diff options
Diffstat (limited to 'arch/x86/kernel/acpi')
| -rw-r--r-- | arch/x86/kernel/acpi/Makefile | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/boot.c | 217 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/cppc.c | 204 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/cstate.c | 9 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/madt_playdead.S | 28 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/madt_wakeup.c | 292 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/wakeup_64.S | 25 |
7 files changed, 604 insertions, 172 deletions
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index fc17b3f136fe..842a5f449404 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o obj-$(CONFIG_ACPI_CPPC_LIB) += cppc.o +obj-$(CONFIG_ACPI_MADT_WAKEUP) += madt_wakeup.o madt_playdead.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 85a3ce2a3666..dae6a73be40e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -67,13 +67,6 @@ static bool has_lapic_cpus __initdata; static bool acpi_support_online_capable; #endif -#ifdef CONFIG_X86_64 -/* Physical address of the Multiprocessor Wakeup Structure mailbox */ -static u64 acpi_mp_wake_mailbox_paddr; -/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ -static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; -#endif - #ifdef CONFIG_X86_IO_APIC /* * Locks related to IOAPIC hotplug @@ -164,35 +157,6 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -/** - * acpi_register_lapic - register a local apic and generates a logic cpu number - * @id: local apic id to register - * @acpiid: ACPI id to register - * @enabled: this cpu is enabled or not - * - * Returns the logic cpu number which maps to the local apic - */ -static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) -{ - int cpu; - - if (id >= MAX_LOCAL_APIC) { - pr_info("skipped apicid that is too big\n"); - return -EINVAL; - } - - if (!enabled) { - ++disabled_cpus; - return -EINVAL; - } - - cpu = generic_processor_info(id); - if (cpu >= 0) - early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid; - - return cpu; -} - static bool __init acpi_is_processor_usable(u32 lapic_flags) { if (lapic_flags & ACPI_MADT_ENABLED) @@ -254,7 +218,7 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) return 0; } - acpi_register_lapic(apic_id, processor->uid, enabled); + topology_register_apic(apic_id, processor->uid, enabled); #else pr_warn("x2apic entry ignored\n"); #endif @@ -263,6 +227,28 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) } static int __init +acpi_check_lapic(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_local_apic *processor = NULL; + + processor = (struct acpi_madt_local_apic *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + /* Ignore invalid ID */ + if (processor->id == 0xff) + return 0; + + /* Ignore processors that can not be onlined */ + if (!acpi_is_processor_usable(processor->lapic_flags)) + return 0; + + has_lapic_cpus = true; + return 0; +} + +static int __init acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic *processor = NULL; @@ -289,11 +275,10 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - acpi_register_lapic(processor->id, /* APIC ID */ - processor->processor_id, /* ACPI ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + topology_register_apic(processor->id, /* APIC ID */ + processor->processor_id, /* ACPI ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); - has_lapic_cpus = true; return 0; } @@ -309,9 +294,9 @@ acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end) acpi_table_print_madt_entry(&header->common); - acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */ - processor->processor_id, /* ACPI ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + topology_register_apic((processor->id << 8) | processor->eid,/* APIC ID */ + processor->processor_id, /* ACPI ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); return 0; } @@ -370,60 +355,6 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e return 0; } - -#ifdef CONFIG_X86_64 -static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) -{ - /* - * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). - * - * Wakeup of secondary CPUs is fully serialized in the core code. - * No need to protect acpi_mp_wake_mailbox from concurrent accesses. - */ - if (!acpi_mp_wake_mailbox) { - acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, - sizeof(*acpi_mp_wake_mailbox), - MEMREMAP_WB); - } - - /* - * Mailbox memory is shared between the firmware and OS. Firmware will - * listen on mailbox command address, and once it receives the wakeup - * command, the CPU associated with the given apicid will be booted. - * - * The value of 'apic_id' and 'wakeup_vector' must be visible to the - * firmware before the wakeup command is visible. smp_store_release() - * ensures ordering and visibility. - */ - acpi_mp_wake_mailbox->apic_id = apicid; - acpi_mp_wake_mailbox->wakeup_vector = start_ip; - smp_store_release(&acpi_mp_wake_mailbox->command, - ACPI_MP_WAKE_COMMAND_WAKEUP); - - /* - * Wait for the CPU to wake up. - * - * The CPU being woken up is essentially in a spin loop waiting to be - * woken up. It should not take long for it wake up and acknowledge by - * zeroing out ->command. - * - * ACPI specification doesn't provide any guidance on how long kernel - * has to wait for a wake up acknowledgement. It also doesn't provide - * a way to cancel a wake up request if it takes too long. - * - * In TDX environment, the VMM has control over how long it takes to - * wake up secondary. It can postpone scheduling secondary vCPU - * indefinitely. Giving up on wake up request and reporting error opens - * possible attack vector for VMM: it can wake up a secondary CPU when - * kernel doesn't expect it. Wait until positive result of the wake up - * request. - */ - while (READ_ONCE(acpi_mp_wake_mailbox->command)) - cpu_relax(); - - return 0; -} -#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -844,12 +775,10 @@ static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) return 0; } -int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, - int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu) { - int cpu; + int cpu = topology_hotplug_apic(physid, acpi_id); - cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { pr_info("Unable to map lapic to logical cpu number\n"); return cpu; @@ -868,15 +797,11 @@ int acpi_unmap_cpu(int cpu) #ifdef CONFIG_ACPI_NUMA set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); #endif - - per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; - set_cpu_present(cpu, false); - num_processors--; - - return (0); + topology_hotunplug_apic(cpu); + return 0; } EXPORT_SYMBOL(acpi_unmap_cpu); -#endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) { @@ -1007,11 +932,8 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) * the resource tree during the lateinit timeframe. */ #define HPET_RESOURCE_NAME_SIZE 9 - hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, + hpet_res = memblock_alloc_or_panic(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, SMP_CACHE_BYTES); - if (!hpet_res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; @@ -1125,6 +1047,8 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) static int __init acpi_parse_madt_lapic_entries(void) { int count, x2count = 0; + struct acpi_subtable_proc madt_proc[2]; + int ret; if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; @@ -1133,10 +1057,27 @@ static int __init acpi_parse_madt_lapic_entries(void) acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_LOCAL_APIC); - x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_LOCAL_APIC); + /* Check if there are valid LAPIC entries */ + acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_check_lapic, MAX_LOCAL_APIC); + + /* + * Enumerate the APIC IDs in the order that they appear in the + * MADT, no matter LAPIC entry or x2APIC entry is used. + */ + memset(madt_proc, 0, sizeof(madt_proc)); + madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC; + madt_proc[0].handler = acpi_parse_lapic; + madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC; + madt_proc[1].handler = acpi_parse_x2apic; + ret = acpi_table_parse_entries_array(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); + if (ret < 0) { + pr_err("Error parsing LAPIC/X2APIC entries\n"); + return ret; + } + count = madt_proc[0].count; + x2count = madt_proc[1].count; } if (!count && !x2count) { pr_err("No LAPIC entries present\n"); @@ -1159,29 +1100,6 @@ static int __init acpi_parse_madt_lapic_entries(void) } return 0; } - -#ifdef CONFIG_X86_64 -static int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, - const unsigned long end) -{ - struct acpi_madt_multiproc_wakeup *mp_wake; - - if (!IS_ENABLED(CONFIG_SMP)) - return -ENODEV; - - mp_wake = (struct acpi_madt_multiproc_wakeup *)header; - if (BAD_MADT_ENTRY(mp_wake, end)) - return -EINVAL; - - acpi_table_print_madt_entry(&header->common); - - acpi_mp_wake_mailbox_paddr = mp_wake->base_address; - - apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu); - - return 0; -} -#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1290,7 +1208,8 @@ static int __init acpi_parse_madt_ioapic_entries(void) } count = acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, - acpi_parse_int_src_ovr, nr_irqs); + acpi_parse_int_src_ovr, + irq_get_nr_irqs()); if (count < 0) { pr_err("Error parsing interrupt source overrides entry\n"); /* TBD: Cleanup to allow fallback to MPS */ @@ -1310,7 +1229,8 @@ static int __init acpi_parse_madt_ioapic_entries(void) mp_config_acpi_legacy_irqs(); count = acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, - acpi_parse_nmi_src, nr_irqs); + acpi_parse_nmi_src, + irq_get_nr_irqs()); if (count < 0) { pr_err("Error parsing NMI SRC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ @@ -1378,7 +1298,7 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } -#ifdef CONFIG_X86_64 +#ifdef CONFIG_ACPI_MADT_WAKEUP /* * Parse MADT MP Wake entry. */ @@ -1897,3 +1817,14 @@ u64 x86_default_get_root_pointer(void) { return boot_params.acpi_rsdp_addr; } + +#ifdef CONFIG_XEN_PV +void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + return ioremap_cache(phys, size); +} + +void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, acpi_size size) = + x86_acpi_os_ioremap; +EXPORT_SYMBOL_GPL(acpi_os_ioremap); +#endif diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 8d8752b44f11..d745dd586303 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -9,6 +9,17 @@ #include <asm/processor.h> #include <asm/topology.h> +#define CPPC_HIGHEST_PERF_PERFORMANCE 196 +#define CPPC_HIGHEST_PERF_PREFCORE 166 + +enum amd_pref_core { + AMD_PREF_CORE_UNKNOWN = 0, + AMD_PREF_CORE_SUPPORTED, + AMD_PREF_CORE_UNSUPPORTED, +}; +static enum amd_pref_core amd_pref_core_detected; +static u64 boost_numerator; + /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ bool cpc_supported_by_cpu(void) @@ -20,7 +31,7 @@ bool cpc_supported_by_cpu(void) (boot_cpu_data.x86_model >= 0x20 && boot_cpu_data.x86_model <= 0x2f))) return true; else if (boot_cpu_data.x86 == 0x17 && - boot_cpu_data.x86_model >= 0x70 && boot_cpu_data.x86_model <= 0x7f) + boot_cpu_data.x86_model >= 0x30 && boot_cpu_data.x86_model <= 0x7f) return true; return boot_cpu_has(X86_FEATURE_CPPC); } @@ -69,38 +80,37 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) static void amd_set_max_freq_ratio(void) { struct cppc_perf_caps perf_caps; - u64 highest_perf, nominal_perf; + u64 numerator, 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); + pr_warn("Could not retrieve perf counters (%d)\n", rc); return; } - highest_perf = amd_get_highest_perf(); + rc = amd_get_boost_ratio_numerator(0, &numerator); + if (rc) { + pr_warn("Could not retrieve highest performance (%d)\n", rc); + return; + } nominal_perf = perf_caps.nominal_perf; - if (!highest_perf || !nominal_perf) { - pr_debug("Could not retrieve highest or nominal performance\n"); + if (!nominal_perf) { + pr_warn("Could not retrieve nominal performance\n"); return; } - 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; - } + perf_ratio = (div_u64(numerator * SCHED_CAPACITY_SCALE, nominal_perf) + SCHED_CAPACITY_SCALE) >> 1; freq_invariance_set_perf_ratio(perf_ratio, false); } static DEFINE_MUTEX(freq_invariance_lock); -void init_freq_invariance_cppc(void) +static inline void init_freq_invariance_cppc(void) { static bool init_done; @@ -116,3 +126,171 @@ void init_freq_invariance_cppc(void) init_done = true; mutex_unlock(&freq_invariance_lock); } + +void acpi_processor_init_invariance_cppc(void) +{ + init_freq_invariance_cppc(); +} + +/* + * Get the highest performance register value. + * @cpu: CPU from which to get highest performance. + * @highest_perf: Return address for highest performance value. + * + * Return: 0 for success, negative error code otherwise. + */ +int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf) +{ + u64 val; + int ret; + + if (cpu_feature_enabled(X86_FEATURE_CPPC)) { + ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val); + if (ret) + goto out; + + val = AMD_CPPC_HIGHEST_PERF(val); + } else { + ret = cppc_get_highest_perf(cpu, &val); + if (ret) + goto out; + } + + WRITE_ONCE(*highest_perf, (u32)val); +out: + return ret; +} +EXPORT_SYMBOL_GPL(amd_get_highest_perf); + +/** + * amd_detect_prefcore: Detect if CPUs in the system support preferred cores + * @detected: Output variable for the result of the detection. + * + * Determine whether CPUs in the system support preferred cores. On systems + * that support preferred cores, different highest perf values will be found + * on different cores. On other systems, the highest perf value will be the + * same on all cores. + * + * The result of the detection will be stored in the 'detected' parameter. + * + * Return: 0 for success, negative error code otherwise + */ +int amd_detect_prefcore(bool *detected) +{ + int cpu, count = 0; + u64 highest_perf[2] = {0}; + + if (WARN_ON(!detected)) + return -EINVAL; + + switch (amd_pref_core_detected) { + case AMD_PREF_CORE_SUPPORTED: + *detected = true; + return 0; + case AMD_PREF_CORE_UNSUPPORTED: + *detected = false; + return 0; + default: + break; + } + + for_each_present_cpu(cpu) { + u32 tmp; + int ret; + + ret = amd_get_highest_perf(cpu, &tmp); + if (ret) + return ret; + + if (!count || (count == 1 && tmp != highest_perf[0])) + highest_perf[count++] = tmp; + + if (count == 2) + break; + } + + *detected = (count == 2); + boost_numerator = highest_perf[0]; + + amd_pref_core_detected = *detected ? AMD_PREF_CORE_SUPPORTED : + AMD_PREF_CORE_UNSUPPORTED; + + pr_debug("AMD CPPC preferred core is %ssupported (highest perf: 0x%llx)\n", + *detected ? "" : "un", highest_perf[0]); + + return 0; +} +EXPORT_SYMBOL_GPL(amd_detect_prefcore); + +/** + * amd_get_boost_ratio_numerator: Get the numerator to use for boost ratio calculation + * @cpu: CPU to get numerator for. + * @numerator: Output variable for numerator. + * + * Determine the numerator to use for calculating the boost ratio on + * a CPU. On systems that support preferred cores, this will be a hardcoded + * value. On other systems this will the highest performance register value. + * + * If booting the system with amd-pstate enabled but preferred cores disabled then + * the correct boost numerator will be returned to match hardware capabilities + * even if the preferred cores scheduling hints are not enabled. + * + * Return: 0 for success, negative error code otherwise. + */ +int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator) +{ + enum x86_topology_cpu_type core_type = get_topology_cpu_type(&cpu_data(cpu)); + bool prefcore; + int ret; + u32 tmp; + + ret = amd_detect_prefcore(&prefcore); + if (ret) + return ret; + + /* without preferred cores, return the highest perf register value */ + if (!prefcore) { + *numerator = boost_numerator; + return 0; + } + + /* + * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f, + * the highest performance level is set to 196. + * https://bugzilla.kernel.org/show_bug.cgi?id=218759 + */ + if (cpu_feature_enabled(X86_FEATURE_ZEN4)) { + switch (boot_cpu_data.x86_model) { + case 0x70 ... 0x7f: + *numerator = CPPC_HIGHEST_PERF_PERFORMANCE; + return 0; + default: + break; + } + } + + /* detect if running on heterogeneous design */ + if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) { + switch (core_type) { + case TOPO_CPU_TYPE_UNKNOWN: + pr_warn("Undefined core type found for cpu %d\n", cpu); + break; + case TOPO_CPU_TYPE_PERFORMANCE: + /* use the max scale for performance cores */ + *numerator = CPPC_HIGHEST_PERF_PERFORMANCE; + return 0; + case TOPO_CPU_TYPE_EFFICIENCY: + /* use the highest perf value for efficiency cores */ + ret = amd_get_highest_perf(cpu, &tmp); + if (ret) + return ret; + *numerator = tmp; + return 0; + } + } + + *numerator = CPPC_HIGHEST_PERF_PREFCORE; + + return 0; +} +EXPORT_SYMBOL_GPL(amd_get_boost_ratio_numerator); diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 401808b47af3..5854f0b8f0f1 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <acpi/processor.h> +#include <asm/cpuid.h> #include <asm/mwait.h> #include <asm/special_insns.h> @@ -128,11 +129,11 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) unsigned int cstate_type; /* C-state type and not ACPI C-state type */ unsigned int num_cstate_subtype; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); /* Check whether this particular cx_type (in CST) is supported or not */ - cstate_type = ((cx->address >> MWAIT_SUBSTATE_SIZE) & - MWAIT_CSTATE_MASK) + 1; + cstate_type = (((cx->address >> MWAIT_SUBSTATE_SIZE) & + MWAIT_CSTATE_MASK) + 1) & MWAIT_CSTATE_MASK; edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE); num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK; @@ -172,7 +173,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, struct cpuinfo_x86 *c = &cpu_data(cpu); long retval; - if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF) + if (!cpu_cstate_entry || c->cpuid_level < CPUID_LEAF_MWAIT) return -1; if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT) diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S new file mode 100644 index 000000000000..4e498d28cdc8 --- /dev/null +++ b/arch/x86/kernel/acpi/madt_playdead.S @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <asm/nospec-branch.h> +#include <asm/page_types.h> +#include <asm/processor-flags.h> + + .text + .align PAGE_SIZE + +/* + * asm_acpi_mp_play_dead() - Hand over control of the CPU to the BIOS + * + * rdi: Address of the ACPI MADT MPWK ResetVector + * rsi: PGD of the identity mapping + */ +SYM_FUNC_START(asm_acpi_mp_play_dead) + /* Turn off global entries. Following CR3 write will flush them. */ + movq %cr4, %rdx + andq $~(X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* Switch to identity mapping */ + movq %rsi, %cr3 + + /* Jump to reset vector */ + ANNOTATE_RETPOLINE_SAFE + jmp *%rdi +SYM_FUNC_END(asm_acpi_mp_play_dead) diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c new file mode 100644 index 000000000000..d5ef6215583b --- /dev/null +++ b/arch/x86/kernel/acpi/madt_wakeup.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/acpi.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/kexec.h> +#include <linux/memblock.h> +#include <linux/pgtable.h> +#include <linux/sched/hotplug.h> +#include <asm/apic.h> +#include <asm/barrier.h> +#include <asm/init.h> +#include <asm/intel_pt.h> +#include <asm/nmi.h> +#include <asm/processor.h> +#include <asm/reboot.h> + +/* Physical address of the Multiprocessor Wakeup Structure mailbox */ +static u64 acpi_mp_wake_mailbox_paddr __ro_after_init; + +/* Virtual address of the Multiprocessor Wakeup Structure mailbox */ +static struct acpi_madt_multiproc_wakeup_mailbox *acpi_mp_wake_mailbox; + +static u64 acpi_mp_pgd __ro_after_init; +static u64 acpi_mp_reset_vector_paddr __ro_after_init; + +static void acpi_mp_stop_this_cpu(void) +{ + asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd); +} + +static void acpi_mp_play_dead(void) +{ + play_dead_common(); + asm_acpi_mp_play_dead(acpi_mp_reset_vector_paddr, acpi_mp_pgd); +} + +static void acpi_mp_cpu_die(unsigned int cpu) +{ + u32 apicid = per_cpu(x86_cpu_to_apicid, cpu); + unsigned long timeout; + + /* + * Use TEST mailbox command to prove that BIOS got control over + * the CPU before declaring it dead. + * + * BIOS has to clear 'command' field of the mailbox. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_TEST); + + /* Don't wait longer than a second. */ + timeout = USEC_PER_SEC; + while (READ_ONCE(acpi_mp_wake_mailbox->command) && --timeout) + udelay(1); + + if (!timeout) + pr_err("Failed to hand over CPU %d to BIOS\n", cpu); +} + +/* The argument is required to match type of x86_mapping_info::alloc_pgt_page */ +static void __init *alloc_pgt_page(void *dummy) +{ + return memblock_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static void __init free_pgt_page(void *pgt, void *dummy) +{ + return memblock_free(pgt, PAGE_SIZE); +} + +/* + * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at + * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches + * to the identity mapping and the function has be present at the same spot in + * the virtual address space before and after switching page tables. + */ +static int __init init_transition_pgtable(pgd_t *pgd) +{ + pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; + unsigned long vaddr, paddr; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + vaddr = (unsigned long)asm_acpi_mp_play_dead; + pgd += pgd_index(vaddr); + if (!pgd_present(*pgd)) { + p4d = (p4d_t *)alloc_pgt_page(NULL); + if (!p4d) + return -ENOMEM; + set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE)); + } + p4d = p4d_offset(pgd, vaddr); + if (!p4d_present(*p4d)) { + pud = (pud_t *)alloc_pgt_page(NULL); + if (!pud) + return -ENOMEM; + set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE)); + } + pud = pud_offset(p4d, vaddr); + if (!pud_present(*pud)) { + pmd = (pmd_t *)alloc_pgt_page(NULL); + if (!pmd) + return -ENOMEM; + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); + } + pmd = pmd_offset(pud, vaddr); + if (!pmd_present(*pmd)) { + pte = (pte_t *)alloc_pgt_page(NULL); + if (!pte) + return -ENOMEM; + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE)); + } + pte = pte_offset_kernel(pmd, vaddr); + + paddr = __pa(vaddr); + set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot)); + + return 0; +} + +static int __init acpi_mp_setup_reset(u64 reset_vector) +{ + struct x86_mapping_info info = { + .alloc_pgt_page = alloc_pgt_page, + .free_pgt_page = free_pgt_page, + .page_flag = __PAGE_KERNEL_LARGE_EXEC, + .kernpg_flag = _KERNPG_TABLE_NOENC, + }; + pgd_t *pgd; + + pgd = alloc_pgt_page(NULL); + if (!pgd) + return -ENOMEM; + + for (int i = 0; i < nr_pfn_mapped; i++) { + unsigned long mstart, mend; + + mstart = pfn_mapped[i].start << PAGE_SHIFT; + mend = pfn_mapped[i].end << PAGE_SHIFT; + if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + } + + if (kernel_ident_mapping_init(&info, pgd, + PAGE_ALIGN_DOWN(reset_vector), + PAGE_ALIGN(reset_vector + 1))) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + + if (init_transition_pgtable(pgd)) { + kernel_ident_mapping_free(&info, pgd); + return -ENOMEM; + } + + smp_ops.play_dead = acpi_mp_play_dead; + smp_ops.stop_this_cpu = acpi_mp_stop_this_cpu; + smp_ops.cpu_die = acpi_mp_cpu_die; + + acpi_mp_reset_vector_paddr = reset_vector; + acpi_mp_pgd = __pa(pgd); + + return 0; +} + +static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) +{ + if (!acpi_mp_wake_mailbox_paddr) { + pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n"); + return -EOPNOTSUPP; + } + + /* + * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). + * + * Wakeup of secondary CPUs is fully serialized in the core code. + * No need to protect acpi_mp_wake_mailbox from concurrent accesses. + */ + if (!acpi_mp_wake_mailbox) { + acpi_mp_wake_mailbox = memremap(acpi_mp_wake_mailbox_paddr, + sizeof(*acpi_mp_wake_mailbox), + MEMREMAP_WB); + } + + /* + * Mailbox memory is shared between the firmware and OS. Firmware will + * listen on mailbox command address, and once it receives the wakeup + * command, the CPU associated with the given apicid will be booted. + * + * The value of 'apic_id' and 'wakeup_vector' must be visible to the + * firmware before the wakeup command is visible. smp_store_release() + * ensures ordering and visibility. + */ + acpi_mp_wake_mailbox->apic_id = apicid; + acpi_mp_wake_mailbox->wakeup_vector = start_ip; + smp_store_release(&acpi_mp_wake_mailbox->command, + ACPI_MP_WAKE_COMMAND_WAKEUP); + + /* + * Wait for the CPU to wake up. + * + * The CPU being woken up is essentially in a spin loop waiting to be + * woken up. It should not take long for it wake up and acknowledge by + * zeroing out ->command. + * + * ACPI specification doesn't provide any guidance on how long kernel + * has to wait for a wake up acknowledgment. It also doesn't provide + * a way to cancel a wake up request if it takes too long. + * + * In TDX environment, the VMM has control over how long it takes to + * wake up secondary. It can postpone scheduling secondary vCPU + * indefinitely. Giving up on wake up request and reporting error opens + * possible attack vector for VMM: it can wake up a secondary CPU when + * kernel doesn't expect it. Wait until positive result of the wake up + * request. + */ + while (READ_ONCE(acpi_mp_wake_mailbox->command)) + cpu_relax(); + + return 0; +} + +static void acpi_mp_disable_offlining(struct acpi_madt_multiproc_wakeup *mp_wake) +{ + cpu_hotplug_disable_offlining(); + + /* + * ACPI MADT doesn't allow to offline a CPU after it was onlined. This + * limits kexec: the second kernel won't be able to use more than one CPU. + * + * To prevent a kexec kernel from onlining secondary CPUs invalidate the + * mailbox address in the ACPI MADT wakeup structure which prevents a + * kexec kernel to use it. + * + * This is safe as the booting kernel has the mailbox address cached + * already and acpi_wakeup_cpu() uses the cached value to bring up the + * secondary CPUs. + * + * Note: This is a Linux specific convention and not covered by the + * ACPI specification. + */ + mp_wake->mailbox_address = 0; +} + +int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_multiproc_wakeup *mp_wake; + + mp_wake = (struct acpi_madt_multiproc_wakeup *)header; + + /* + * Cannot use the standard BAD_MADT_ENTRY() to sanity check the @mp_wake + * entry. 'sizeof (struct acpi_madt_multiproc_wakeup)' can be larger + * than the actual size of the MP wakeup entry in ACPI table because the + * 'reset_vector' is only available in the V1 MP wakeup structure. + */ + if (!mp_wake) + return -EINVAL; + if (end - (unsigned long)mp_wake < ACPI_MADT_MP_WAKEUP_SIZE_V0) + return -EINVAL; + if (mp_wake->header.length < ACPI_MADT_MP_WAKEUP_SIZE_V0) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + acpi_mp_wake_mailbox_paddr = mp_wake->mailbox_address; + + if (mp_wake->version >= ACPI_MADT_MP_WAKEUP_VERSION_V1 && + mp_wake->header.length >= ACPI_MADT_MP_WAKEUP_SIZE_V1) { + if (acpi_mp_setup_reset(mp_wake->reset_vector)) { + pr_warn("Failed to setup MADT reset vector\n"); + acpi_mp_disable_offlining(mp_wake); + } + } else { + /* + * CPU offlining requires version 1 of the ACPI MADT wakeup + * structure. + */ + acpi_mp_disable_offlining(mp_wake); + } + + apic_update_callback(wakeup_secondary_cpu_64, acpi_wakeup_cpu); + + return 0; +} diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index d5d8a352eafa..b200a193beeb 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -17,7 +17,7 @@ * Hooray, we are in Long 64-bit mode (but still running in low memory) */ SYM_FUNC_START(wakeup_long64) - movq saved_magic, %rax + movq saved_magic(%rip), %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax je 2f @@ -33,14 +33,14 @@ SYM_FUNC_START(wakeup_long64) movw %ax, %es movw %ax, %fs movw %ax, %gs - movq saved_rsp, %rsp + movq saved_rsp(%rip), %rsp - movq saved_rbx, %rbx - movq saved_rdi, %rdi - movq saved_rsi, %rsi - movq saved_rbp, %rbp + movq saved_rbx(%rip), %rbx + movq saved_rdi(%rip), %rdi + movq saved_rsi(%rip), %rsi + movq saved_rbp(%rip), %rbp - movq saved_rip, %rax + movq saved_rip(%rip), %rax ANNOTATE_RETPOLINE_SAFE jmp *%rax SYM_FUNC_END(wakeup_long64) @@ -72,11 +72,11 @@ SYM_FUNC_START(do_suspend_lowlevel) movq $.Lresume_point, saved_rip(%rip) - movq %rsp, saved_rsp - movq %rbp, saved_rbp - movq %rbx, saved_rbx - movq %rdi, saved_rdi - movq %rsi, saved_rsi + movq %rsp, saved_rsp(%rip) + movq %rbp, saved_rbp(%rip) + movq %rbx, saved_rbx(%rip) + movq %rdi, saved_rdi(%rip) + movq %rsi, saved_rsi(%rip) addq $8, %rsp movl $3, %edi @@ -87,6 +87,7 @@ SYM_FUNC_START(do_suspend_lowlevel) .align 4 .Lresume_point: + ANNOTATE_NOENDBR /* We don't restore %rax, it must be 0 anyway */ movq $saved_context, %rax movq saved_context_cr4(%rax), %rbx |