } - -/** - * topology_is_primary_thread - Check whether CPU is the primary SMT thread - * @cpu: CPU to check - */ -bool topology_is_primary_thread(unsigned int cpu) -{ - return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu)); -} - -/** - * topology_smt_supported - Check whether SMT is supported by the CPUs - */ -bool topology_smt_supported(void) -{ - return smp_num_siblings > 1; -} - -/** - * topology_phys_to_logical_pkg - Map a physical package id to a logical - * - * Returns logical package id or -1 if not found - */ -int topology_phys_to_logical_pkg(unsigned int phys_pkg) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->initialized && c->phys_proc_id == phys_pkg) - return c->logical_proc_id; - } - return -1; -} -EXPORT_SYMBOL(topology_phys_to_logical_pkg); -/** - * topology_phys_to_logical_die - Map a physical die id to logical - * - * Returns logical die id or -1 if not found - */ -int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) -{ - int cpu; - int proc_id = cpu_data(cur_cpu).phys_proc_id; - - for_each_possible_cpu(cpu) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->initialized && c->cpu_die_id == die_id && - c->phys_proc_id == proc_id) - return c->logical_die_id; - } - return -1; -} -EXPORT_SYMBOL(topology_phys_to_logical_die); - -/** - * topology_update_package_map - Update the physical to logical package map - * @pkg: The physical package id as retrieved via CPUID - * @cpu: The cpu for which this is updated - */ -int topology_update_package_map(unsigned int pkg, unsigned int cpu) -{ - int new; - - /* Already available somewhere? */ - new = topology_phys_to_logical_pkg(pkg); - if (new >= 0) - goto found; - - new = logical_packages++; - if (new != pkg) { - pr_info("CPU %u Converting physical %u to logical package %u\n", - cpu, pkg, new); - } -found: - cpu_data(cpu).logical_proc_id = new; - return 0; -} -/** - * topology_update_die_map - Update the physical to logical die map - * @die: The die id as retrieved via CPUID - * @cpu: The cpu for which this is updated - */ -int topology_update_die_map(unsigned int die, unsigned int cpu) -{ - int new; - - /* Already available somewhere? */ - new = topology_phys_to_logical_die(die, cpu); - if (new >= 0) - goto found; - - new = logical_die++; - if (new != die) { - pr_info("CPU %u Converting physical %u to logical die %u\n", - cpu, die, new); - } -found: - cpu_data(cpu).logical_die_id = new; - return 0; -} - -void __init smp_store_boot_cpu_info(void) -{ - int id = 0; /* CPU 0 */ - struct cpuinfo_x86 *c = &cpu_data(id); - - *c = boot_cpu_data; - c->cpu_index = id; - topology_update_package_map(c->phys_proc_id, id); - topology_update_die_map(c->cpu_die_id, id); - c->initialized = true; -} - -/* - * The bootstrap kernel entry code has set these up. Save them for - * a given CPU - */ -void smp_store_cpu_info(int id) -{ - struct cpuinfo_x86 *c = &cpu_data(id); - - /* Copy boot_cpu_data only on the first bringup */ - if (!c->initialized) - *c = boot_cpu_data; - c->cpu_index = id; - /* - * During boot time, CPU0 has this setup already. Save the info when - * bringing up AP or offlined CPU0. - */ - identify_secondary_cpu(c); - c->initialized = true; -} +ANNOTATE_NOENDBR_SYM(start_secondary); static bool topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -435,21 +343,22 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - if (c->phys_proc_id == o->phys_proc_id && - c->cpu_die_id == o->cpu_die_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { - if (c->cpu_core_id == o->cpu_core_id) + if (c->topo.pkg_id == o->topo.pkg_id && + c->topo.die_id == o->topo.die_id && + c->topo.amd_node_id == o->topo.amd_node_id && + per_cpu_llc_id(cpu1) == per_cpu_llc_id(cpu2)) { + if (c->topo.core_id == o->topo.core_id) return topology_sane(c, o, "smt"); - if ((c->cu_id != 0xff) && - (o->cu_id != 0xff) && - (c->cu_id == o->cu_id)) + if ((c->topo.cu_id != 0xff) && + (o->topo.cu_id != 0xff) && + (c->topo.cu_id == o->topo.cu_id)) return topology_sane(c, o, "smt"); } - } else if (c->phys_proc_id == o->phys_proc_id && - c->cpu_die_id == o->cpu_die_id && - c->cpu_core_id == o->cpu_core_id) { + } else if (c->topo.pkg_id == o->topo.pkg_id && + c->topo.die_id == o->topo.die_id && + c->topo.core_id == o->topo.core_id) { return topology_sane(c, o, "smt"); } @@ -458,10 +367,28 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->phys_proc_id == o->phys_proc_id && - c->cpu_die_id == o->cpu_die_id) - return true; - return false; + if (c->topo.pkg_id != o->topo.pkg_id || c->topo.die_id != o->topo.die_id) + return false; + + if (cpu_feature_enabled(X86_FEATURE_TOPOEXT) && topology_amd_nodes_per_pkg() > 1) + return c->topo.amd_node_id == o->topo.amd_node_id; + + return true; +} + +static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + /* If the arch didn't set up l2c_id, fall back to SMT */ + if (per_cpu_l2c_id(cpu1) == BAD_APICID) + return match_smt(c, o); + + /* Do not match if L2 cache id does not match: */ + if (per_cpu_l2c_id(cpu1) != per_cpu_l2c_id(cpu2)) + return false; + + return topology_sane(c, o, "l2c"); } /* @@ -471,7 +398,7 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) */ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->phys_proc_id == o->phys_proc_id) + if (c->topo.pkg_id == o->topo.pkg_id) return true; return false; } @@ -491,9 +418,9 @@ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) */ static const struct x86_cpu_id intel_cod_cpu[] = { - X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0), /* COD */ - X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0), /* COD */ - X86_MATCH_INTEL_FAM6_MODEL(ANY, 1), /* SNC */ + X86_MATCH_VFM(INTEL_HASWELL_X, 0), /* COD */ + X86_MATCH_VFM(INTEL_BROADWELL_X, 0), /* COD */ + X86_MATCH_VFM(INTEL_ANY, 1), /* SNC */ {} }; @@ -504,11 +431,11 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) bool intel_snc = id && id->driver_data; /* Do not match if we do not have a valid APICID for cpu: */ - if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID) + if (per_cpu_llc_id(cpu1) == BAD_APICID) return false; /* Do not match if LLC id does not match: */ - if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2)) + if (per_cpu_llc_id(cpu1) != per_cpu_llc_id(cpu2)) return false; /* @@ -523,7 +450,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) } -#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC) static inline int x86_sched_itmt_flags(void) { return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0; @@ -535,46 +461,131 @@ static int x86_core_flags(void) return cpu_core_flags() | x86_sched_itmt_flags(); } #endif -#ifdef CONFIG_SCHED_SMT -static int x86_smt_flags(void) +#ifdef CONFIG_SCHED_CLUSTER +static int x86_cluster_flags(void) { - return cpu_smt_flags() | x86_sched_itmt_flags(); + return cpu_cluster_flags() | x86_sched_itmt_flags(); } #endif -#endif -static struct sched_domain_topology_level x86_numa_in_package_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, -#endif -#ifdef CONFIG_SCHED_MC - { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, -#endif - { NULL, }, -}; +/* + * Set if a package/die has multiple NUMA nodes inside. + * AMD Magny-Cours, Intel Cluster-on-Die, and Intel + * Sub-NUMA Clustering have this. + */ +static bool x86_has_numa_in_package; static struct sched_domain_topology_level x86_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, + SDTL_INIT(tl_smt_mask, cpu_smt_flags, SMT), +#ifdef CONFIG_SCHED_CLUSTER + SDTL_INIT(tl_cls_mask, x86_cluster_flags, CLS), #endif #ifdef CONFIG_SCHED_MC - { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, + SDTL_INIT(tl_mc_mask, x86_core_flags, MC), #endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, + SDTL_INIT(tl_pkg_mask, x86_sched_itmt_flags, PKG), + { NULL }, }; -/* - * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours, Intel Cluster-on-Die, and Intel - * Sub-NUMA Clustering have this. - */ -static bool x86_has_numa_in_package; +static void __init build_sched_topology(void) +{ + struct sched_domain_topology_level *topology = x86_topology; + + /* + * When there is NUMA topology inside the package invalidate the + * PKG domain since the NUMA domains will auto-magically create the + * right spanning domains based on the SLIT. + */ + if (x86_has_numa_in_package) { + unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2; + + memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom])); + } + + /* + * Drop the SMT domains if there is only one thread per-core + * since it'll get degenerated by the scheduler anyways. + */ + if (cpu_smt_num_threads <= 1) + ++topology; + + set_sched_topology(topology); +} + +#ifdef CONFIG_NUMA +static int sched_avg_remote_distance; +static int avg_remote_numa_distance(void) +{ + int i, j; + int distance, nr_remote, total_distance; + + if (sched_avg_remote_distance > 0) + return sched_avg_remote_distance; + + nr_remote = 0; + total_distance = 0; + for_each_node_state(i, N_CPU) { + for_each_node_state(j, N_CPU) { + distance = node_distance(i, j); + + if (distance >= REMOTE_DISTANCE) { + nr_remote++; + total_distance += distance; + } + } + } + if (nr_remote) + sched_avg_remote_distance = total_distance / nr_remote; + else + sched_avg_remote_distance = REMOTE_DISTANCE; + + return sched_avg_remote_distance; +} + +int arch_sched_node_distance(int from, int to) +{ + int d = node_distance(from, to); + + switch (boot_cpu_data.x86_vfm) { + case INTEL_GRANITERAPIDS_X: + case INTEL_ATOM_DARKMONT_X: + + if (!x86_has_numa_in_package || topology_max_packages() == 1 || + d < REMOTE_DISTANCE) + return d; + + /* + * With SNC enabled, there could be too many levels of remote + * NUMA node distances, creating NUMA domain levels + * including local nodes and partial remote nodes. + * + * Trim finer distance tuning for NUMA nodes in remote package + * for the purpose of building sched domains. Group NUMA nodes + * in the remote package in the same sched group. + * Simplify NUMA domains and avoid extra NUMA levels including + * different remote NUMA nodes and local nodes. + * + * GNR and CWF don't expect systems with more than 2 packages + * and more than 2 hops between packages. Single average remote + * distance won't be appropriate if there are more than 2 + * packages as average distance to different remote packages + * could be different. + */ + WARN_ONCE(topology_max_packages() > 2, + "sched: Expect only up to 2 packages for GNR or CWF, " + "but saw %d packages when building sched domains.", + topology_max_packages()); + + d = avg_remote_numa_distance(); + } + return d; +} +#endif /* CONFIG_NUMA */ void set_cpu_sibling_map(int cpu) { - bool has_smt = smp_num_siblings > 1; - bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; + bool has_smt = __max_threads_per_core > 1; + bool has_mp = has_smt || topology_num_cores_per_package() > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i, threads; @@ -584,6 +595,7 @@ void set_cpu_sibling_map(int cpu) if (!has_mp) { cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); + cpumask_set_cpu(cpu, cpu_l2c_shared_mask(cpu)); cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); cpumask_set_cpu(cpu, topology_die_cpumask(cpu)); c->booted_cores = 1; @@ -602,6 +614,9 @@ void set_cpu_sibling_map(int cpu) if ((i == cpu) || (has_mp && match_llc(c, o))) link_mask(cpu_llc_shared_mask, cpu, i); + if ((i == cpu) || (has_mp && match_l2c(c, o))) + link_mask(cpu_l2c_shared_mask, cpu, i); + if ((i == cpu) || (has_mp && match_die(c, o))) link_mask(topology_die_cpumask, cpu, i); } @@ -610,6 +625,9 @@ void set_cpu_sibling_map(int cpu) if (threads > __max_smt_threads) __max_smt_threads = threads; + for_each_cpu(i, topology_sibling_cpumask(cpu)) + cpu_data(i).smt_active = threads > 1; + /* * This needs a separate iteration over the cpus because we rely on all * topology_sibling_cpumask links to be set-up. @@ -649,6 +667,12 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return cpu_llc_shared_mask(cpu); } +const struct cpumask *cpu_clustergroup_mask(int cpu) +{ + return cpu_l2c_shared_mask(cpu); +} +EXPORT_SYMBOL_GPL(cpu_clustergroup_mask); + static void impress_friends(void) { int cpu; @@ -657,9 +681,9 @@ static void impress_friends(void) * Allow the user to impress friends. */ pr_debug("Before bogomips\n"); - for_each_possible_cpu(cpu) - if (cpumask_test_cpu(cpu, cpu_callout_mask)) - bogosum += cpu_data(cpu).loops_per_jiffy; + for_each_online_cpu(cpu) + bogosum += cpu_data(cpu).loops_per_jiffy; + pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n", num_online_cpus(), bogosum/(500000/HZ), @@ -668,44 +692,6 @@ static void impress_friends(void) pr_debug("Before bogocount - setting activated=1\n"); } -void __inquire_remote_apic(int apicid) -{ - unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; - const char * const names[] = { "ID", "VERSION", "SPIV" }; - int timeout; - u32 status; - - pr_info("Inquiring remote APIC 0x%x...\n", apicid); - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - pr_info("... APIC 0x%x %s: ", apicid, names[i]); - - /* - * Wait for idle. - */ - status = safe_apic_wait_icr_idle(); - if (status) - pr_cont("a previous APIC delivery may have failed\n"); - - apic_icr_write(APIC_DM_REMRD | regs[i], apicid); - - 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); - pr_cont("%08x\n", status); - break; - default: - pr_cont("failed\n"); - } - } -} - /* * The Multiprocessor Specification 1.4 (1997) example code suggests * that there should be a 10ms delay between the BSP asserting INIT @@ -713,10 +699,9 @@ void __inquire_remote_apic(int apicid) * But that slows boot and resume on modern processors, which include * many cores and don't require that delay. * - * Cmdline "init_cpu_udelay=" is available to over-ride this delay. - * Modern processor families are quirked to remove the delay entirely. + * Cmdline "cpu_init_udelay=" is available to override this delay. */ -#define UDELAY_10MS_DEFAULT 10000 +#define UDELAY_10MS_LEGACY 10000 static unsigned int init_udelay = UINT_MAX; @@ -728,104 +713,60 @@ static int __init cpu_init_udelay(char *str) } early_param("cpu_init_udelay", cpu_init_udelay); -static void __init smp_quirk_init_udelay(void) +static void __init smp_set_init_udelay(void) { /* if cmdline changed it from default, leave it alone */ if (init_udelay != UINT_MAX) return; /* if modern processor, use no delay */ - if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || - ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) || - ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) { + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO) || + (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON && boot_cpu_data.x86 >= 0x18) || + (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86 >= 0xF)) { init_udelay = 0; return; } /* else, use legacy delay */ - init_udelay = UDELAY_10MS_DEFAULT; + init_udelay = UDELAY_10MS_LEGACY; } /* - * 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. + * Wake up AP by INIT, INIT, STARTUP sequence. */ -int -wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) +static void send_init_sequence(u32 phys_apicid) { - u32 dm = apic->dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; - unsigned long send_status, accept_status = 0; - int maxlvt; - - /* Target chip */ - /* Boot on the stack */ - /* Kick the second */ - apic_icr_write(APIC_DM_NMI | dm, apicid); - - pr_debug("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); + int maxlvt = lapic_get_maxlvt(); - /* - * Give the other CPU some time to accept the IPI. - */ - udelay(200); + /* Be paranoid about clearing APIC errors. */ if (APIC_INTEGRATED(boot_cpu_apic_version)) { - maxlvt = lapic_get_maxlvt(); - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ + /* Due to the Pentium erratum 3AP. */ + if (maxlvt > 3) apic_write(APIC_ESR, 0); - accept_status = (apic_read(APIC_ESR) & 0xEF); + apic_read(APIC_ESR); } - pr_debug("NMI sent\n"); - if (send_status) - pr_err("APIC never delivered???\n"); - if (accept_status) - pr_err("APIC delivery error (%lx)\n", accept_status); + /* Assert INIT on the target CPU */ + apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT, phys_apicid); + safe_apic_wait_icr_idle(); - return (send_status | accept_status); + udelay(init_udelay); + + /* Deassert INIT on the target CPU */ + apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid); + safe_apic_wait_icr_idle(); } -static int -wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) +/* + * Wake up AP by INIT, INIT, STARTUP sequence. + */ +static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip, unsigned int cpu) { unsigned long send_status = 0, accept_status = 0; - int maxlvt, num_starts, j; + int num_starts, j, maxlvt; + preempt_disable(); maxlvt = lapic_get_maxlvt(); - - /* - * Be paranoid about clearing APIC errors. - */ - if (APIC_INTEGRATED(boot_cpu_apic_version)) { - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - apic_read(APIC_ESR); - } - - pr_debug("Asserting INIT\n"); - - /* - * Turn INIT on target chip - */ - /* - * Send IPI - */ - apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT, - phys_apicid); - - pr_debug("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); - - udelay(init_udelay); - - pr_debug("Deasserting INIT\n"); - - /* Target chip */ - /* Send IPI */ - apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid); - - pr_debug("Waiting for send to finish...\n"); - send_status = safe_apic_wait_icr_idle(); + send_init_sequence(phys_apicid); mb(); @@ -896,15 +837,16 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) if (accept_status) pr_err("APIC delivery error (%lx)\n", accept_status); + preempt_enable(); return (send_status | accept_status); } /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { + static int width, node_width, first = 1; static int current_node = NUMA_NO_NODE; int node = early_cpu_to_node(cpu); - static int width, node_width; if (!width) width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */ @@ -912,10 +854,10 @@ static void announce_cpu(int cpu, int apicid) if (!node_width) node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */ - if (cpu == 1) - printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state < SYSTEM_RUNNING) { + if (first) + pr_info("x86: Booting SMP configuration:\n"); + if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); @@ -926,77 +868,16 @@ static void announce_cpu(int cpu, int apicid) } /* Add padding for the BSP */ - if (cpu == 1) + if (first) pr_cont("%*s", width + 1, " "); + first = 0; pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu); - } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", node, cpu, apicid); } -static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs) -{ - int cpu; - - cpu = smp_processor_id(); - if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0) - return NMI_HANDLED; - - return NMI_DONE; -} - -/* - * Wake up AP by INIT, INIT, STARTUP sequence. - * - * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS - * boot-strap code which is not a desired behavior for waking up BSP. To - * void the boot-strap code, wake up CPU0 by NMI instead. - * - * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined - * (i.e. physically hot removed and then hot added), NMI won't wake it up. - * We'll change this code in the future to wake up hard offlined CPU0 if - * real platform and request are available. - */ -static int -wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, - int *cpu0_nmi_registered) -{ - int id; - int boot_error; - - preempt_disable(); - - /* - * Wake up AP by INIT, INIT, STARTUP sequence. - */ - if (cpu) { - boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip); - goto out; - } - - /* - * Wake up BSP by nmi. - * - * Register a NMI handler to help wake up CPU0. - */ - boot_error = register_nmi_handler(NMI_LOCAL, - wakeup_cpu0_nmi, 0, "wake_cpu0"); - - if (!boot_error) { - enable_start_cpu0 = 1; - *cpu0_nmi_registered = 1; - id = apic->dest_mode_logical ? cpu0_logical_apicid : apicid; - boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip); - } - -out: - preempt_enable(); - - return boot_error; -} - int common_cpu_up(unsigned int cpu, struct task_struct *idle) { int ret; @@ -1015,8 +896,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) #ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle); -#else - initial_gs = per_cpu_offset(cpu); #endif return 0; } @@ -1024,22 +903,28 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) /* * 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 + * Returns zero if startup was successfully sent, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, - int *cpu0_nmi_registered) +static int do_boot_cpu(u32 apicid, unsigned int cpu, struct task_struct *idle) { - /* start_ip had better be page-aligned! */ unsigned long start_ip = real_mode_header->trampoline_start; + int ret; - unsigned long boot_error = 0; - unsigned long timeout; - +#ifdef CONFIG_X86_64 + /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */ + if (apic->wakeup_secondary_cpu_64) + start_ip = real_mode_header->trampoline_start64; +#endif idle->thread.sp = (unsigned long)task_pt_regs(idle); - early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; - initial_stack = idle->thread.sp; + + if (IS_ENABLED(CONFIG_X86_32)) { + early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); + initial_stack = idle->thread.sp; + } else if (!(smpboot_control & STARTUP_PARALLEL_MASK)) { + smpboot_control = cpu; + } /* Enable the espfix hack for this CPU */ init_espfix_ap(cpu); @@ -1051,7 +936,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, * This grunge runs the startup process for * the targeted processor. */ - if (x86_platform.legacy.warm_reset) { pr_debug("Setting warm reset code and vector.\n"); @@ -1066,95 +950,45 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, } } - /* - * AP might wait on cpu_callout_mask in cpu_init() with - * cpu_initialized_mask set if previous attempt to online - * it timed-out. Clear cpu_initialized_mask so that after - * INIT/SIPI it could start with a clean state. - */ - cpumask_clear_cpu(cpu, cpu_initialized_mask); smp_mb(); /* * Wake up a CPU in difference cases: - * - Use the method in the APIC driver if it's defined + * - Use a method from the APIC driver if one defined, with wakeup + * straight to 64-bit mode preferred over wakeup to RM. * Otherwise, - * - Use an INIT boot APIC message for APs or NMI for BSP. + * - Use an INIT boot APIC message */ - if (apic->wakeup_secondary_cpu) - boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); + if (apic->wakeup_secondary_cpu_64) + ret = apic->wakeup_secondary_cpu_64(apicid, start_ip, cpu); + else if (apic->wakeup_secondary_cpu) + ret = apic->wakeup_secondary_cpu(apicid, start_ip, cpu); else - boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, - cpu0_nmi_registered); - - if (!boot_error) { - /* - * Wait 10s total for first sign of life from AP - */ - boot_error = -1; - timeout = jiffies + 10*HZ; - while (time_before(jiffies, timeout)) { - if (cpumask_test_cpu(cpu, cpu_initialized_mask)) { - /* - * Tell AP to proceed with initialization - */ - cpumask_set_cpu(cpu, cpu_callout_mask); - boot_error = 0; - break; - } - schedule(); - } - } - - if (!boot_error) { - /* - * Wait till AP completes initial initialization - */ - while (!cpumask_test_cpu(cpu, cpu_callin_mask)) { - /* - * Allow other tasks to run while we wait for the - * AP to come online. This also gives a chance - * for the MTRR work(triggered by the AP coming online) - * to be completed in the stop machine context. - */ - schedule(); - } - } + ret = wakeup_secondary_cpu_via_init(apicid, start_ip, cpu); - if (x86_platform.legacy.warm_reset) { - /* - * Cleanup possible dangling ends... - */ - smpboot_restore_warm_reset_vector(); - } - - return boot_error; + /* If the wakeup mechanism failed, cleanup the warm reset vector */ + if (ret) + arch_cpuhp_cleanup_kick_cpu(cpu); + return ret; } -int native_cpu_up(unsigned int cpu, struct task_struct *tidle) +int native_kick_ap(unsigned int cpu, struct task_struct *tidle) { - int apicid = apic->cpu_present_to_apicid(cpu); - int cpu0_nmi_registered = 0; - unsigned long flags; - int err, ret = 0; + u32 apicid = apic->cpu_present_to_apicid(cpu); + int err; lockdep_assert_irqs_enabled(); pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); - if (apicid == BAD_APICID || - !physid_isset(apicid, phys_cpu_present_map) || - !apic->apic_id_valid(apicid)) { - pr_err("%s: bad cpu %d\n", __func__, cpu); + if (apicid == BAD_APICID || !apic_id_valid(apicid)) { + pr_err("CPU %u has invalid APIC ID %x. Aborting bringup\n", cpu, apicid); return -EINVAL; } - /* - * Already booted CPU? - */ - if (cpumask_test_cpu(cpu, cpu_callin_mask)) { - pr_debug("do_boot_cpu %d Already started\n", cpu); - return -ENOSYS; + if (!test_bit(apicid, phys_cpu_present_map)) { + pr_err("CPU %u APIC ID %x is not present. Aborting bringup\n", cpu, apicid); + return -EINVAL; } /* @@ -1163,11 +997,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) */ mtrr_save_state(); - /* x86 CPUs take themselves offline, so delayed offline is OK. */ - err = cpu_check_up_prepare(cpu); - if (err && err != -EBUSY) - return err; - /* the FPU context is blank, nobody can own it */ per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; @@ -1175,41 +1004,44 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) if (err) return err; - err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered); - if (err) { + err = do_boot_cpu(apicid, cpu, tidle); + if (err) pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); - ret = -EIO; - goto unreg_nmi; - } - /* - * 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); + return err; +} - while (!cpu_online(cpu)) { - cpu_relax(); - touch_nmi_watchdog(); - } +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle) +{ + return smp_ops.kick_ap_alive(cpu, tidle); +} -unreg_nmi: - /* - * Clean up the nmi handler. Do this after the callin and callout sync - * to avoid impact of possible long unregister time. - */ - if (cpu0_nmi_registered) - unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); +void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) +{ + /* Cleanup possible dangling ends... */ + if (smp_ops.kick_ap_alive == native_kick_ap && x86_platform.legacy.warm_reset) + smpboot_restore_warm_reset_vector(); +} - return ret; +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) +{ + if (smp_ops.cleanup_dead_cpu) + smp_ops.cleanup_dead_cpu(cpu); + + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); +} + +void arch_cpuhp_sync_state_poll(void) +{ + if (smp_ops.poll_sync_state) + smp_ops.poll_sync_state(); } /** - * arch_disable_smp_support() - disables SMP support for x86 at runtime + * arch_disable_smp_support() - Disables SMP support for x86 at boottime */ -void arch_disable_smp_support(void) +void __init arch_disable_smp_support(void) { disable_ioapic_support(); } @@ -1224,90 +1056,55 @@ static __init void disable_smp(void) pr_info("SMP disabled\n"); disable_ioapic_support(); + topology_reset_possible_cpus_up(); - init_cpu_present(cpumask_of(0)); - init_cpu_possible(cpumask_of(0)); - - if (smp_found_config) - physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); - else - physid_set_mask_of_physid(0, &phys_cpu_present_map); cpumask_set_cpu(0, topology_sibling_cpumask(0)); cpumask_set_cpu(0, topology_core_cpumask(0)); cpumask_set_cpu(0, topology_die_cpumask(0)); } -/* - * Various sanity checks. - */ -static void __init smp_sanity_check(void) +void __init smp_prepare_cpus_common(void) { - preempt_disable(); - -#if !defined(CONFIG_X86_BIGSMP) && defined(CONFIG_X86_32) - if (def_to_bigsmp && nr_cpu_ids > 8) { - unsigned int cpu; - unsigned nr; + unsigned int cpu, node; - pr_warn("More than 8 CPUs detected - skipping them\n" - "Use CONFIG_X86_BIGSMP\n"); - - nr = 0; - for_each_present_cpu(cpu) { - if (nr >= 8) - set_cpu_present(cpu, false); - nr++; - } - - nr = 0; - for_each_possible_cpu(cpu) { - if (nr >= 8) - set_cpu_possible(cpu, false); - nr++; - } - - nr_cpu_ids = 8; + /* Mark all except the boot CPU as hotpluggable */ + for_each_possible_cpu(cpu) { + if (cpu) + per_cpu(cpu_info.cpu_index, cpu) = nr_cpu_ids; } -#endif - if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) { - pr_warn("weird, boot CPU (#%d) not listed by the BIOS\n", - hard_smp_processor_id()); + for_each_possible_cpu(cpu) { + node = cpu_to_node(cpu); - physid_set(hard_smp_processor_id(), phys_cpu_present_map); + zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu), GFP_KERNEL, node); + zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, node); + zalloc_cpumask_var_node(&per_cpu(cpu_die_map, cpu), GFP_KERNEL, node); + zalloc_cpumask_var_node(&per_cpu(cpu_llc_shared_map, cpu), GFP_KERNEL, node); + zalloc_cpumask_var_node(&per_cpu(cpu_l2c_shared_map, cpu), GFP_KERNEL, node); } - /* - * Should not be necessary because the MP table should list the boot - * CPU too, but we do it for the sake of robustness anyway. - */ - if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) { - pr_notice("weird, boot CPU (#%d) not listed by the BIOS\n", - boot_cpu_physical_apicid); - physid_set(hard_smp_processor_id(), phys_cpu_present_map); - } - preempt_enable(); + set_cpu_sibling_map(0); } -static void __init smp_cpu_index_default(void) +void __init smp_prepare_boot_cpu(void) { - int i; - struct cpuinfo_x86 *c; - - for_each_possible_cpu(i) { - c = &cpu_data(i); - /* mark all to hotplug */ - c->cpu_index = nr_cpu_ids; - } + smp_ops.smp_prepare_boot_cpu(); } -static void __init smp_get_logical_apicid(void) +#ifdef CONFIG_X86_64 +/* Establish whether parallel bringup can be supported. */ +bool __init arch_cpuhp_init_parallel_bringup(void) { - if (x2apic_mode) - cpu0_logical_apicid = apic_read(APIC_LDR); - else - cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (!x86_cpuinit.parallel_bringup) { + pr_info("Parallel CPU startup disabled by the platform\n"); + return false; + } + + smpboot_control = STARTUP_READ_APICID; + pr_debug("Parallel CPU startup enabled: 0x%08x\n", smpboot_control); + return true; } +#endif /* * Prepare for SMP bootup. @@ -1316,36 +1113,7 @@ static void __init smp_get_logical_apicid(void) */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { - unsigned int i; - - smp_cpu_index_default(); - - /* - * Setup boot CPU information - */ - smp_store_boot_cpu_info(); /* Final full version of the data */ - cpumask_copy(cpu_callin_mask, cpumask_of(0)); - mb(); - - for_each_possible_cpu(i) { - zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL); - zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); - } - - /* - * Set 'default' x86 topology, this matches default_topology() in that - * it has NUMA nodes as a topology level. See also - * native_smp_cpus_done(). - * - * Must be done before set_cpus_sibling_map() is ran. - */ - set_sched_topology(x86_topology); - - set_cpu_sibling_map(0); - init_freq_invariance(false, false); - smp_sanity_check(); + smp_prepare_cpus_common(); switch (apic_intr_mode) { case APIC_PIC: @@ -1365,28 +1133,26 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) /* Setup local timer */ x86_init.timers.setup_percpu_clockev(); - smp_get_logical_apicid(); - pr_info("CPU0: "); print_cpu_info(&cpu_data(0)); uv_system_init(); - set_mtrr_aps_delayed_init(); - - smp_quirk_init_udelay(); + smp_set_init_udelay(); speculative_store_bypass_ht_init(); + + snp_set_wakeup_secondary_cpu(); } void arch_thaw_secondary_cpus_begin(void) { - set_mtrr_aps_delayed_init(); + set_cache_aps_delayed_init(true); } void arch_thaw_secondary_cpus_end(void) { - mtrr_aps_init(); + cache_aps_init(); } /* @@ -1395,128 +1161,28 @@ void arch_thaw_secondary_cpus_end(void) void __init native_smp_prepare_boot_cpu(void) { int me = smp_processor_id(); - switch_to_new_gdt(me); - /* already set me in cpu_online_mask in boot_cpu_init() */ - cpumask_set_cpu(me, cpu_callout_mask); - cpu_set_state_online(me); - native_pv_lock_init(); -} -void __init calculate_max_logical_packages(void) -{ - int ncpus; + /* SMP handles this from setup_per_cpu_areas() */ + if (!IS_ENABLED(CONFIG_SMP)) + switch_gdt_and_percpu_base(me); - /* - * Today neither Intel nor AMD support heterogeneous systems so - * extrapolate the boot cpu's data to all packages. - */ - ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); - __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); - pr_info("Max logical packages: %u\n", __max_logical_packages); + native_pv_lock_init(); } void __init native_smp_cpus_done(unsigned int max_cpus) { pr_debug("Boot done\n"); - calculate_max_logical_packages(); - - if (x86_has_numa_in_package) - set_sched_topology(x86_numa_in_package_topology); - + build_sched_topology(); nmi_selftest(); impress_friends(); - mtrr_aps_init(); + cache_aps_init(); } -static int __initdata setup_possible_cpus = -1; -static int __init _setup_possible_cpus(char *str) -{ - get_option(&str, &setup_possible_cpus); - return 0; -} -early_param("possible_cpus", _setup_possible_cpus); - - -/* - * cpu_possible_mask should be static, it cannot change as cpu's - * are onlined, or offlined. The reason is per-cpu data-structures - * are allocated by some modules at init time, and don't expect to - * do this dynamically on cpu arrival/departure. - * cpu_present_mask on the other hand can change dynamically. - * In case when cpu_hotplug is not compiled, then we resort to current - * behaviour, which is cpu_possible == cpu_present. - * - Ashok Raj - * - * Three ways to find out the number of additional hotplug CPUs: - * - If the BIOS specified disabled CPUs in ACPI/mptables use that. - * - The user can overwrite it with possible_cpus=NUM - * - Otherwise don't reserve additional CPUs. - * We do this because additional CPUs waste a lot of memory. - * -AK - */ -__init void prefill_possible_map(void) +/* correctly size the local cpu masks */ +void __init setup_cpu_local_masks(void) { - int i, possible; - - /* No boot processor was found in mptable or ACPI MADT */ - if (!num_processors) { - if (boot_cpu_has(X86_FEATURE_APIC)) { - int apicid = boot_cpu_physical_apicid; - int cpu = hard_smp_processor_id(); - - pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu); - - /* Make sure boot cpu is enumerated */ - if (apic->cpu_present_to_apicid(0) == BAD_APICID && - apic->apic_id_valid(apicid)) - generic_processor_info(apicid, boot_cpu_apic_version); - } - - if (!num_processors) - num_processors = 1; - } - - i = setup_max_cpus ?: 1; - if (setup_possible_cpus == -1) { - possible = num_processors; -#ifdef CONFIG_HOTPLUG_CPU - if (setup_max_cpus) - possible += disabled_cpus; -#else - if (possible > i) - possible = i; -#endif - } else - possible = setup_possible_cpus; - - total_cpus = max_t(int, possible, num_processors + disabled_cpus); - - /* nr_cpu_ids could be reduced via nr_cpus= */ - if (possible > nr_cpu_ids) { - pr_warn("%d Processors exceeds NR_CPUS limit of %u\n", - possible, nr_cpu_ids); - possible = nr_cpu_ids; - } - -#ifdef CONFIG_HOTPLUG_CPU - if (!setup_max_cpus) -#endif - if (possible > i) { - pr_warn("%d Processors exceeds max_cpus limit of %u\n", - possible, setup_max_cpus); - possible = i; - } - - nr_cpu_ids = possible; - - pr_info("Allowing %d CPUs, %d hotplug CPUs\n", - possible, max_t(int, possible - num_processors, 0)); - - reset_cpu_possible_mask(); - - for (i = 0; i < possible; i++) - set_cpu_possible(i, true); + alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); } #ifdef CONFIG_HOTPLUG_CPU @@ -1552,15 +1218,23 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, topology_die_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_die_cpumask(sibling)); - for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) { cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + if (cpumask_weight(topology_sibling_cpumask(sibling)) == 1) + cpu_data(sibling).smt_active = false; + } + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + for_each_cpu(sibling, cpu_l2c_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_l2c_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); + cpumask_clear(cpu_l2c_shared_mask(cpu)); cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); cpumask_clear(topology_die_cpumask(cpu)); - c->cpu_core_id = 0; + c->topo.core_id = 0; c->booted_cores = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); @@ -1569,10 +1243,6 @@ static void remove_siblinginfo(int cpu) static void remove_cpu_from_maps(int cpu) { set_cpu_online(cpu, false); - cpumask_clear_cpu(cpu, cpu_callout_mask); - cpumask_clear_cpu(cpu, cpu_callin_mask); - /* was set by cpu_init() */ - cpumask_clear_cpu(cpu, cpu_initialized_mask); numa_remove_cpu(cpu); } @@ -1582,6 +1252,12 @@ void cpu_disable_common(void) remove_siblinginfo(cpu); + /* + * Stop allowing kernel-mode FPU. This is needed so that if the CPU is + * brought online again, the initial state is not allowed: + */ + this_cpu_write(kernel_fpu_allowed, false); + /* It's now safe to remove this processor from the online map */ lock_vector_lock(); remove_cpu_from_maps(cpu); @@ -1623,104 +1299,26 @@ int native_cpu_disable(void) return 0; } -int common_cpu_die(unsigned int cpu) -{ - int ret = 0; - - /* We don't do anything here: idle task is faking death itself. */ - - /* They ack this in play_dead() by setting CPU_DEAD */ - if (cpu_wait_death(cpu, 5)) { - if (system_state == SYSTEM_RUNNING) - pr_info("CPU %u is now offline\n", cpu); - } else { - pr_err("CPU %u didn't die...\n", cpu); - ret = -1; - } - - return ret; -} - -void native_cpu_die(unsigned int cpu) -{ - common_cpu_die(cpu); -} - void play_dead_common(void) { idle_task_exit(); - /* Ack it */ - (void)cpu_report_death(); + cpuhp_ap_report_dead(); - /* - * With physical CPU hotplug, we should halt the cpu - */ local_irq_disable(); } -/** - * cond_wakeup_cpu0 - Wake up CPU0 if needed. - * - * If NMI wants to wake up CPU0, start CPU0. - */ -void cond_wakeup_cpu0(void) -{ - if (smp_processor_id() == 0 && enable_start_cpu0) - start_cpu0(); -} -EXPORT_SYMBOL_GPL(cond_wakeup_cpu0); - /* * We need to flush the caches before going to sleep, lest we have * dirty data in our caches when we come back up. */ -static inline void mwait_play_dead(void) +void __noreturn mwait_play_dead(unsigned int eax_hint) { - unsigned int eax, ebx, ecx, edx; - unsigned int highest_cstate = 0; - unsigned int highest_subcstate = 0; - void *mwait_ptr; - int i; - - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - return; - if (!this_cpu_has(X86_FEATURE_MWAIT)) - return; - if (!this_cpu_has(X86_FEATURE_CLFLUSH)) - return; - if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF) - return; - - eax = CPUID_MWAIT_LEAF; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - - /* - * eax will be 0 if EDX enumeration is not valid. - * Initialized below to cstate, sub_cstate value when EDX is valid. - */ - if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) { - eax = 0; - } else { - edx >>= MWAIT_SUBSTATE_SIZE; - for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) { - if (edx & MWAIT_SUBSTATE_MASK) { - highest_cstate = i; - highest_subcstate = edx & MWAIT_SUBSTATE_MASK; - } - } - eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) | - (highest_subcstate - 1); - } + struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead); - /* - * This should be a memory location in a cache line which is - * unlikely to be touched by other processors. The actual - * content is immaterial as it is not actually modified in any way. - */ - mwait_ptr = ¤t_thread_info()->flags; + /* Set up state for the kexec() hack below */ + md->status = CPUDEAD_MWAIT_WAIT; + md->control = CPUDEAD_MWAIT_WAIT; wbinvd(); @@ -1733,469 +1331,92 @@ static inline void mwait_play_dead(void) * case where we return around the loop. */ mb(); - clflush(mwait_ptr); + clflush(md); mb(); - __monitor(mwait_ptr, 0, 0); + __monitor(md, 0, 0); mb(); - __mwait(eax, 0); - - cond_wakeup_cpu0(); - } -} - -void hlt_play_dead(void) -{ - if (__this_cpu_read(cpu_info.x86) >= 4) - wbinvd(); + __mwait(eax_hint, 0); - while (1) { - native_halt(); - - cond_wakeup_cpu0(); + if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) { + /* + * Kexec is about to happen. Don't go back into mwait() as + * the kexec kernel might overwrite text and data including + * page tables and stack. So mwait() would resume when the + * monitor cache line is written to and then the CPU goes + * south due to overwritten text, page tables and stack. + * + * Note: This does _NOT_ protect against a stray MCE, NMI, + * SMI. They will resume execution at the instruction + * following the HLT instruction and run into the problem + * which this is trying to prevent. + */ + WRITE_ONCE(md->status, CPUDEAD_MWAIT_KEXEC_HLT); + while(1) + native_halt(); + } } } -void native_play_dead(void) -{ - play_dead_common(); - tboot_shutdown(TB_SHUTDOWN_WFS); - - mwait_play_dead(); /* Only returns on failure */ - if (cpuidle_play_dead()) - hlt_play_dead(); -} - -#else /* ... !CONFIG_HOTPLUG_CPU */ -int native_cpu_disable(void) -{ - return -ENOSYS; -} - -void native_cpu_die(unsigned int cpu) -{ - /* We said "no" in __cpu_disable */ - BUG(); -} - -void native_play_dead(void) -{ - BUG(); -} - -#endif - -#ifdef CONFIG_X86_64 /* - * APERF/MPERF frequency ratio computation. - * - * The scheduler wants to do frequency invariant accounting and needs a <1 - * ratio to account for the 'current' frequency, corresponding to - * freq_curr / freq_max. - * - * Since the frequency freq_curr on x86 is controlled by micro-controller and - * our P-state setting is little more than a request/hint, we need to observe - * the effective frequency 'BusyMHz', i.e. the average frequency over a time - * interval after discarding idle time. This is given by: - * - * BusyMHz = delta_APERF / delta_MPERF * freq_base - * - * where freq_base is the max non-turbo P-state. - * - * The freq_max term has to be set to a somewhat arbitrary value, because we - * can't know which turbo states will be available at a given point in time: - * it all depends on the thermal headroom of the entire package. We set it to - * the turbo level with 4 cores active. - * - * Benchmarks show that's a good compromise between the 1C turbo ratio - * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, - * which would ignore the entire turbo range (a conspicuous part, making - * freq_curr/freq_max always maxed out). - * - * An exception to the heuristic above is the Atom uarch, where we choose the - * highest turbo level for freq_max since Atom's are generally oriented towards - * power efficiency. - * - * Setting freq_max to anything less than the 1C turbo ratio makes the ratio - * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. + * Kick all "offline" CPUs out of mwait on kexec(). See comment in + * mwait_play_dead(). */ - -DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); - -static DEFINE_PER_CPU(u64, arch_prev_aperf); -static DEFINE_PER_CPU(u64, arch_prev_mperf); -static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; -static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; - -void arch_set_max_freq_ratio(bool turbo_disabled) +void smp_kick_mwait_play_dead(void) { - arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : - arch_turbo_freq_ratio; -} -EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); + u32 newstate = CPUDEAD_MWAIT_KEXEC_HLT; + struct mwait_cpu_dead *md; + unsigned int cpu, i; -static bool turbo_disabled(void) -{ - u64 misc_en; - int err; - - err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en); - if (err) - return false; - - return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); -} + for_each_cpu_andnot(cpu, cpu_present_mask, cpu_online_mask) { + md = per_cpu_ptr(&mwait_cpu_dead, cpu); -static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) -{ - int err; - - err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq); - if (err) - return false; + /* Does it sit in mwait_play_dead() ? */ + if (READ_ONCE(md->status) != CPUDEAD_MWAIT_WAIT) + continue; - err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ - *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ - - return true; -} - -#define X86_MATCH(model) \ - X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ - INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) - -static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = { - X86_MATCH(XEON_PHI_KNL), - X86_MATCH(XEON_PHI_KNM), - {} -}; - -static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = { - X86_MATCH(SKYLAKE_X), - {} -}; - -static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = { - X86_MATCH(ATOM_GOLDMONT), - X86_MATCH(ATOM_GOLDMONT_D), - X86_MATCH(ATOM_GOLDMONT_PLUS), - {} -}; - -static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, - int num_delta_fratio) -{ - int fratio, delta_fratio, found; - int err, i; - u64 msr; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); - if (err) - return false; - - fratio = (msr >> 8) & 0xFF; - i = 16; - found = 0; - do { - if (found >= num_delta_fratio) { - *turbo_freq = fratio; - return true; + /* Wait up to 5ms */ + for (i = 0; READ_ONCE(md->status) != newstate && i < 1000; i++) { + /* Bring it out of mwait */ + WRITE_ONCE(md->control, newstate); + udelay(5); } - delta_fratio = (msr >> (i + 5)) & 0x7; - - if (delta_fratio) { - found += 1; - fratio -= delta_fratio; - } - - i += 8; - } while (i < 64); - - return true; -} - -static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) -{ - u64 ratios, counts; - u32 group_size; - int err, i; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios); - if (err) - return false; - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts); - if (err) - return false; - - for (i = 0; i < 64; i += 8) { - group_size = (counts >> i) & 0xFF; - if (group_size >= size) { - *turbo_freq = (ratios >> i) & 0xFF; - return true; - } + if (READ_ONCE(md->status) != newstate) + pr_err_once("CPU%u is stuck in mwait_play_dead()\n", cpu); } - - return false; -} - -static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) -{ - u64 msr; - int err; - - err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq); - if (err) - return false; - - err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr); - if (err) - return false; - - *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ - *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ - - /* The CPU may have less than 4 cores */ - if (!*turbo_freq) - *turbo_freq = msr & 0xFF; /* 1C turbo */ - - return true; } -static bool intel_set_max_freq_ratio(void) +void __noreturn hlt_play_dead(void) { - u64 base_freq, turbo_freq; - u64 turbo_ratio; - - if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) - goto out; - - if (x86_match_cpu(has_glm_turbo_ratio_limits) && - skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) - goto out; - - if (x86_match_cpu(has_knl_turbo_ratio_limits) && - knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) - goto out; - - if (x86_match_cpu(has_skx_turbo_ratio_limits) && - skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) - goto out; - - if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) - goto out; - - return false; - -out: - /* - * Some hypervisors advertise X86_FEATURE_APERFMPERF - * but then fill all MSR's with zeroes. - * Some CPUs have turbo boost but don't declare any turbo ratio - * in MSR_TURBO_RATIO_LIMIT. - */ - if (!base_freq || !turbo_freq) { - pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); - return false; - } - - turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); - if (!turbo_ratio) { - pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); - return false; - } - - arch_turbo_freq_ratio = turbo_ratio; - arch_set_max_freq_ratio(turbo_disabled()); - - return true; -} - -#ifdef CONFIG_ACPI_CPPC_LIB -static bool amd_set_max_freq_ratio(void) -{ - struct cppc_perf_caps perf_caps; - u64 highest_perf, nominal_perf; - u64 perf_ratio; - int rc; - - rc = cppc_get_perf_caps(0, &perf_caps); - if (rc) { - pr_debug("Could not retrieve perf counters (%d)\n", rc); - return false; - } - - highest_perf = amd_get_highest_perf(); - nominal_perf = perf_caps.nominal_perf; - - if (!highest_perf || !nominal_perf) { - pr_debug("Could not retrieve highest or nominal performance\n"); - return false; - } - - perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf); - /* midpoint between max_boost and max_P */ - perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1; - if (!perf_ratio) { - pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n"); - return false; - } - - arch_turbo_freq_ratio = perf_ratio; - arch_set_max_freq_ratio(false); + if (__this_cpu_read(cpu_info.x86) >= 4) + wbinvd(); - return true; -} -#else -static bool amd_set_max_freq_ratio(void) -{ - return false; + while (1) + native_halt(); } -#endif -static void init_counter_refs(void) +void __noreturn native_play_dead(void) { - u64 aperf, mperf; + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + __update_spec_ctrl(0); - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); + play_dead_common(); + tboot_shutdown(TB_SHUTDOWN_WFS); - this_cpu_write(arch_prev_aperf, aperf); - this_cpu_write(arch_prev_mperf, mperf); + /* Below returns only on error. */ + cpuidle_play_dead(); + hlt_play_dead(); } -#ifdef CONFIG_PM_SLEEP -static struct syscore_ops freq_invariance_syscore_ops = { - .resume = init_counter_refs, -}; - -static void register_freq_invariance_syscore_ops(void) +#else /* ... !CONFIG_HOTPLUG_CPU */ +int native_cpu_disable(void) { - /* Bail out if registered already. */ - if (freq_invariance_syscore_ops.node.prev) - return; - - register_syscore_ops(&freq_invariance_syscore_ops); + return -ENOSYS; } -#else -static inline void register_freq_invariance_syscore_ops(void) {} -#endif -static void init_freq_invariance(bool secondary, bool cppc_ready) +void __noreturn native_play_dead(void) { - bool ret = false; - - if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) - return; - - if (secondary) { - if (static_branch_likely(&arch_scale_freq_key)) { - init_counter_refs(); - } - return; - } - - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - ret = intel_set_max_freq_ratio(); - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (!cppc_ready) { - return; - } - ret = amd_set_max_freq_ratio(); - } - - if (ret) { - init_counter_refs(); - static_branch_enable(&arch_scale_freq_key); - register_freq_invariance_syscore_ops(); - pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); - } else { - pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); - } + BUG(); } -#ifdef CONFIG_ACPI_CPPC_LIB -static DEFINE_MUTEX(freq_invariance_lock); - -void init_freq_invariance_cppc(void) -{ - static bool secondary; - - mutex_lock(&freq_invariance_lock); - - init_freq_invariance(secondary, true); - secondary = true; - - mutex_unlock(&freq_invariance_lock); -} #endif - -static void disable_freq_invariance_workfn(struct work_struct *work) -{ - static_branch_disable(&arch_scale_freq_key); -} - -static DECLARE_WORK(disable_freq_invariance_work, - disable_freq_invariance_workfn); - -DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; - -void arch_scale_freq_tick(void) -{ - u64 freq_scale = SCHED_CAPACITY_SCALE; - u64 aperf, mperf; - u64 acnt, mcnt; - - if (!arch_scale_freq_invariant()) - return; - - rdmsrl(MSR_IA32_APERF, aperf); - rdmsrl(MSR_IA32_MPERF, mperf); - - acnt = aperf - this_cpu_read(arch_prev_aperf); - mcnt = mperf - this_cpu_read(arch_prev_mperf); - - this_cpu_write(arch_prev_aperf, aperf); - this_cpu_write(arch_prev_mperf, mperf); - - if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) - goto error; - - if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt) - goto error; - - freq_scale = div64_u64(acnt, mcnt); - if (!freq_scale) - goto error; - - if (freq_scale > SCHED_CAPACITY_SCALE) - freq_scale = SCHED_CAPACITY_SCALE; - - this_cpu_write(arch_freq_scale, freq_scale); - return; - -error: - pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); - schedule_work(&disable_freq_invariance_work); -} -#else -static inline void init_freq_invariance(bool secondary, bool cppc_ready) -{ -} -#endif /* CONFIG_X86_64 */ |