diff options
Diffstat (limited to 'arch/x86/kernel/acpi')
| -rw-r--r-- | arch/x86/kernel/acpi/Makefile | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/apei.c | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/boot.c | 308 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/cppc.c | 118 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/cppc_msr.c | 49 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/cstate.c | 21 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/sleep.c | 29 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/sleep.h | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/wakeup_32.S | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/acpi/wakeup_64.S | 6 |
10 files changed, 384 insertions, 163 deletions
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index f1bb57b0e41e..fc17b3f136fe 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y obj-$(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_msr.o +obj-$(CONFIG_ACPI_CPPC_LIB) += cppc.o ifneq ($(CONFIG_ACPI_PROCESSOR),) obj-y += cstate.o diff --git a/arch/x86/kernel/acpi/apei.c b/arch/x86/kernel/acpi/apei.c index c22fb55abcfd..0916f00a992e 100644 --- a/arch/x86/kernel/acpi/apei.c +++ b/arch/x86/kernel/acpi/apei.c @@ -43,3 +43,8 @@ void arch_apei_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) apei_mce_report_mem_error(sev, mem_err); #endif } + +int arch_apei_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) +{ + return apei_smca_report_x86_error(ctx_info, lapic_id); +} diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 04205ce127a1..907cc98b1938 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -5,6 +5,7 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2001 Jun Nakajima <jun.nakajima@intel.com> */ +#define pr_fmt(fmt) "ACPI: " fmt #include <linux/init.h> #include <linux/acpi.h> @@ -20,11 +21,11 @@ #include <linux/pci.h> #include <linux/efi-bgrt.h> #include <linux/serial_core.h> +#include <linux/pgtable.h> #include <asm/e820/api.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> -#include <asm/pgtable.h> #include <asm/io_apic.h> #include <asm/apic.h> #include <asm/io.h> @@ -42,9 +43,8 @@ EXPORT_SYMBOL(acpi_disabled); # include <asm/proto.h> #endif /* X86 */ -#define PREFIX "ACPI: " - int acpi_noirq; /* skip ACPI IRQ initialization */ +static int acpi_nobgrt; /* skip ACPI BGRT */ int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); @@ -62,6 +62,14 @@ int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; +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 @@ -129,16 +137,17 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) madt = (struct acpi_table_madt *)table; if (!madt) { - printk(KERN_WARNING PREFIX "Unable to map MADT\n"); + pr_warn("Unable to map MADT\n"); return -ENODEV; } if (madt->address) { acpi_lapic_addr = (u64) madt->address; - printk(KERN_DEBUG PREFIX "Local APIC address 0x%08x\n", - madt->address); + pr_debug("Local APIC address 0x%08x\n", madt->address); } + if (madt->header.revision >= 5) + acpi_support_online_capable = true; default_acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id); @@ -160,7 +169,7 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) int cpu; if (id >= MAX_LOCAL_APIC) { - printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); + pr_info("skipped apicid that is too big\n"); return -EINVAL; } @@ -212,13 +221,13 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) */ if (!apic->apic_id_valid(apic_id)) { if (enabled) - pr_warn(PREFIX "x2apic entry ignored\n"); + pr_warn("x2apic entry ignored\n"); return 0; } acpi_register_lapic(apic_id, processor->uid, enabled); #else - printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); + pr_warn("x2apic entry ignored\n"); #endif return 0; @@ -240,6 +249,12 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) if (processor->id == 0xff) return 0; + /* don't register processors that can not be onlined */ + if (acpi_support_online_capable && + !(processor->lapic_flags & ACPI_MADT_ENABLED) && + !(processor->lapic_flags & ACPI_MADT_ONLINE_CAPABLE)) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size @@ -305,7 +320,7 @@ acpi_parse_x2apic_nmi(union acpi_subtable_headers *header, acpi_table_print_madt_entry(&header->common); if (x2apic_nmi->lint != 1) - printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + pr_warn("NMI not connected to LINT 1!\n"); return 0; } @@ -323,12 +338,65 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e acpi_table_print_madt_entry(&header->common); if (lapic_nmi->lint != 1) - printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + pr_warn("NMI not connected to LINT 1!\n"); return 0; } -#endif /*CONFIG_X86_LOCAL_APIC */ +#ifdef CONFIG_X86_64 +static int acpi_wakeup_cpu(int 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 #define MP_ISA_BUS 0 @@ -367,7 +435,7 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, isa_irq_to_gsi[bus_irq] = gsi; } -static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, +static void mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, int polarity) { #ifdef CONFIG_X86_MPPARSE @@ -379,9 +447,9 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, u8 pin; if (!acpi_ioapic) - return 0; + return; if (!dev || !dev_is_pci(dev)) - return 0; + return; pdev = to_pci_dev(dev); number = pdev->bus->number; @@ -400,7 +468,6 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, mp_save_irq(&mp_irq); #endif - return 0; } static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, @@ -513,14 +580,14 @@ acpi_parse_int_src_ovr(union acpi_subtable_headers * header, if (intsrc->source_irq == 0) { if (acpi_skip_timer_override) { - printk(PREFIX "BIOS IRQ0 override ignored.\n"); + pr_warn("BIOS IRQ0 override ignored.\n"); return 0; } if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; - printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); + pr_warn("BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); } } @@ -559,10 +626,10 @@ acpi_parse_nmi_src(union acpi_subtable_headers * header, const unsigned long end * If a PIC-mode SCI is not recognized or gives spurious IRQ7's * it may require Edge Trigger -- use "acpi_sci=edge" * - * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers + * Port 0x4d0-4d1 are ELCR1 and ELCR2, the Edge/Level Control Registers * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge. - * ECLR1 is IRQs 0-7 (IRQ 0, 1, 2 must be 0) - * ECLR2 is IRQs 8-15 (IRQ 8, 13 must be 0) + * ELCR1 is IRQs 0-7 (IRQ 0, 1, 2 must be 0) + * ELCR2 is IRQs 8-15 (IRQ 8, 13 must be 0) */ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) @@ -571,7 +638,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) unsigned int old, new; /* Real old ELCR mask */ - old = inb(0x4d0) | (inb(0x4d1) << 8); + old = inb(PIC_ELCR1) | (inb(PIC_ELCR2) << 8); /* * If we use ACPI to set PCI IRQs, then we should clear ELCR @@ -596,9 +663,9 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) if (old == new) return; - printk(PREFIX "setting ELCR to %04x (from %04x)\n", new, old); - outb(new, 0x4d0); - outb(new >> 8, 0x4d1); + pr_warn("setting ELCR to %04x (from %04x)\n", new, old); + outb(new, PIC_ELCR1); + outb(new >> 8, PIC_ELCR2); } int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp) @@ -753,7 +820,7 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { - pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); + pr_info("Unable to map lapic to logical cpu number\n"); return cpu; } @@ -829,7 +896,7 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base) EXPORT_SYMBOL(acpi_unregister_ioapic); /** - * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base + * acpi_ioapic_registered - Check whether IOAPIC associated with @gsi_base * has been registered * @handle: ACPI handle of the IOAPIC device * @gsi_base: GSI base associated with the IOAPIC @@ -869,8 +936,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) struct acpi_table_hpet *hpet_tbl = (struct acpi_table_hpet *)table; if (hpet_tbl->address.space_id != ACPI_SPACE_MEM) { - printk(KERN_WARNING PREFIX "HPET timers must be located in " - "memory.\n"); + pr_warn("HPET timers must be located in memory.\n"); return -1; } @@ -882,9 +948,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) * want to allocate a resource there. */ if (!hpet_address) { - printk(KERN_WARNING PREFIX - "HPET id: %#x base: %#lx is invalid\n", - hpet_tbl->id, hpet_address); + pr_warn("HPET id: %#x base: %#lx is invalid\n", hpet_tbl->id, hpet_address); return 0; } #ifdef CONFIG_X86_64 @@ -895,21 +959,17 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) */ if (hpet_address == 0xfed0000000000000UL) { if (!hpet_force_user) { - printk(KERN_WARNING PREFIX "HPET id: %#x " - "base: 0xfed0000000000000 is bogus\n " - "try hpet=force on the kernel command line to " - "fix it up to 0xfed00000.\n", hpet_tbl->id); + pr_warn("HPET id: %#x base: 0xfed0000000000000 is bogus, try hpet=force on the kernel command line to fix it up to 0xfed00000.\n", + hpet_tbl->id); hpet_address = 0; return 0; } - printk(KERN_WARNING PREFIX - "HPET id: %#x base: 0xfed0000000000000 fixed up " - "to 0xfed00000.\n", hpet_tbl->id); + pr_warn("HPET id: %#x base: 0xfed0000000000000 fixed up to 0xfed00000.\n", + hpet_tbl->id); hpet_address >>= 32; } #endif - printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", - hpet_tbl->id, hpet_address); + pr_info("HPET id: %#x base: %#lx\n", hpet_tbl->id, hpet_address); /* * Allocate and initialize the HPET firmware resource for adding into @@ -954,24 +1014,24 @@ late_initcall(hpet_insert_resource); static int __init acpi_parse_fadt(struct acpi_table_header *table) { if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) { - pr_debug("ACPI: no legacy devices present\n"); + pr_debug("no legacy devices present\n"); x86_platform.legacy.devices.pnpbios = 0; } if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && !(acpi_gbl_FADT.boot_flags & ACPI_FADT_8042) && x86_platform.legacy.i8042 != X86_LEGACY_I8042_PLATFORM_ABSENT) { - pr_debug("ACPI: i8042 controller is absent\n"); + pr_debug("i8042 controller is absent\n"); x86_platform.legacy.i8042 = X86_LEGACY_I8042_FIRMWARE_ABSENT; } if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { - pr_debug("ACPI: not registering RTC platform device\n"); + pr_debug("not registering RTC platform device\n"); x86_platform.legacy.rtc = 0; } if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_VGA) { - pr_debug("ACPI: probing for VGA not safe\n"); + pr_debug("probing for VGA not safe\n"); x86_platform.legacy.no_vga = 1; } @@ -996,8 +1056,7 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) pmtmr_ioport = acpi_gbl_FADT.pm_timer_block; } if (pmtmr_ioport) - printk(KERN_INFO PREFIX "PM-Timer IO Port: %#x\n", - pmtmr_ioport); + pr_info("PM-Timer IO Port: %#x\n", pmtmr_ioport); #endif return 0; } @@ -1023,8 +1082,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, acpi_parse_lapic_addr_ovr, 0); if (count < 0) { - printk(KERN_ERR PREFIX - "Error parsing LAPIC address override entry\n"); + pr_err("Error parsing LAPIC address override entry\n"); return count; } @@ -1056,8 +1114,7 @@ static int __init acpi_parse_madt_lapic_entries(void) sizeof(struct acpi_table_madt), madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); if (ret < 0) { - printk(KERN_ERR PREFIX - "Error parsing LAPIC/X2APIC entries\n"); + pr_err("Error parsing LAPIC/X2APIC entries\n"); return ret; } @@ -1065,11 +1122,11 @@ static int __init acpi_parse_madt_lapic_entries(void) x2count = madt_proc[1].count; } if (!count && !x2count) { - printk(KERN_ERR PREFIX "No LAPIC entries present\n"); + pr_err("No LAPIC entries present\n"); /* TBD: Cleanup to allow fallback to MPS */ return -ENODEV; } else if (count < 0 || x2count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n"); + pr_err("Error parsing LAPIC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1079,12 +1136,35 @@ static int __init acpi_parse_madt_lapic_entries(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0); if (count < 0 || x2count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); + pr_err("Error parsing LAPIC NMI entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } 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; + + acpi_wake_cpu_handler_update(acpi_wakeup_cpu); + + return 0; +} +#endif /* CONFIG_X86_64 */ #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC @@ -1138,7 +1218,7 @@ static void __init mp_config_acpi_legacy_irqs(void) } if (idx != mp_irq_entries) { - printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); + pr_debug("ACPI: IRQ%d used by override.\n", i); continue; /* IRQ already used */ } @@ -1178,26 +1258,24 @@ static int __init acpi_parse_madt_ioapic_entries(void) * if "noapic" boot option, don't look for IO-APICs */ if (skip_ioapic_setup) { - printk(KERN_INFO PREFIX "Skipping IOAPIC probe " - "due to 'noapic' option.\n"); + pr_info("Skipping IOAPIC probe due to 'noapic' option.\n"); return -ENODEV; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic, MAX_IO_APICS); if (!count) { - printk(KERN_ERR PREFIX "No IOAPIC entries present\n"); + pr_err("No IOAPIC entries present\n"); return -ENODEV; } else if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing IOAPIC entry\n"); + pr_err("Error parsing IOAPIC entry\n"); return count; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr, nr_irqs); if (count < 0) { - printk(KERN_ERR PREFIX - "Error parsing interrupt source overrides entry\n"); + pr_err("Error parsing interrupt source overrides entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1217,7 +1295,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src, nr_irqs); if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n"); + pr_err("Error parsing NMI SRC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1250,8 +1328,7 @@ static void __init early_acpi_process_madt(void) /* * Dell Precision Workstation 410, 610 come here. */ - printk(KERN_ERR PREFIX - "Invalid BIOS MADT, disabling ACPI\n"); + pr_err("Invalid BIOS MADT, disabling ACPI\n"); disable_acpi(); } } @@ -1283,13 +1360,20 @@ static void __init acpi_process_madt(void) smp_found_config = 1; } + +#ifdef CONFIG_X86_64 + /* + * Parse MADT MP Wake entry. + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_MULTIPROC_WAKEUP, + acpi_parse_mp_wake, 1); +#endif } if (error == -EINVAL) { /* * Dell Precision Workstation 410, 610 come here. */ - printk(KERN_ERR PREFIX - "Invalid BIOS MADT, disabling ACPI\n"); + pr_err("Invalid BIOS MADT, disabling ACPI\n"); disable_acpi(); } } else { @@ -1299,8 +1383,7 @@ static void __init acpi_process_madt(void) * Boot with "acpi=off" to use MPS on such a system. */ if (smp_found_config) { - printk(KERN_WARNING PREFIX - "No APIC-table, disabling MPS\n"); + pr_warn("No APIC-table, disabling MPS\n"); smp_found_config = 0; } } @@ -1310,11 +1393,9 @@ static void __init acpi_process_madt(void) * processors, where MPS only supports physical. */ if (acpi_lapic && acpi_ioapic) - printk(KERN_INFO "Using ACPI (MADT) for SMP configuration " - "information\n"); + pr_info("Using ACPI (MADT) for SMP configuration information\n"); else if (acpi_lapic) - printk(KERN_INFO "Using ACPI for processor (LAPIC) " - "configuration information\n"); + pr_info("Using ACPI for processor (LAPIC) configuration information\n"); #endif return; } @@ -1322,8 +1403,7 @@ static void __init acpi_process_madt(void) static int __init disable_acpi_irq(const struct dmi_system_id *d) { if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of acpi=noirq\n", - d->ident); + pr_notice("%s detected: force use of acpi=noirq\n", d->ident); acpi_noirq_set(); } return 0; @@ -1332,21 +1412,30 @@ static int __init disable_acpi_irq(const struct dmi_system_id *d) static int __init disable_acpi_pci(const struct dmi_system_id *d) { if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of pci=noacpi\n", - d->ident); + pr_notice("%s detected: force use of pci=noacpi\n", d->ident); acpi_disable_pci(); } return 0; } +static int __init disable_acpi_xsdt(const struct dmi_system_id *d) +{ + if (!acpi_force) { + pr_notice("%s detected: force use of acpi=rsdt\n", d->ident); + acpi_gbl_do_not_use_xsdt = TRUE; + } else { + pr_notice("Warning: DMI blacklist says broken, but acpi XSDT forced\n"); + } + return 0; +} + static int __init dmi_disable_acpi(const struct dmi_system_id *d) { if (!acpi_force) { - printk(KERN_NOTICE "%s detected: acpi off\n", d->ident); + pr_notice("%s detected: acpi off\n", d->ident); disable_acpi(); } else { - printk(KERN_NOTICE - "Warning: DMI blacklist says broken, but acpi forced\n"); + pr_notice("Warning: DMI blacklist says broken, but acpi forced\n"); } return 0; } @@ -1463,6 +1552,19 @@ static const struct dmi_system_id acpi_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), }, }, + /* + * Boxes that need ACPI XSDT use disabled due to corrupted tables + */ + { + .callback = disable_acpi_xsdt, + .ident = "Advantech DAC-BJ01", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Bearlake CRB Board"), + DMI_MATCH(DMI_BIOS_VERSION, "V1.12"), + DMI_MATCH(DMI_BIOS_DATE, "02/01/2011"), + }, + }, {} }; @@ -1553,10 +1655,18 @@ void __init acpi_boot_table_init(void) /* * Initialize the ACPI boot-time table parser. */ - if (acpi_table_init()) { + if (acpi_locate_initial_tables()) disable_acpi(); - return; - } + else + acpi_reserve_initial_tables(); +} + +int __init early_acpi_boot_init(void) +{ + if (acpi_disabled) + return 1; + + acpi_table_init_complete(); acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1565,22 +1675,13 @@ void __init acpi_boot_table_init(void) */ if (acpi_blacklisted()) { if (acpi_force) { - printk(KERN_WARNING PREFIX "acpi=force override\n"); + pr_warn("acpi=force override\n"); } else { - printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); + pr_warn("Disabling ACPI support\n"); disable_acpi(); - return; + return 1; } } -} - -int __init early_acpi_boot_init(void) -{ - /* - * If acpi_disabled, bail out - */ - if (acpi_disabled) - return 1; /* * Process the Multiple APIC Description Table (MADT), if present @@ -1619,7 +1720,7 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); - if (IS_ENABLED(CONFIG_ACPI_BGRT)) + if (IS_ENABLED(CONFIG_ACPI_BGRT) && !acpi_nobgrt) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) @@ -1656,7 +1757,7 @@ static int __init parse_acpi(char *arg) else if (strcmp(arg, "noirq") == 0) { acpi_noirq_set(); } - /* "acpi=copy_dsdt" copys DSDT */ + /* "acpi=copy_dsdt" copies DSDT */ else if (strcmp(arg, "copy_dsdt") == 0) { acpi_gbl_copy_dsdt_locally = 1; } @@ -1671,6 +1772,13 @@ static int __init parse_acpi(char *arg) } early_param("acpi", parse_acpi); +static int __init parse_acpi_bgrt(char *arg) +{ + acpi_nobgrt = true; + return 0; +} +early_param("bgrt_disable", parse_acpi_bgrt); + /* FIXME: Using pci= for an ACPI parameter is a travesty. */ static int __init parse_pci(char *arg) { @@ -1685,9 +1793,7 @@ int __init acpi_mps_check(void) #if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE) /* mptable code is not built-in*/ if (acpi_disabled || acpi_noirq) { - printk(KERN_WARNING "MPS support code is not built-in.\n" - "Using acpi=off or acpi=noirq or pci=noacpi " - "may have problem\n"); + pr_warn("MPS support code is not built-in, using acpi=off or acpi=noirq or pci=noacpi may have problem\n"); return 1; } #endif @@ -1740,7 +1846,7 @@ int __acpi_acquire_global_lock(unsigned int *lock) new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); val = cmpxchg(lock, old, new); } while (unlikely (val != old)); - return (new < 3) ? -1 : 0; + return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) @@ -1756,7 +1862,7 @@ int __acpi_release_global_lock(unsigned int *lock) void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) { - e820__range_add(addr, size, E820_TYPE_ACPI); + e820__range_add(addr, size, E820_TYPE_NVS); e820__update_table_print(); } diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c new file mode 100644 index 000000000000..8d8752b44f11 --- /dev/null +++ b/arch/x86/kernel/acpi/cppc.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * cppc.c: CPPC Interface for x86 + * Copyright (c) 2016, Intel Corporation. + */ + +#include <acpi/cppc_acpi.h> +#include <asm/msr.h> +#include <asm/processor.h> +#include <asm/topology.h> + +/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ + +bool cpc_supported_by_cpu(void) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: + if (boot_cpu_data.x86 == 0x19 && ((boot_cpu_data.x86_model <= 0x0f) || + (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) + return true; + return boot_cpu_has(X86_FEATURE_CPPC); + } + return false; +} + +bool cpc_ffh_supported(void) +{ + return true; +} + +int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val) +{ + int err; + + err = rdmsrl_safe_on_cpu(cpunum, reg->address, val); + if (!err) { + u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, + reg->bit_offset); + + *val &= mask; + *val >>= reg->bit_offset; + } + return err; +} + +int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) +{ + u64 rd_val; + int err; + + err = rdmsrl_safe_on_cpu(cpunum, reg->address, &rd_val); + if (!err) { + u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, + reg->bit_offset); + + val <<= reg->bit_offset; + val &= mask; + rd_val &= ~mask; + rd_val |= val; + err = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val); + } + return err; +} + +static void 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; + } + + 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; + } + + 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; + } + + freq_invariance_set_perf_ratio(perf_ratio, false); +} + +static DEFINE_MUTEX(freq_invariance_lock); + +void init_freq_invariance_cppc(void) +{ + static bool init_done; + + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) + return; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + + mutex_lock(&freq_invariance_lock); + if (!init_done) + amd_set_max_freq_ratio(); + init_done = true; + mutex_unlock(&freq_invariance_lock); +} diff --git a/arch/x86/kernel/acpi/cppc_msr.c b/arch/x86/kernel/acpi/cppc_msr.c deleted file mode 100644 index b961de569e7e..000000000000 --- a/arch/x86/kernel/acpi/cppc_msr.c +++ /dev/null @@ -1,49 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * cppc_msr.c: MSR Interface for CPPC - * Copyright (c) 2016, Intel Corporation. - */ - -#include <acpi/cppc_acpi.h> -#include <asm/msr.h> - -/* Refer to drivers/acpi/cppc_acpi.c for the description of functions */ - -bool cpc_ffh_supported(void) -{ - return true; -} - -int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val) -{ - int err; - - err = rdmsrl_safe_on_cpu(cpunum, reg->address, val); - if (!err) { - u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, - reg->bit_offset); - - *val &= mask; - *val >>= reg->bit_offset; - } - return err; -} - -int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) -{ - u64 rd_val; - int err; - - err = rdmsrl_safe_on_cpu(cpunum, reg->address, &rd_val); - if (!err) { - u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, - reg->bit_offset); - - val <<= reg->bit_offset; - val &= mask; - rd_val &= ~mask; - rd_val |= val; - err = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val); - } - return err; -} diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index caf2edccbad2..7945eae5b315 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -79,6 +79,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, */ flags->bm_control = 0; } + if (c->x86_vendor == X86_VENDOR_AMD && c->x86 >= 0x17) { + /* + * For all AMD Zen or newer CPUs that support C3, caches + * should not be flushed by software while entering C3 + * type state. Set bm->check to 1 so that kernel doesn't + * need to execute cache flush operation. + */ + flags->bm_check = 1; + /* + * In current AMD C state implementation ARB_DIS is no longer + * used. So set bm_control to zero to indicate ARB_DIS is not + * required while entering C3 type state. + */ + flags->bm_control = 0; + } } EXPORT_SYMBOL(acpi_processor_power_init_bm_check); @@ -161,7 +176,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, /* Make sure we are running on right CPU */ - retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx); + retval = call_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx, + false); if (retval == 0) { /* Use the hint in CST */ percpu_entry->states[cx->index].eax = cx->address; @@ -196,7 +212,8 @@ static int __init ffh_cstate_init(void) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_INTEL && - c->x86_vendor != X86_VENDOR_AMD) + c->x86_vendor != X86_VENDOR_AMD && + c->x86_vendor != X86_VENDOR_HYGON) return -1; cpu_cstate_entry = alloc_percpu(struct cstate_entry); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 26b7256f590f..3b7f4cdbf2e0 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -10,11 +10,12 @@ #include <linux/memblock.h> #include <linux/dmi.h> #include <linux/cpumask.h> +#include <linux/pgtable.h> #include <asm/segment.h> #include <asm/desc.h> -#include <asm/pgtable.h> #include <asm/cacheflush.h> #include <asm/realmode.h> +#include <asm/hypervisor.h> #include <linux/ftrace.h> #include "../../realmode/rm/wakeup.h" @@ -41,9 +42,9 @@ unsigned long acpi_get_wakeup_address(void) * x86_acpi_enter_sleep_state - enter sleep state * @state: Sleep state to enter. * - * Wrapper around acpi_enter_sleep_state() to be called by assmebly. + * Wrapper around acpi_enter_sleep_state() to be called by assembly. */ -acpi_status asmlinkage __visible x86_acpi_enter_sleep_state(u8 state) +asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state) { return acpi_enter_sleep_state(state); } @@ -139,8 +140,10 @@ static int __init acpi_sleep_setup(char *str) if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; #ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_hwsig", 8) == 0) + acpi_check_s4_hw_signature = 1; if (strncmp(str, "s4_nohwsig", 10) == 0) - acpi_no_s4_hw_signature(); + acpi_check_s4_hw_signature = 0; #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); @@ -158,3 +161,21 @@ static int __init acpi_sleep_setup(char *str) } __setup("acpi_sleep=", acpi_sleep_setup); + +#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HYPERVISOR_GUEST) +static int __init init_s4_sigcheck(void) +{ + /* + * If running on a hypervisor, honour the ACPI specification + * by default and trigger a clean reboot when the hardware + * signature in FACS is changed after hibernation. + */ + if (acpi_check_s4_hw_signature == -1 && + !hypervisor_is_type(X86_HYPER_NATIVE)) + acpi_check_s4_hw_signature = 1; + + return 0; +} +/* This must happen before acpi_init() which is a subsys initcall */ +arch_initcall(init_s4_sigcheck); +#endif diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index d06c2079b6c1..171a40c74db6 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -19,4 +19,4 @@ extern void do_suspend_lowlevel(void); extern int x86_acpi_suspend_lowlevel(void); -acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state); +asmlinkage acpi_status x86_acpi_enter_sleep_state(u8 state); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index daf88f8143c5..cf69081073b5 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -60,7 +60,7 @@ save_registers: popl saved_context_eflags movl $ret_point, saved_eip - ret + RET restore_registers: @@ -70,7 +70,7 @@ restore_registers: movl saved_context_edi, %edi pushl saved_context_eflags popfl - ret + RET SYM_CODE_START(do_suspend_lowlevel) call save_processor_state @@ -86,7 +86,7 @@ SYM_CODE_START(do_suspend_lowlevel) ret_point: call restore_registers call restore_processor_state - ret + RET SYM_CODE_END(do_suspend_lowlevel) .data diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index c8daa92f38dc..d5d8a352eafa 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -1,12 +1,14 @@ /* SPDX-License-Identifier: GPL-2.0-only */ .text #include <linux/linkage.h> +#include <linux/objtool.h> #include <asm/segment.h> #include <asm/pgtable_types.h> #include <asm/page_types.h> #include <asm/msr.h> #include <asm/asm-offsets.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> # Copyright 2003 Pavel Machek <pavel@suse.cz @@ -39,6 +41,7 @@ SYM_FUNC_START(wakeup_long64) movq saved_rbp, %rbp movq saved_rip, %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax SYM_FUNC_END(wakeup_long64) @@ -112,7 +115,7 @@ SYM_FUNC_START(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) /* * The suspend path may have poisoned some areas deeper in the stack, * which we now need to unpoison. @@ -126,6 +129,7 @@ SYM_FUNC_START(do_suspend_lowlevel) FRAME_END jmp restore_processor_state SYM_FUNC_END(do_suspend_lowlevel) +STACK_FRAME_NON_STANDARD do_suspend_lowlevel .data saved_rbp: .quad 0 |