diff options
Diffstat (limited to 'arch/x86/kernel')
114 files changed, 5469 insertions, 7795 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9bcd0b56c..0f15af41b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -22,7 +22,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n CFLAGS_irq.o := -I$(src)/../include/asm/trace -obj-y := process_$(BITS).o signal.o entry_$(BITS).o +obj-y := process_$(BITS).o signal.o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o @@ -31,9 +31,6 @@ obj-y += probe_roms.o obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o -obj-y += syscall_$(BITS).o vsyscall_gtod.o -obj-$(CONFIG_IA32_EMULATION) += syscall_32.o -obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o @@ -44,7 +41,7 @@ obj-y += pci-iommu_table.o obj-y += resource.o obj-y += process.o -obj-y += i387.o xsave.o +obj-y += fpu/ obj-y += ptrace.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index bde7a2dc5..e49ee24da 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -31,12 +31,12 @@ #include <linux/module.h> #include <linux/dmi.h> #include <linux/irq.h> -#include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <asm/irqdomain.h> #include <asm/pci_x86.h> #include <asm/pgtable.h> #include <asm/io_apic.h> @@ -400,57 +400,13 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } -static int mp_register_gsi(struct device *dev, u32 gsi, int trigger, - int polarity) -{ - int irq, node; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; - - trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; - polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; - node = dev ? dev_to_node(dev) : NUMA_NO_NODE; - if (mp_set_gsi_attr(gsi, trigger, polarity, node)) { - pr_warn("Failed to set pin attr for GSI%d\n", gsi); - return -1; - } - - irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC); - if (irq < 0) - return irq; - - /* Don't set up the ACPI SCI because it's already set up */ - if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi) - mp_config_acpi_gsi(dev, gsi, trigger, polarity); - - return irq; -} - -static void mp_unregister_gsi(u32 gsi) -{ - int irq; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return; - - irq = mp_map_gsi_to_irq(gsi, 0); - if (irq > 0) - mp_unmap_irq(irq); -} - -static struct irq_domain_ops acpi_irqdomain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, -}; - static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_io_apic *ioapic = NULL; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_DYNAMIC, - .ops = &acpi_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; ioapic = (struct acpi_madt_io_apic *)header; @@ -652,7 +608,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi, * Make sure all (legacy) PCI IRQs are set as level-triggered. */ if (trigger == ACPI_LEVEL_SENSITIVE) - eisa_set_level_irq(gsi); + elcr_set_level_irq(gsi); #endif return gsi; @@ -663,10 +619,21 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int trigger, int polarity) { int irq = gsi; - #ifdef CONFIG_X86_IO_APIC + int node; + struct irq_alloc_info info; + + node = dev ? dev_to_node(dev) : NUMA_NO_NODE; + trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; + polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; + ioapic_set_alloc_attr(&info, node, trigger, polarity); + mutex_lock(&acpi_ioapic_lock); - irq = mp_register_gsi(dev, gsi, trigger, polarity); + irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); + /* Don't set up the ACPI SCI because it's already set up */ + if (irq >= 0 && enable_update_mptable && + acpi_gbl_FADT.sci_interrupt != gsi) + mp_config_acpi_gsi(dev, gsi, trigger, polarity); mutex_unlock(&acpi_ioapic_lock); #endif @@ -676,8 +643,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, static void acpi_unregister_gsi_ioapic(u32 gsi) { #ifdef CONFIG_X86_IO_APIC + int irq; + mutex_lock(&acpi_ioapic_lock); - mp_unregister_gsi(gsi); + irq = mp_map_gsi_to_irq(gsi, 0, NULL); + if (irq > 0) + mp_unmap_irq(irq); mutex_unlock(&acpi_ioapic_lock); #endif } @@ -786,7 +757,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) u64 addr; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_DYNAMIC, - .ops = &acpi_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr); @@ -1432,42 +1403,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), }, }, - /* ThinkPad Edge 11 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "254523U"), - }, - }, - /* ThinkPad Edge 13 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "022120U"), - }, - }, - /* ThinkPad Edge 14 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "019923U"), - }, - }, - /* ThinkPad Edge 15 (AMD) */ - { - .callback = dmi_ignore_irq0_timer_override, - .ident = "ThinkPad Edge", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "030222U"), - }, - }, {} }; diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 665c6b7d2..0c26b1b44 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -12,11 +12,13 @@ ENTRY(wakeup_pmode_return) wakeup_pmode_return: movw $__KERNEL_DS, %ax movw %ax, %ss - movw %ax, %ds - movw %ax, %es movw %ax, %fs movw %ax, %gs + movw $__USER_DS, %ax + movw %ax, %ds + movw %ax, %es + # reload the gdt, as we need the full 32 bit address lidt saved_idt lldt saved_ldt diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index ae693b51e..8c35df468 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -62,7 +62,7 @@ ENTRY(do_suspend_lowlevel) pushfq popq pt_regs_flags(%rax) - movq $resume_point, saved_rip(%rip) + movq $.Lresume_point, saved_rip(%rip) movq %rsp, saved_rsp movq %rbp, saved_rbp @@ -75,10 +75,10 @@ ENTRY(do_suspend_lowlevel) xorl %eax, %eax call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ - jmp resume_point + jmp .Lresume_point .align 4 -resume_point: +.Lresume_point: /* We don't restore %rax, it must be 0 anyway */ movq $saved_context, %rax movq saved_context_cr4(%rax), %rbx diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index aef653193..c42827eb8 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -21,6 +21,10 @@ #include <asm/io.h> #include <asm/fixmap.h> +int __read_mostly alternatives_patched; + +EXPORT_SYMBOL_GPL(alternatives_patched); + #define MAX_PATCH_LEN (255-1) static int __initdata_or_module debug_alternative; @@ -227,6 +231,15 @@ void __init arch_init_ideal_nops(void) #endif } break; + + case X86_VENDOR_AMD: + if (boot_cpu_data.x86 > 0xf) { + ideal_nops = p6_nops; + return; + } + + /* fall through */ + default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; @@ -627,6 +640,7 @@ void __init alternative_instructions(void) apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); + alternatives_patched = 1; } /** diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 5caed1dd7..29fa475ec 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -89,9 +89,7 @@ int amd_cache_northbridges(void) next_northbridge(link, amd_nb_link_ids); } - /* GART present only on Fam15h upto model 0fh */ - if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + if (amd_gart_present()) amd_northbridges.flags |= AMD_NB_GART; /* diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 6a7c23ff2..ede92c336 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -171,10 +171,6 @@ static int __init apbt_clockevent_register(void) static void apbt_setup_irq(struct apbt_dev *adev) { - /* timer0 irq has been setup early */ - if (adev->irq == 0) - return; - irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 76164e173..6e85f7136 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void) u64 aper_base = 0, last_aper_base = 0; int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; + if (!amd_gart_present()) + return; + if (!early_pci_allowed()) return; @@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void) int fix, slot, valid_agp = 0; int i, node; + if (!amd_gart_present()) + return -ENODEV; + if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) return -ENODEV; @@ -452,7 +458,7 @@ out: force_iommu || valid_agp || fallback_aper_force) { - pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Your BIOS doesn't leave an aperture memory hole\n"); pr_info("Please enable the IOMMU option in the BIOS setup\n"); pr_info("This costs you %dMB of RAM\n", 32 << fallback_aper_order); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index dcb52850a..cde732c1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1424,7 +1424,7 @@ static inline void __x2apic_disable(void) { u64 msr; - if (cpu_has_apic) + if (!cpu_has_apic) return; rdmsrl(MSR_IA32_APICBASE, msr); @@ -1483,10 +1483,13 @@ void x2apic_setup(void) static __init void x2apic_disable(void) { - u32 x2apic_id; + u32 x2apic_id, state = x2apic_state; - if (x2apic_state != X2APIC_ON) - goto out; + x2apic_mode = 0; + x2apic_state = X2APIC_DISABLED; + + if (state != X2APIC_ON) + return; x2apic_id = read_apic_id(); if (x2apic_id >= 255) @@ -1494,9 +1497,6 @@ static __init void x2apic_disable(void) __x2apic_disable(); register_lapic_address(mp_lapic_addr); -out: - x2apic_state = X2APIC_DISABLED; - x2apic_mode = 0; } static __init void x2apic_enable(void) diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c index 816f36e97..ae50d3454 100644 --- a/arch/x86/kernel/apic/htirq.c +++ b/arch/x86/kernel/apic/htirq.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Add support of hierarchical irqdomain * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -14,78 +16,112 @@ #include <linux/device.h> #include <linux/pci.h> #include <linux/htirq.h> +#include <asm/irqdomain.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/hypertransport.h> +static struct irq_domain *htirq_domain; + /* * Hypertransport interrupt support */ -static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) -{ - struct ht_irq_msg msg; - - fetch_ht_irq_msg(irq, &msg); - - msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK); - msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); - - msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest); - msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest); - - write_ht_irq_msg(irq, &msg); -} - static int ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest; + struct irq_data *parent = data->parent_data; int ret; - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - target_ht_irq(data->irq, dest, cfg->vector); - return IRQ_SET_MASK_OK_NOCOPY; + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0) { + struct ht_irq_msg msg; + struct irq_cfg *cfg = irqd_cfg(data); + + fetch_ht_irq_msg(data->irq, &msg); + msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | + HT_IRQ_LOW_DEST_ID_MASK); + msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) | + HT_IRQ_LOW_DEST_ID(cfg->dest_apicid); + msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); + msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); + write_ht_irq_msg(data->irq, &msg); + } + + return ret; } static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, - .irq_ack = apic_ack_edge, + .irq_ack = irq_chip_ack_parent, .irq_set_affinity = ht_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) +static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - struct irq_cfg *cfg; - struct ht_irq_msg msg; - unsigned dest; - int err; + struct ht_irq_cfg *ht_cfg; + struct irq_alloc_info *info = arg; + struct pci_dev *dev; + irq_hw_number_t hwirq; + int ret; - if (disable_apic) - return -ENXIO; + if (nr_irqs > 1 || !info) + return -EINVAL; - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + dev = info->ht_dev; + hwirq = (info->ht_idx & 0xFF) | + PCI_DEVID(dev->bus->number, dev->devfn) << 8 | + (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24; + if (irq_find_mapping(domain, hwirq) > 0) + return -EEXIST; - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; + ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL); + if (!ht_cfg) + return -ENOMEM; - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); + if (ret < 0) { + kfree(ht_cfg); + return ret; + } + + /* Initialize msg to a value that will never match the first write. */ + ht_cfg->msg.address_lo = 0xffffffff; + ht_cfg->msg.address_hi = 0xffffffff; + ht_cfg->dev = info->ht_dev; + ht_cfg->update = info->ht_update; + ht_cfg->pos = info->ht_pos; + ht_cfg->idx = 0x10 + (info->ht_idx * 2); + irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg, + handle_edge_irq, ht_cfg, "edge"); + + return 0; +} + +static void htirq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + BUG_ON(nr_irqs != 1); + kfree(irq_data->chip_data); + irq_domain_free_irqs_top(domain, virq, nr_irqs); +} +static void htirq_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct ht_irq_msg msg; + struct irq_cfg *cfg = irqd_cfg(irq_data); + + msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); msg.address_lo = HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) | HT_IRQ_LOW_VECTOR(cfg->vector) | ((apic->irq_dest_mode == 0) ? HT_IRQ_LOW_DM_PHYSICAL : @@ -95,13 +131,56 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) HT_IRQ_LOW_MT_FIXED : HT_IRQ_LOW_MT_ARBITRATED) | HT_IRQ_LOW_IRQ_MASKED; + write_ht_irq_msg(irq_data->irq, &msg); +} - write_ht_irq_msg(irq, &msg); +static void htirq_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct ht_irq_msg msg; - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + memset(&msg, 0, sizeof(msg)); + write_ht_irq_msg(irq_data->irq, &msg); +} - dev_dbg(&dev->dev, "irq %d for HT\n", irq); +static const struct irq_domain_ops htirq_domain_ops = { + .alloc = htirq_domain_alloc, + .free = htirq_domain_free, + .activate = htirq_domain_activate, + .deactivate = htirq_domain_deactivate, +}; - return 0; +void arch_init_htirq_domain(struct irq_domain *parent) +{ + if (disable_apic) + return; + + htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL); + if (!htirq_domain) + pr_warn("failed to initialize irqdomain for HTIRQ.\n"); + else + htirq_domain->parent = parent; +} + +int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, + ht_irq_update_t *update) +{ + struct irq_alloc_info info; + + if (!htirq_domain) + return -ENOSYS; + + init_irq_alloc_info(&info, NULL); + info.ht_idx = idx; + info.ht_pos = pos; + info.ht_dev = dev; + info.ht_update = update; + + return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev), + &info); +} + +void arch_teardown_ht_irq(unsigned int irq) +{ + irq_domain_free_irqs(irq, 1); } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index a72075cf2..206052e55 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -18,6 +18,16 @@ * and Rolf G. Tews * for testing these extensively * Paul Diefenbaugh : Added full ACPI support + * + * Historical information which is worth to be preserved: + * + * - SiS APIC rmw bug: + * + * We used to have a workaround for a bug in SiS chips which + * required to rewrite the index register for a read-modify-write + * operation as the chip lost the index information which was + * setup for the read already. We cache the data now, so that + * workaround has been removed. */ #include <linux/mm.h> @@ -31,13 +41,13 @@ #include <linux/acpi.h> #include <linux/module.h> #include <linux/syscore_ops.h> -#include <linux/irqdomain.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> #include <linux/bootmem.h> +#include <asm/irqdomain.h> #include <asm/idle.h> #include <asm/io.h> #include <asm/smp.h> @@ -63,27 +73,31 @@ #define for_each_ioapic_pin(idx, pin) \ for_each_ioapic((idx)) \ for_each_pin((idx), (pin)) - #define for_each_irq_pin(entry, head) \ list_for_each_entry(entry, &head, list) -/* - * Is the SiS APIC rmw bug present ? - * -1 = don't know, 0 = no, 1 = yes - */ -int sis_apic_bug = -1; - static DEFINE_RAW_SPINLOCK(ioapic_lock); static DEFINE_MUTEX(ioapic_mutex); static unsigned int ioapic_dynirq_base; static int ioapic_initialized; -struct mp_pin_info { +struct irq_pin_list { + struct list_head list; + int apic, pin; +}; + +struct mp_chip_data { + struct list_head irq_2_pin; + struct IO_APIC_route_entry entry; int trigger; int polarity; - int node; - int set; u32 count; + bool isa_irq; +}; + +struct mp_ioapic_gsi { + u32 gsi_base; + u32 gsi_end; }; static struct ioapic { @@ -101,7 +115,6 @@ static struct ioapic { struct mp_ioapic_gsi gsi_config; struct ioapic_domain_cfg irqdomain_cfg; struct irq_domain *irqdomain; - struct mp_pin_info *pin_info; struct resource *iomem_res; } ioapics[MAX_IO_APICS]; @@ -117,7 +130,7 @@ unsigned int mpc_ioapic_addr(int ioapic_idx) return ioapics[ioapic_idx].mp_config.apicaddr; } -struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) +static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) { return &ioapics[ioapic_idx].gsi_config; } @@ -129,11 +142,16 @@ static inline int mp_ioapic_pin_count(int ioapic) return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; } -u32 mp_pin_to_gsi(int ioapic, int pin) +static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin; } +static inline bool mp_is_legacy_irq(int irq) +{ + return irq >= 0 && irq < nr_legacy_irqs(); +} + /* * Initialize all legacy IRQs and all pins on the first IOAPIC * if we have legacy interrupt controller. Kernel boot option "pirq=" @@ -144,12 +162,7 @@ static inline int mp_init_irq_at_boot(int ioapic, int irq) if (!nr_legacy_irqs()) return 0; - return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs()); -} - -static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin) -{ - return ioapics[ioapic_idx].pin_info + pin; + return ioapic == 0 || mp_is_legacy_irq(irq); } static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic) @@ -216,16 +229,6 @@ void mp_save_irq(struct mpc_intsrc *m) panic("Max # of irq sources exceeded!!\n"); } -struct irq_pin_list { - struct list_head list; - int apic, pin; -}; - -static struct irq_pin_list *alloc_irq_pin_list(int node) -{ - return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node); -} - static void alloc_ioapic_saved_registers(int idx) { size_t size; @@ -247,8 +250,7 @@ static void free_ioapic_saved_registers(int idx) int __init arch_early_ioapic_init(void) { - struct irq_cfg *cfg; - int i, node = cpu_to_node(0); + int i; if (!nr_legacy_irqs()) io_apic_irqs = ~0UL; @@ -256,16 +258,6 @@ int __init arch_early_ioapic_init(void) for_each_ioapic(i) alloc_ioapic_saved_registers(i); - /* - * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. - */ - for (i = 0; i < nr_legacy_irqs(); i++) { - cfg = alloc_irq_and_cfg_at(i, node); - cfg->vector = IRQ0_VECTOR + i; - cpumask_setall(cfg->domain); - } - return 0; } @@ -283,7 +275,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mpc_ioapic_addr(idx) & ~PAGE_MASK); } -void io_apic_eoi(unsigned int apic, unsigned int vector) +static inline void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(vector, &io_apic->eoi); @@ -296,7 +288,8 @@ unsigned int native_io_apic_read(unsigned int apic, unsigned int reg) return readl(&io_apic->data); } -void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +static void io_apic_write(unsigned int apic, unsigned int reg, + unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -304,21 +297,6 @@ void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int valu writel(value, &io_apic->data); } -/* - * Re-write a value: to be used for read-modify-write - * cycles where the read already set up the index register. - * - * Older SiS APIC requires we rewrite the index register - */ -void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) -{ - struct io_apic __iomem *io_apic = io_apic_base(apic); - - if (sis_apic_bug) - writel(reg, &io_apic->index); - writel(value, &io_apic->data); -} - union entry_union { struct { u32 w1, w2; }; struct IO_APIC_route_entry entry; @@ -378,7 +356,7 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) static void ioapic_mask_entry(int apic, int pin) { unsigned long flags; - union entry_union eu = { .entry.mask = 1 }; + union entry_union eu = { .entry.mask = IOAPIC_MASKED }; raw_spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0x10 + 2*pin, eu.w1); @@ -391,16 +369,17 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static int __add_pin_to_irq_node(struct mp_chip_data *data, + int node, int apic, int pin) { struct irq_pin_list *entry; /* don't allow duplicates */ - for_each_irq_pin(entry, cfg->irq_2_pin) + for_each_irq_pin(entry, data->irq_2_pin) if (entry->apic == apic && entry->pin == pin) return 0; - entry = alloc_irq_pin_list(node); + entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node); if (!entry) { pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", node, apic, pin); @@ -408,16 +387,16 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi } entry->apic = apic; entry->pin = pin; + list_add_tail(&entry->list, &data->irq_2_pin); - list_add_tail(&entry->list, &cfg->irq_2_pin); return 0; } -static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) +static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) { struct irq_pin_list *tmp, *entry; - list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list) + list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list) if (entry->apic == apic && entry->pin == pin) { list_del(&entry->list); kfree(entry); @@ -425,22 +404,23 @@ static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) } } -static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static void add_pin_to_irq_node(struct mp_chip_data *data, + int node, int apic, int pin) { - if (__add_pin_to_irq_node(cfg, node, apic, pin)) + if (__add_pin_to_irq_node(data, node, apic, pin)) panic("IO-APIC: failed to add irq-pin. Can not proceed\n"); } /* * Reroute an IRQ to a different pin. */ -static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, +static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node, int oldapic, int oldpin, int newapic, int newpin) { struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, data->irq_2_pin) { if (entry->apic == oldapic && entry->pin == oldpin) { entry->apic = newapic; entry->pin = newpin; @@ -450,32 +430,26 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, } /* old apic/pin didn't exist, so just add new ones */ - add_pin_to_irq_node(cfg, node, newapic, newpin); + add_pin_to_irq_node(data, node, newapic, newpin); } -static void __io_apic_modify_irq(struct irq_pin_list *entry, - int mask_and, int mask_or, - void (*final)(struct irq_pin_list *entry)) -{ - unsigned int reg, pin; - - pin = entry->pin; - reg = io_apic_read(entry->apic, 0x10 + pin * 2); - reg &= mask_and; - reg |= mask_or; - io_apic_modify(entry->apic, 0x10 + pin * 2, reg); - if (final) - final(entry); -} - -static void io_apic_modify_irq(struct irq_cfg *cfg, +static void io_apic_modify_irq(struct mp_chip_data *data, int mask_and, int mask_or, void (*final)(struct irq_pin_list *entry)) { + union entry_union eu; struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) - __io_apic_modify_irq(entry, mask_and, mask_or, final); + eu.entry = data->entry; + eu.w1 &= mask_and; + eu.w1 |= mask_or; + data->entry = eu.entry; + + for_each_irq_pin(entry, data->irq_2_pin) { + io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1); + if (final) + final(entry); + } } static void io_apic_sync(struct irq_pin_list *entry) @@ -490,39 +464,31 @@ static void io_apic_sync(struct irq_pin_list *entry) readl(&io_apic->data); } -static void mask_ioapic(struct irq_cfg *cfg) +static void mask_ioapic_irq(struct irq_data *irq_data) { + struct mp_chip_data *data = irq_data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); + io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } -static void mask_ioapic_irq(struct irq_data *data) -{ - mask_ioapic(irqd_cfg(data)); -} - -static void __unmask_ioapic(struct irq_cfg *cfg) +static void __unmask_ioapic(struct mp_chip_data *data) { - io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL); + io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL); } -static void unmask_ioapic(struct irq_cfg *cfg) +static void unmask_ioapic_irq(struct irq_data *irq_data) { + struct mp_chip_data *data = irq_data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - __unmask_ioapic(cfg); + __unmask_ioapic(data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } -static void unmask_ioapic_irq(struct irq_data *data) -{ - unmask_ioapic(irqd_cfg(data)); -} - /* * IO-APIC versions below 0x20 don't support EOI register. * For the record, here is the information about various versions: @@ -539,7 +505,7 @@ static void unmask_ioapic_irq(struct irq_data *data) * Otherwise, we simulate the EOI message manually by changing the trigger * mode to edge and then back to level, with RTE being masked during this. */ -void native_eoi_ioapic_pin(int apic, int pin, int vector) +static void __eoi_ioapic_pin(int apic, int pin, int vector) { if (mpc_ioapic_ver(apic) >= 0x20) { io_apic_eoi(apic, vector); @@ -551,7 +517,7 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector) /* * Mask the entry and change the trigger mode to edge. */ - entry1.mask = 1; + entry1.mask = IOAPIC_MASKED; entry1.trigger = IOAPIC_EDGE; __ioapic_write_entry(apic, pin, entry1); @@ -563,15 +529,14 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector) } } -void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +void eoi_ioapic_pin(int vector, struct mp_chip_data *data) { - struct irq_pin_list *entry; unsigned long flags; + struct irq_pin_list *entry; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) - x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin, - cfg->vector); + for_each_irq_pin(entry, data->irq_2_pin) + __eoi_ioapic_pin(entry->apic, entry->pin, vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -588,8 +553,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * Make sure the entry is masked and re-read the contents to check * if it is a level triggered pin and if the remote-IRR is set. */ - if (!entry.mask) { - entry.mask = 1; + if (entry.mask == IOAPIC_UNMASKED) { + entry.mask = IOAPIC_MASKED; ioapic_write_entry(apic, pin, entry); entry = ioapic_read_entry(apic, pin); } @@ -602,13 +567,12 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * doesn't clear the remote-IRR if the trigger mode is not * set to level. */ - if (!entry.trigger) { + if (entry.trigger == IOAPIC_EDGE) { entry.trigger = IOAPIC_LEVEL; ioapic_write_entry(apic, pin, entry); } - raw_spin_lock_irqsave(&ioapic_lock, flags); - x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector); + __eoi_ioapic_pin(apic, pin, entry.vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -706,8 +670,8 @@ void mask_ioapic_entries(void) struct IO_APIC_route_entry entry; entry = ioapics[apic].saved_registers[pin]; - if (!entry.mask) { - entry.mask = 1; + if (entry.mask == IOAPIC_UNMASKED) { + entry.mask = IOAPIC_MASKED; ioapic_write_entry(apic, pin, entry); } } @@ -809,11 +773,11 @@ static int EISA_ELCR(unsigned int irq) #endif -/* ISA interrupts are always polarity zero edge triggered, +/* ISA interrupts are always active high edge triggered, * when listed as conforming in the MP table. */ -#define default_ISA_trigger(idx) (0) -#define default_ISA_polarity(idx) (0) +#define default_ISA_trigger(idx) (IOAPIC_EDGE) +#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH) /* EISA interrupts are always polarity zero and can be edge or level * trigger depending on the ELCR value. If an interrupt is listed as @@ -823,53 +787,55 @@ static int EISA_ELCR(unsigned int irq) #define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq)) #define default_EISA_polarity(idx) default_ISA_polarity(idx) -/* PCI interrupts are always polarity one level triggered, +/* PCI interrupts are always active low level triggered, * when listed as conforming in the MP table. */ -#define default_PCI_trigger(idx) (1) -#define default_PCI_polarity(idx) (1) +#define default_PCI_trigger(idx) (IOAPIC_LEVEL) +#define default_PCI_polarity(idx) (IOAPIC_POL_LOW) static int irq_polarity(int idx) { int bus = mp_irqs[idx].srcbus; - int polarity; /* * Determine IRQ line polarity (high active or low active): */ - switch (mp_irqs[idx].irqflag & 3) - { - case 0: /* conforms, ie. bus-type dependent polarity */ - if (test_bit(bus, mp_bus_not_pci)) - polarity = default_ISA_polarity(idx); - else - polarity = default_PCI_polarity(idx); - break; - case 1: /* high active */ - { - polarity = 0; - break; - } - case 2: /* reserved */ - { - pr_warn("broken BIOS!!\n"); - polarity = 1; - break; - } - case 3: /* low active */ - { - polarity = 1; - break; - } - default: /* invalid */ - { - pr_warn("broken BIOS!!\n"); - polarity = 1; - break; - } + switch (mp_irqs[idx].irqflag & 0x03) { + case 0: + /* conforms to spec, ie. bus-type dependent polarity */ + if (test_bit(bus, mp_bus_not_pci)) + return default_ISA_polarity(idx); + else + return default_PCI_polarity(idx); + case 1: + return IOAPIC_POL_HIGH; + case 2: + pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); + case 3: + default: /* Pointless default required due to do gcc stupidity */ + return IOAPIC_POL_LOW; + } +} + +#ifdef CONFIG_EISA +static int eisa_irq_trigger(int idx, int bus, int trigger) +{ + switch (mp_bus_id_to_type[bus]) { + case MP_BUS_PCI: + case MP_BUS_ISA: + return trigger; + case MP_BUS_EISA: + return default_EISA_trigger(idx); } - return polarity; + pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus); + return IOAPIC_LEVEL; +} +#else +static inline int eisa_irq_trigger(int idx, int bus, int trigger) +{ + return trigger; } +#endif static int irq_trigger(int idx) { @@ -879,153 +845,227 @@ static int irq_trigger(int idx) /* * Determine IRQ trigger mode (edge or level sensitive): */ - switch ((mp_irqs[idx].irqflag>>2) & 3) - { - case 0: /* conforms, ie. bus-type dependent */ - if (test_bit(bus, mp_bus_not_pci)) - trigger = default_ISA_trigger(idx); - else - trigger = default_PCI_trigger(idx); -#ifdef CONFIG_EISA - switch (mp_bus_id_to_type[bus]) { - case MP_BUS_ISA: /* ISA pin */ - { - /* set before the switch */ - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* set before the switch */ - break; - } - default: - { - pr_warn("broken BIOS!!\n"); - trigger = 1; - break; - } - } + switch ((mp_irqs[idx].irqflag >> 2) & 0x03) { + case 0: + /* conforms to spec, ie. bus-type dependent trigger mode */ + if (test_bit(bus, mp_bus_not_pci)) + trigger = default_ISA_trigger(idx); + else + trigger = default_PCI_trigger(idx); + /* Take EISA into account */ + return eisa_irq_trigger(idx, bus, trigger); + case 1: + return IOAPIC_EDGE; + case 2: + pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); + case 3: + default: /* Pointless default required due to do gcc stupidity */ + return IOAPIC_LEVEL; + } +} + +void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node, + int trigger, int polarity) +{ + init_irq_alloc_info(info, NULL); + info->type = X86_IRQ_ALLOC_TYPE_IOAPIC; + info->ioapic_node = node; + info->ioapic_trigger = trigger; + info->ioapic_polarity = polarity; + info->ioapic_valid = 1; +} + +#ifndef CONFIG_ACPI +int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #endif - break; - case 1: /* edge */ - { - trigger = 0; - break; - } - case 2: /* reserved */ - { - pr_warn("broken BIOS!!\n"); - trigger = 1; - break; - } - case 3: /* level */ - { - trigger = 1; - break; - } - default: /* invalid */ - { - pr_warn("broken BIOS!!\n"); - trigger = 0; - break; + +static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, + struct irq_alloc_info *src, + u32 gsi, int ioapic_idx, int pin) +{ + int trigger, polarity; + + copy_irq_alloc_info(dst, src); + dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC; + dst->ioapic_id = mpc_ioapic_id(ioapic_idx); + dst->ioapic_pin = pin; + dst->ioapic_valid = 1; + if (src && src->ioapic_valid) { + dst->ioapic_node = src->ioapic_node; + dst->ioapic_trigger = src->ioapic_trigger; + dst->ioapic_polarity = src->ioapic_polarity; + } else { + dst->ioapic_node = NUMA_NO_NODE; + if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) { + dst->ioapic_trigger = trigger; + dst->ioapic_polarity = polarity; + } else { + /* + * PCI interrupts are always active low level + * triggered. + */ + dst->ioapic_trigger = IOAPIC_LEVEL; + dst->ioapic_polarity = IOAPIC_POL_LOW; } } - return trigger; } -static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin) +static int ioapic_alloc_attr_node(struct irq_alloc_info *info) { + return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE; +} + +static void mp_register_handler(unsigned int irq, unsigned long trigger) +{ + irq_flow_handler_t hdl; + bool fasteoi; + + if (trigger) { + irq_set_status_flags(irq, IRQ_LEVEL); + fasteoi = true; + } else { + irq_clear_status_flags(irq, IRQ_LEVEL); + fasteoi = false; + } + + hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; + __irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge"); +} + +static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) +{ + struct mp_chip_data *data = irq_get_chip_data(irq); + + /* + * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger + * and polarity attirbutes. So allow the first user to reprogram the + * pin with real trigger and polarity attributes. + */ + if (irq < nr_legacy_irqs() && data->count == 1) { + if (info->ioapic_trigger != data->trigger) + mp_register_handler(irq, info->ioapic_trigger); + data->entry.trigger = data->trigger = info->ioapic_trigger; + data->entry.polarity = data->polarity = info->ioapic_polarity; + } + + return data->trigger == info->ioapic_trigger && + data->polarity == info->ioapic_polarity; +} + +static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, + struct irq_alloc_info *info) +{ + bool legacy = false; int irq = -1; - int ioapic = (int)(long)domain->host_data; int type = ioapics[ioapic].irqdomain_cfg.type; switch (type) { case IOAPIC_DOMAIN_LEGACY: /* - * Dynamically allocate IRQ number for non-ISA IRQs in the first 16 - * GSIs on some weird platforms. + * Dynamically allocate IRQ number for non-ISA IRQs in the first + * 16 GSIs on some weird platforms. */ - if (gsi < nr_legacy_irqs()) - irq = irq_create_mapping(domain, pin); - else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) + if (!ioapic_initialized || gsi >= nr_legacy_irqs()) irq = gsi; + legacy = mp_is_legacy_irq(irq); break; case IOAPIC_DOMAIN_STRICT: - if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) - irq = gsi; + irq = gsi; break; case IOAPIC_DOMAIN_DYNAMIC: - irq = irq_create_mapping(domain, pin); break; default: WARN(1, "ioapic: unknown irqdomain type %d\n", type); - break; + return -1; } - return irq > 0 ? irq : -1; + return __irq_domain_alloc_irqs(domain, irq, 1, + ioapic_alloc_attr_node(info), + info, legacy); +} + +/* + * Need special handling for ISA IRQs because there may be multiple IOAPIC pins + * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping + * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are + * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). + * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and + * some BIOSes may use MP Interrupt Source records to override IRQ numbers for + * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be + * multiple pins sharing the same legacy IRQ number when ACPI is disabled. + */ +static int alloc_isa_irq_from_domain(struct irq_domain *domain, + int irq, int ioapic, int pin, + struct irq_alloc_info *info) +{ + struct mp_chip_data *data; + struct irq_data *irq_data = irq_get_irq_data(irq); + int node = ioapic_alloc_attr_node(info); + + /* + * Legacy ISA IRQ has already been allocated, just add pin to + * the pin list assoicated with this IRQ and program the IOAPIC + * entry. The IOAPIC entry + */ + if (irq_data && irq_data->parent_data) { + if (!mp_check_pin_attr(irq, info)) + return -EBUSY; + if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, + info->ioapic_pin)) + return -ENOMEM; + } else { + irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true); + if (irq >= 0) { + irq_data = irq_domain_get_irq_data(domain, irq); + data = irq_data->chip_data; + data->isa_irq = true; + } + } + + return irq; } static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, - unsigned int flags) + unsigned int flags, struct irq_alloc_info *info) { int irq; + bool legacy = false; + struct irq_alloc_info tmp; + struct mp_chip_data *data; struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); - struct mp_pin_info *info = mp_pin_info(ioapic, pin); if (!domain) - return -1; - - mutex_lock(&ioapic_mutex); + return -ENOSYS; - /* - * Don't use irqdomain to manage ISA IRQs because there may be - * multiple IOAPIC pins sharing the same ISA IRQ number and - * irqdomain only supports 1:1 mapping between IOAPIC pin and - * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used - * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). - * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are - * available, and some BIOSes may use MP Interrupt Source records - * to override IRQ numbers for PIRQs instead of reprogramming - * the interrupt routing logic. Thus there may be multiple pins - * sharing the same legacy IRQ number when ACPI is disabled. - */ if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; - if (flags & IOAPIC_MAP_ALLOC) { - if (info->count == 0 && - mp_irqdomain_map(domain, irq, pin) != 0) - irq = -1; + legacy = mp_is_legacy_irq(irq); + } - /* special handling for timer IRQ0 */ + mutex_lock(&ioapic_mutex); + if (!(flags & IOAPIC_MAP_ALLOC)) { + if (!legacy) { + irq = irq_find_mapping(domain, pin); if (irq == 0) - info->count++; + irq = -ENOENT; } } else { - irq = irq_find_mapping(domain, pin); - if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC)) - irq = alloc_irq_from_domain(domain, gsi, pin); - } - - if (flags & IOAPIC_MAP_ALLOC) { - /* special handling for legacy IRQs */ - if (irq < nr_legacy_irqs() && info->count == 1 && - mp_irqdomain_map(domain, irq, pin) != 0) - irq = -1; - - if (irq > 0) - info->count++; - else if (info->count == 0) - info->set = 0; + ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin); + if (legacy) + irq = alloc_isa_irq_from_domain(domain, irq, + ioapic, pin, &tmp); + else if ((irq = irq_find_mapping(domain, pin)) == 0) + irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp); + else if (!mp_check_pin_attr(irq, &tmp)) + irq = -EBUSY; + if (irq >= 0) { + data = irq_get_chip_data(irq); + data->count++; + } } - mutex_unlock(&ioapic_mutex); - return irq > 0 ? irq : -1; + return irq; } static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) @@ -1058,10 +1098,10 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) } #endif - return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL); } -int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) +int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info) { int ioapic, pin, idx; @@ -1074,31 +1114,24 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) if ((flags & IOAPIC_MAP_CHECK) && idx < 0) return -1; - return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info); } void mp_unmap_irq(int irq) { - struct irq_data *data = irq_get_irq_data(irq); - struct mp_pin_info *info; - int ioapic, pin; + struct irq_data *irq_data = irq_get_irq_data(irq); + struct mp_chip_data *data; - if (!data || !data->domain) + if (!irq_data || !irq_data->domain) return; - ioapic = (int)(long)data->domain->host_data; - pin = (int)data->hwirq; - info = mp_pin_info(ioapic, pin); + data = irq_data->chip_data; + if (!data || data->isa_irq) + return; mutex_lock(&ioapic_mutex); - if (--info->count == 0) { - info->set = 0; - if (irq < nr_legacy_irqs() && - ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY) - mp_irqdomain_unmap(data->domain, irq); - else - irq_dispose_mapping(irq); - } + if (--data->count == 0) + irq_domain_free_irqs(irq, 1); mutex_unlock(&ioapic_mutex); } @@ -1165,7 +1198,7 @@ out: } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); -static struct irq_chip ioapic_chip; +static struct irq_chip ioapic_chip, ioapic_ir_chip; #ifdef CONFIG_X86_32 static inline int IO_APIC_irq_trigger(int irq) @@ -1189,96 +1222,6 @@ static inline int IO_APIC_irq_trigger(int irq) } #endif -static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, - unsigned long trigger) -{ - struct irq_chip *chip = &ioapic_chip; - irq_flow_handler_t hdl; - bool fasteoi; - - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) { - irq_set_status_flags(irq, IRQ_LEVEL); - fasteoi = true; - } else { - irq_clear_status_flags(irq, IRQ_LEVEL); - fasteoi = false; - } - - if (setup_remapped_irq(irq, cfg, chip)) - fasteoi = trigger != 0; - - hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; - irq_set_chip_and_handler_name(irq, chip, hdl, - fasteoi ? "fasteoi" : "edge"); -} - -int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr) -{ - memset(entry, 0, sizeof(*entry)); - - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->dest = destination; - entry->vector = vector; - entry->mask = 0; /* enable IRQ */ - entry->trigger = attr->trigger; - entry->polarity = attr->polarity; - - /* - * Mask level triggered irqs. - * Use IRQ_DELAYED_DISABLE for edge triggered irqs. - */ - if (attr->trigger) - entry->mask = 1; - - return 0; -} - -static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, - struct io_apic_irq_attr *attr) -{ - struct IO_APIC_route_entry entry; - unsigned int dest; - - if (!IO_APIC_IRQ(irq)) - return; - - if (assign_irq_vector(irq, cfg, apic->target_cpus())) - return; - - if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), - &dest)) { - pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", - mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - clear_irq_vector(irq, cfg); - - return; - } - - apic_printk(APIC_VERBOSE,KERN_DEBUG - "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " - "IRQ %d Mode:%i Active:%i Dest:%d)\n", - attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, - cfg->vector, irq, attr->trigger, attr->polarity, dest); - - if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", - mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - clear_irq_vector(irq, cfg); - - return; - } - - ioapic_register_intr(irq, cfg, attr->trigger); - if (irq < nr_legacy_irqs()) - legacy_pic->mask(irq); - - ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry); -} - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; @@ -1298,106 +1241,41 @@ static void __init setup_IO_APIC_irqs(void) } } -/* - * Set up the timer pin, possibly with the 8259A-master behind. - */ -static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, - unsigned int pin, int vector) -{ - struct IO_APIC_route_entry entry; - unsigned int dest; - - memset(&entry, 0, sizeof(entry)); - - /* - * We use logical delivery to get the timer IRQ - * to the first CPU. - */ - if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(), - apic->target_cpus(), &dest))) - dest = BAD_APICID; - - entry.dest_mode = apic->irq_dest_mode; - entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = dest; - entry.delivery_mode = apic->irq_delivery_mode; - entry.polarity = 0; - entry.trigger = 0; - entry.vector = vector; - - /* - * The timer IRQ doesn't have to know that behind the - * scene we may have a 8259A-master in AEOI mode ... - */ - irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, - "edge"); - - /* - * Add it to the IO-APIC irq-routing table: - */ - ioapic_write_entry(ioapic_idx, pin, entry); -} - -void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries) +void ioapic_zap_locks(void) { - int i; - - pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n"); - - for (i = 0; i <= nr_entries; i++) { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(apic, i); - - pr_debug(" %02x %02X ", i, entry.dest); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector); - } + raw_spin_lock_init(&ioapic_lock); } -void intel_ir_io_apic_print_entries(unsigned int apic, - unsigned int nr_entries) +static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) { int i; + char buf[256]; + struct IO_APIC_route_entry entry; + struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry; - pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n"); - + printk(KERN_DEBUG "IOAPIC %d:\n", apic); for (i = 0; i <= nr_entries; i++) { - struct IR_IO_APIC_route_entry *ir_entry; - struct IO_APIC_route_entry entry; - entry = ioapic_read_entry(apic, i); - - ir_entry = (struct IR_IO_APIC_route_entry *)&entry; - - pr_debug(" %02x %04X ", i, ir_entry->index); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %X %02X\n", - ir_entry->format, - ir_entry->mask, - ir_entry->trigger, - ir_entry->irr, - ir_entry->polarity, - ir_entry->delivery_status, - ir_entry->index2, - ir_entry->zero, - ir_entry->vector); + snprintf(buf, sizeof(buf), + " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)", + i, + entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ", + entry.trigger == IOAPIC_LEVEL ? "level" : "edge ", + entry.polarity == IOAPIC_POL_LOW ? "low " : "high", + entry.vector, entry.irr, entry.delivery_status); + if (ir_entry->format) + printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", + buf, (ir_entry->index << 15) | ir_entry->index, + ir_entry->zero); + else + printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", + buf, + entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ? + "logical " : "physical", + entry.dest, entry.delivery_mode); } } -void ioapic_zap_locks(void) -{ - raw_spin_lock_init(&ioapic_lock); -} - static void __init print_IO_APIC(int ioapic_idx) { union IO_APIC_reg_00 reg_00; @@ -1451,16 +1329,13 @@ static void __init print_IO_APIC(int ioapic_idx) } printk(KERN_DEBUG ".... IRQ redirection table:\n"); - - x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); + io_apic_print_entries(ioapic_idx, reg_01.bits.entries); } void __init print_IO_APICs(void) { int ioapic_idx; - struct irq_cfg *cfg; unsigned int irq; - struct irq_chip *chip; printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for_each_ioapic(ioapic_idx) @@ -1480,18 +1355,20 @@ void __init print_IO_APICs(void) printk(KERN_DEBUG "IRQ to pin mappings:\n"); for_each_active_irq(irq) { struct irq_pin_list *entry; + struct irq_chip *chip; + struct mp_chip_data *data; chip = irq_get_chip(irq); - if (chip != &ioapic_chip) + if (chip != &ioapic_chip && chip != &ioapic_ir_chip) continue; - - cfg = irq_cfg(irq); - if (!cfg) + data = irq_get_chip_data(irq); + if (!data) continue; - if (list_empty(&cfg->irq_2_pin)) + if (list_empty(&data->irq_2_pin)) continue; + printk(KERN_DEBUG "IRQ%d ", irq); - for_each_irq_pin(entry, cfg->irq_2_pin) + for_each_irq_pin(entry, data->irq_2_pin) pr_cont("-> %d:%d", entry->apic, entry->pin); pr_cont("\n"); } @@ -1564,15 +1441,12 @@ void native_disable_io_apic(void) struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); - entry.mask = 0; /* Enabled */ - entry.trigger = 0; /* Edge */ - entry.irr = 0; - entry.polarity = 0; /* High */ - entry.delivery_status = 0; - entry.dest_mode = 0; /* Physical */ - entry.delivery_mode = dest_ExtINT; /* ExtInt */ - entry.vector = 0; - entry.dest = read_apic_id(); + entry.mask = IOAPIC_UNMASKED; + entry.trigger = IOAPIC_EDGE; + entry.polarity = IOAPIC_POL_HIGH; + entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; + entry.delivery_mode = dest_ExtINT; + entry.dest = read_apic_id(); /* * Add it to the IO-APIC irq-routing table: @@ -1582,7 +1456,6 @@ void native_disable_io_apic(void) if (cpu_has_apic || apic_from_smp_config()) disconnect_bsp_APIC(ioapic_i8259.pin != -1); - } /* @@ -1792,7 +1665,6 @@ static int __init timer_irq_works(void) * This is not complete - we should be able to fake * an edge even if it isn't on the 8259A... */ - static unsigned int startup_ioapic_irq(struct irq_data *data) { int was_pending = 0, irq = data->irq; @@ -1804,74 +1676,22 @@ static unsigned int startup_ioapic_irq(struct irq_data *data) if (legacy_pic->irq_pending(irq)) was_pending = 1; } - __unmask_ioapic(irqd_cfg(data)); + __unmask_ioapic(data->chip_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return was_pending; } -/* - * Level and edge triggered IO-APIC interrupts need different handling, - * so we use two separate IRQ descriptors. Edge triggered IRQs can be - * handled with the level-triggered descriptor, but that one has slightly - * more overhead. Level-triggered interrupts cannot be handled with the - * edge-triggered handler, without risking IRQ storms and other ugly - * races. - */ - -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -int native_ioapic_set_affinity(struct irq_data *data, - const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - if (!config_enabled(CONFIG_SMP)) - return -EPERM; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = apic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, irqd_cfg(data)); - ret = IRQ_SET_MASK_OK_NOCOPY; - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return ret; -} - atomic_t irq_mis_count; #ifdef CONFIG_GENERIC_PENDING_IRQ -static bool io_apic_level_ack_pending(struct irq_cfg *cfg) +static bool io_apic_level_ack_pending(struct mp_chip_data *data) { struct irq_pin_list *entry; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, data->irq_2_pin) { unsigned int reg; int pin; @@ -1888,18 +1708,17 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) return false; } -static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +static inline bool ioapic_irqd_mask(struct irq_data *data) { /* If we are moving the irq we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic(cfg); + mask_ioapic_irq(data); return true; } return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, - struct irq_cfg *cfg, bool masked) +static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) { if (unlikely(masked)) { /* Only migrate the irq if the ack has been received. @@ -1928,31 +1747,30 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, * accurate and is causing problems then it is a hardware bug * and you can go talk to the chipset vendor about it. */ - if (!io_apic_level_ack_pending(cfg)) + if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic(cfg); + unmask_ioapic_irq(data); } } #else -static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +static inline bool ioapic_irqd_mask(struct irq_data *data) { return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, - struct irq_cfg *cfg, bool masked) +static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) { } #endif -static void ack_ioapic_level(struct irq_data *data) +static void ioapic_ack_level(struct irq_data *irq_data) { - struct irq_cfg *cfg = irqd_cfg(data); - int i, irq = data->irq; + struct irq_cfg *cfg = irqd_cfg(irq_data); unsigned long v; bool masked; + int i; irq_complete_move(cfg); - masked = ioapic_irqd_mask(data, cfg); + masked = ioapic_irqd_mask(irq_data); /* * It appears there is an erratum which affects at least version 0x11 @@ -2004,11 +1822,49 @@ static void ack_ioapic_level(struct irq_data *data) */ if (!(v & (1 << (i & 0x1f)))) { atomic_inc(&irq_mis_count); + eoi_ioapic_pin(cfg->vector, irq_data->chip_data); + } + + ioapic_irqd_unmask(irq_data, masked); +} + +static void ioapic_ir_ack_level(struct irq_data *irq_data) +{ + struct mp_chip_data *data = irq_data->chip_data; - eoi_ioapic_irq(irq, cfg); + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + ack_APIC_irq(); + eoi_ioapic_pin(data->entry.vector, data); +} + +static int ioapic_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = irq_data->parent_data; + struct mp_chip_data *data = irq_data->chip_data; + struct irq_pin_list *entry; + struct irq_cfg *cfg; + unsigned long flags; + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + raw_spin_lock_irqsave(&ioapic_lock, flags); + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { + cfg = irqd_cfg(irq_data); + data->entry.dest = cfg->dest_apicid; + data->entry.vector = cfg->vector; + for_each_irq_pin(entry, data->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, + data->entry); } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); - ioapic_irqd_unmask(data, cfg, masked); + return ret; } static struct irq_chip ioapic_chip __read_mostly = { @@ -2016,10 +1872,20 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_startup = startup_ioapic_irq, .irq_mask = mask_ioapic_irq, .irq_unmask = unmask_ioapic_irq, - .irq_ack = apic_ack_edge, - .irq_eoi = ack_ioapic_level, - .irq_set_affinity = native_ioapic_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_ack = irq_chip_ack_parent, + .irq_eoi = ioapic_ack_level, + .irq_set_affinity = ioapic_set_affinity, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static struct irq_chip ioapic_ir_chip __read_mostly = { + .name = "IR-IO-APIC", + .irq_startup = startup_ioapic_irq, + .irq_mask = mask_ioapic_irq, + .irq_unmask = unmask_ioapic_irq, + .irq_ack = irq_chip_ack_parent, + .irq_eoi = ioapic_ir_ack_level, + .irq_set_affinity = ioapic_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -2113,12 +1979,12 @@ static inline void __init unlock_ExtINT_logic(void) memset(&entry1, 0, sizeof(entry1)); - entry1.dest_mode = 0; /* physical delivery */ - entry1.mask = 0; /* unmask IRQ now */ + entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; + entry1.mask = IOAPIC_UNMASKED; entry1.dest = hard_smp_processor_id(); entry1.delivery_mode = dest_ExtINT; entry1.polarity = entry0.polarity; - entry1.trigger = 0; + entry1.trigger = IOAPIC_EDGE; entry1.vector = 0; ioapic_write_entry(apic, pin, entry1); @@ -2152,6 +2018,25 @@ static int __init disable_timer_pin_setup(char *arg) } early_param("disable_timer_pin_1", disable_timer_pin_setup); +static int mp_alloc_timer_irq(int ioapic, int pin) +{ + int irq = -1; + struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); + + if (domain) { + struct irq_alloc_info info; + + ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0); + info.ioapic_id = mpc_ioapic_id(ioapic); + info.ioapic_pin = pin; + mutex_lock(&ioapic_mutex); + irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info); + mutex_unlock(&ioapic_mutex); + } + + return irq; +} + /* * This code may look a bit paranoid, but it's supposed to cooperate with * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ @@ -2162,7 +2047,9 @@ early_param("disable_timer_pin_1", disable_timer_pin_setup); */ static inline void __init check_timer(void) { - struct irq_cfg *cfg = irq_cfg(0); + struct irq_data *irq_data = irq_get_irq_data(0); + struct mp_chip_data *data = irq_data->chip_data; + struct irq_cfg *cfg = irqd_cfg(irq_data); int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; unsigned long flags; @@ -2174,7 +2061,6 @@ static inline void __init check_timer(void) * get/set the timer IRQ vector: */ legacy_pic->mask(0); - assign_irq_vector(0, cfg, apic->target_cpus()); /* * As IRQ0 is to be enabled in the 8259A, the virtual @@ -2215,23 +2101,21 @@ static inline void __init check_timer(void) } if (pin1 != -1) { - /* - * Ok, does IRQ0 through the IOAPIC work? - */ + /* Ok, does IRQ0 through the IOAPIC work? */ if (no_pin1) { - add_pin_to_irq_node(cfg, node, apic1, pin1); - setup_timer_IRQ0_pin(apic1, pin1, cfg->vector); + mp_alloc_timer_irq(apic1, pin1); } else { - /* for edge trigger, setup_ioapic_irq already - * leave it unmasked. + /* + * for edge trigger, it's already unmasked, * so only need to unmask if it is level-trigger * do we really have level trigger timer? */ int idx; idx = find_irq_entry(apic1, pin1, mp_INT); if (idx != -1 && irq_trigger(idx)) - unmask_ioapic(cfg); + unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); @@ -2251,8 +2135,8 @@ static inline void __init check_timer(void) /* * legacy devices should be connected to IO APIC #0 */ - replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2); - setup_timer_IRQ0_pin(apic2, pin2, cfg->vector); + replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); @@ -2329,36 +2213,35 @@ out: static int mp_irqdomain_create(int ioapic) { - size_t size; + struct irq_alloc_info info; + struct irq_domain *parent; int hwirqs = mp_ioapic_pin_count(ioapic); struct ioapic *ip = &ioapics[ioapic]; struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); - size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic); - ip->pin_info = kzalloc(size, GFP_KERNEL); - if (!ip->pin_info) - return -ENOMEM; - if (cfg->type == IOAPIC_DOMAIN_INVALID) return 0; + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_IOAPIC; + info.ioapic_id = mpc_ioapic_id(ioapic); + parent = irq_remapping_get_ir_irq_domain(&info); + if (!parent) + parent = x86_vector_domain; + ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops, (void *)(long)ioapic); - if(!ip->irqdomain) { - kfree(ip->pin_info); - ip->pin_info = NULL; + if (!ip->irqdomain) return -ENOMEM; - } + + ip->irqdomain->parent = parent; if (cfg->type == IOAPIC_DOMAIN_LEGACY || cfg->type == IOAPIC_DOMAIN_STRICT) ioapic_dynirq_base = max(ioapic_dynirq_base, gsi_cfg->gsi_end + 1); - if (gsi_cfg->gsi_base == 0) - irq_set_default_host(ip->irqdomain); - return 0; } @@ -2368,8 +2251,6 @@ static void ioapic_destroy_irqdomain(int idx) irq_domain_remove(ioapics[idx].irqdomain); ioapics[idx].irqdomain = NULL; } - kfree(ioapics[idx].pin_info); - ioapics[idx].pin_info = NULL; } void __init setup_IO_APIC(void) @@ -2399,20 +2280,6 @@ void __init setup_IO_APIC(void) ioapic_initialized = 1; } -/* - * Called after all the initialization is done. If we didn't find any - * APIC bugs then we can allow the modify fast path - */ - -static int __init io_apic_bug_finalize(void) -{ - if (sis_apic_bug == -1) - sis_apic_bug = 0; - return 0; -} - -late_initcall(io_apic_bug_finalize); - static void resume_ioapic_id(int ioapic_idx) { unsigned long flags; @@ -2451,20 +2318,6 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); -static int -io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) -{ - struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node); - int ret; - - if (!cfg) - return -EINVAL; - ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin); - if (!ret) - setup_ioapic_irq(irq, cfg, attr); - return ret; -} - static int io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; @@ -2638,11 +2491,6 @@ int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { int ioapic, pin, idx; -#ifdef CONFIG_ACPI - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return -1; -#endif - if (skip_ioapic_setup) return -1; @@ -2697,7 +2545,7 @@ void __init setup_ioapic_dest(void) else mask = apic->target_cpus(); - x86_io_apic_ops.set_affinity(idata, mask, false); + irq_set_affinity(irq, mask); } } @@ -2742,7 +2590,7 @@ static struct resource * __init ioapic_setup_resources(void) return res; } -void __init native_io_apic_init_mappings(void) +void __init io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; struct resource *ioapic_res; @@ -2967,7 +2815,6 @@ int mp_unregister_ioapic(u32 gsi_base) { int ioapic, pin; int found = 0; - struct mp_pin_info *pin_info; for_each_ioapic(ioapic) if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) { @@ -2980,11 +2827,17 @@ int mp_unregister_ioapic(u32 gsi_base) } for_each_pin(ioapic, pin) { - pin_info = mp_pin_info(ioapic, pin); - if (pin_info->count) { - pr_warn("pin%d on IOAPIC%d is still in use.\n", - pin, ioapic); - return -EBUSY; + u32 gsi = mp_pin_to_gsi(ioapic, pin); + int irq = mp_map_gsi_to_irq(gsi, 0, NULL); + struct mp_chip_data *data; + + if (irq >= 0) { + data = irq_get_chip_data(irq); + if (data && data->count) { + pr_warn("pin%d on IOAPIC%d is still in use.\n", + pin, ioapic); + return -EBUSY; + } } } @@ -3011,108 +2864,141 @@ int mp_ioapic_registered(u32 gsi_base) return 0; } -static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr, - int ioapic, int ioapic_pin, - int trigger, int polarity) +static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, + struct irq_alloc_info *info) { - irq_attr->ioapic = ioapic; - irq_attr->ioapic_pin = ioapic_pin; - irq_attr->trigger = trigger; - irq_attr->polarity = polarity; + if (info && info->ioapic_valid) { + data->trigger = info->ioapic_trigger; + data->polarity = info->ioapic_polarity; + } else if (acpi_get_override_irq(gsi, &data->trigger, + &data->polarity) < 0) { + /* PCI interrupts are always active low level triggered. */ + data->trigger = IOAPIC_LEVEL; + data->polarity = IOAPIC_POL_LOW; + } } -int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, + struct IO_APIC_route_entry *entry) { - int ioapic = (int)(long)domain->host_data; - struct mp_pin_info *info = mp_pin_info(ioapic, hwirq); - struct io_apic_irq_attr attr; + memset(entry, 0, sizeof(*entry)); + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->dest = cfg->dest_apicid; + entry->vector = cfg->vector; + entry->trigger = data->trigger; + entry->polarity = data->polarity; + /* + * Mask level triggered irqs. Edge triggered irqs are masked + * by the irq core code in case they fire. + */ + if (data->trigger == IOAPIC_LEVEL) + entry->mask = IOAPIC_MASKED; + else + entry->mask = IOAPIC_UNMASKED; +} - /* Get default attribute if not set by caller yet */ - if (!info->set) { - u32 gsi = mp_pin_to_gsi(ioapic, hwirq); +int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + int ret, ioapic, pin; + struct irq_cfg *cfg; + struct irq_data *irq_data; + struct mp_chip_data *data; + struct irq_alloc_info *info = arg; - if (acpi_get_override_irq(gsi, &info->trigger, - &info->polarity) < 0) { - /* - * PCI interrupts are always polarity one level - * triggered. - */ - info->trigger = 1; - info->polarity = 1; - } - info->node = NUMA_NO_NODE; + if (!info || nr_irqs > 1) + return -EINVAL; + irq_data = irq_domain_get_irq_data(domain, virq); + if (!irq_data) + return -EINVAL; - /* - * setup_IO_APIC_irqs() programs all legacy IRQs with default - * trigger and polarity attributes. Don't set the flag for that - * case so the first legacy IRQ user could reprogram the pin - * with real trigger and polarity attributes. - */ - if (virq >= nr_legacy_irqs() || info->count) - info->set = 1; - } - set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger, - info->polarity); + ioapic = mp_irqdomain_ioapic_idx(domain); + pin = info->ioapic_pin; + if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0) + return -EEXIST; - return io_apic_setup_irq_pin(virq, info->node, &attr); -} + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; -void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq) -{ - struct irq_data *data = irq_get_irq_data(virq); - struct irq_cfg *cfg = irq_cfg(virq); - int ioapic = (int)(long)domain->host_data; - int pin = (int)data->hwirq; + info->ioapic_entry = &data->entry; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); + if (ret < 0) { + kfree(data); + return ret; + } + + INIT_LIST_HEAD(&data->irq_2_pin); + irq_data->hwirq = info->ioapic_pin; + irq_data->chip = (domain->parent == x86_vector_domain) ? + &ioapic_chip : &ioapic_ir_chip; + irq_data->chip_data = data; + mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); + + cfg = irqd_cfg(irq_data); + add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + if (info->ioapic_entry) + mp_setup_entry(cfg, data, info->ioapic_entry); + mp_register_handler(virq, data->trigger); + if (virq < nr_legacy_irqs()) + legacy_pic->mask(virq); + + apic_printk(APIC_VERBOSE, KERN_DEBUG + "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", + ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector, + virq, data->trigger, data->polarity, cfg->dest_apicid); - ioapic_mask_entry(ioapic, pin); - __remove_pin_from_irq(cfg, ioapic, pin); - WARN_ON(!list_empty(&cfg->irq_2_pin)); - arch_teardown_hwirq(virq); + return 0; } -int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node) +void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { - int ret = 0; - int ioapic, pin; - struct mp_pin_info *info; + struct irq_data *irq_data; + struct mp_chip_data *data; - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return -ENODEV; - - pin = mp_find_ioapic_pin(ioapic, gsi); - info = mp_pin_info(ioapic, pin); - trigger = trigger ? 1 : 0; - polarity = polarity ? 1 : 0; - - mutex_lock(&ioapic_mutex); - if (!info->set) { - info->trigger = trigger; - info->polarity = polarity; - info->node = node; - info->set = 1; - } else if (info->trigger != trigger || info->polarity != polarity) { - ret = -EBUSY; + BUG_ON(nr_irqs != 1); + irq_data = irq_domain_get_irq_data(domain, virq); + if (irq_data && irq_data->chip_data) { + data = irq_data->chip_data; + __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain), + (int)irq_data->hwirq); + WARN_ON(!list_empty(&data->irq_2_pin)); + kfree(irq_data->chip_data); } - mutex_unlock(&ioapic_mutex); - - return ret; + irq_domain_free_irqs_top(domain, virq, nr_irqs); } -/* Enable IOAPIC early just for system timer */ -void __init pre_init_apic_IRQ0(void) +void mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data) { - struct io_apic_irq_attr attr = { 0, 0, 0, 0 }; + unsigned long flags; + struct irq_pin_list *entry; + struct mp_chip_data *data = irq_data->chip_data; - printk(KERN_INFO "Early APIC setup for system timer0\n"); -#ifndef CONFIG_SMP - physid_set_mask_of_physid(boot_cpu_physical_apicid, - &phys_cpu_present_map); -#endif - setup_local_APIC(); + raw_spin_lock_irqsave(&ioapic_lock, flags); + for_each_irq_pin(entry, data->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, data->entry); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); +} - io_apic_setup_irq_pin(0, 0, &attr); - irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, - "edge"); +void mp_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + /* It won't be called for IRQ with multiple IOAPIC pins associated */ + ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain), + (int)irq_data->hwirq); +} + +int mp_irqdomain_ioapic_idx(struct irq_domain *domain) +{ + return (int)(long)domain->host_data; } + +const struct irq_domain_ops mp_ioapic_irqdomain_ops = { + .alloc = mp_irqdomain_alloc, + .free = mp_irqdomain_free, + .activate = mp_irqdomain_activate, + .deactivate = mp_irqdomain_deactivate, +}; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index d6ba2d660..1a9d735e0 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Convert to hierarchical irqdomain * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -14,22 +16,23 @@ #include <linux/dmar.h> #include <linux/hpet.h> #include <linux/msi.h> +#include <asm/irqdomain.h> #include <asm/msidef.h> #include <asm/hpet.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/irq_remapping.h> -void native_compose_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id) +static struct irq_domain *msi_default_domain; + +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_cfg *cfg = irqd_cfg(data); msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) - msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); + msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid); msg->address_lo = MSI_ADDR_BASE_LO | @@ -39,7 +42,7 @@ void native_compose_msi_msg(struct pci_dev *pdev, ((apic->irq_delivery_mode != dest_LowestPrio) ? MSI_ADDR_REDIRECTION_CPU : MSI_ADDR_REDIRECTION_LOWPRI) | - MSI_ADDR_DEST_ID(dest); + MSI_ADDR_DEST_ID(cfg->dest_apicid); msg->data = MSI_DATA_TRIGGER_EDGE | @@ -50,180 +53,201 @@ void native_compose_msi_msg(struct pci_dev *pdev, MSI_DATA_VECTOR(cfg->vector); } -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg, u8 hpet_id) +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip pci_msi_controller = { + .name = "PCI-MSI", + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - struct irq_cfg *cfg; - int err; - unsigned dest; + struct irq_domain *domain; + struct irq_alloc_info info; - if (disable_apic) - return -ENXIO; + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_MSI; + info.msi_dev = dev; - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + domain = irq_remapping_get_irq_domain(&info); + if (domain == NULL) + domain = msi_default_domain; + if (domain == NULL) + return -ENOSYS; - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; + return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); +} - x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); +void native_teardown_msi_irq(unsigned int irq) +{ + irq_domain_free_irqs(irq, 1); +} - return 0; +static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->msi_hwirq; } -static int -msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) +static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) { - struct irq_cfg *cfg = irqd_cfg(data); - struct msi_msg msg; - unsigned int dest; - int ret; + struct pci_dev *pdev = to_pci_dev(dev); + struct msi_desc *desc = first_pci_msi_entry(pdev); + + init_irq_alloc_info(arg, NULL); + arg->msi_dev = pdev; + if (desc->msi_attrib.is_msix) { + arg->type = X86_IRQ_ALLOC_TYPE_MSIX; + } else { + arg->type = X86_IRQ_ALLOC_TYPE_MSI; + arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + } - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; + return 0; +} - __get_cached_msi_msg(data->msi_desc, &msg); +static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); +} + +static struct msi_domain_ops pci_msi_domain_ops = { + .get_hwirq = pci_msi_get_hwirq, + .msi_prepare = pci_msi_prepare, + .set_desc = pci_msi_set_desc, +}; - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); +static struct msi_domain_info pci_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &pci_msi_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; - __pci_write_msi_msg(data->msi_desc, &msg); +void arch_init_msi_domain(struct irq_domain *parent) +{ + if (disable_apic) + return; - return IRQ_SET_MASK_OK_NOCOPY; + msi_default_domain = pci_msi_create_irq_domain(NULL, + &pci_msi_domain_info, parent); + if (!msi_default_domain) + pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); } -/* - * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, - * which implement the MSI or MSI-X Capability Structure. - */ -static struct irq_chip msi_chip = { - .name = "PCI-MSI", +#ifdef CONFIG_IRQ_REMAP +static struct irq_chip pci_msi_ir_controller = { + .name = "IR-PCI-MSI", .irq_unmask = pci_msi_unmask_irq, .irq_mask = pci_msi_mask_irq, - .irq_ack = apic_ack_edge, - .irq_set_affinity = msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset) -{ - struct irq_chip *chip = &msi_chip; - struct msi_msg msg; - unsigned int irq = irq_base + irq_offset; - int ret; - - ret = msi_compose_msg(dev, irq, &msg, -1); - if (ret < 0) - return ret; - - irq_set_msi_desc_off(irq_base, irq_offset, msidesc); - - /* - * MSI-X message is written per-IRQ, the offset is always 0. - * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. - */ - if (!irq_offset) - pci_write_msi_msg(irq, &msg); +static struct msi_domain_info pci_msi_ir_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &pci_msi_ir_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; - setup_remapped_irq(irq, irq_cfg(irq), chip); +struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent) +{ + return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent); +} +#endif - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); +#ifdef CONFIG_DMAR_TABLE +static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + dmar_msi_write(data->irq, msg); +} - dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq); +static struct irq_chip dmar_msi_controller = { + .name = "DMAR-MSI", + .irq_unmask = dmar_msi_unmask, + .irq_mask = dmar_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_write_msi_msg = dmar_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; - return 0; +static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->dmar_id; } -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +static int dmar_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - struct msi_desc *msidesc; - unsigned int irq; - int node, ret; + irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL, + handle_edge_irq, arg->dmar_data, "edge"); - /* Multiple MSI vectors only supported with interrupt remapping */ - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; + return 0; +} - node = dev_to_node(&dev->dev); +static struct msi_domain_ops dmar_msi_domain_ops = { + .get_hwirq = dmar_msi_get_hwirq, + .msi_init = dmar_msi_init, +}; - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = irq_alloc_hwirq(node); - if (!irq) - return -ENOSPC; +static struct msi_domain_info dmar_msi_domain_info = { + .ops = &dmar_msi_domain_ops, + .chip = &dmar_msi_controller, +}; - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) { - irq_free_hwirq(irq); - return ret; - } +static struct irq_domain *dmar_get_irq_domain(void) +{ + static struct irq_domain *dmar_domain; + static DEFINE_MUTEX(dmar_lock); - } - return 0; -} + mutex_lock(&dmar_lock); + if (dmar_domain == NULL) + dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info, + x86_vector_domain); + mutex_unlock(&dmar_lock); -void native_teardown_msi_irq(unsigned int irq) -{ - irq_free_hwirq(irq); + return dmar_domain; } -#ifdef CONFIG_DMAR_TABLE -static int -dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) +int dmar_alloc_hwirq(int id, int node, void *arg) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest, irq = data->irq; - struct msi_msg msg; - int ret; - - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; + struct irq_domain *domain = dmar_get_irq_domain(); + struct irq_alloc_info info; - dmar_msi_read(irq, &msg); + if (!domain) + return -1; - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); - msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_DMAR; + info.dmar_id = id; + info.dmar_data = arg; - dmar_msi_write(irq, &msg); - - return IRQ_SET_MASK_OK_NOCOPY; + return irq_domain_alloc_irqs(domain, 1, node, &info); } -static struct irq_chip dmar_msi_type = { - .name = "DMAR_MSI", - .irq_unmask = dmar_msi_unmask, - .irq_mask = dmar_msi_mask, - .irq_ack = apic_ack_edge, - .irq_set_affinity = dmar_msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - -int arch_setup_dmar_msi(unsigned int irq) +void dmar_free_hwirq(int irq) { - int ret; - struct msi_msg msg; - - ret = msi_compose_msg(NULL, irq, &msg, -1); - if (ret < 0) - return ret; - dmar_msi_write(irq, &msg); - irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, - "edge"); - return 0; + irq_domain_free_irqs(irq, 1); } #endif @@ -231,56 +255,103 @@ int arch_setup_dmar_msi(unsigned int irq) * MSI message composition */ #ifdef CONFIG_HPET_TIMER +static inline int hpet_dev_id(struct irq_domain *domain) +{ + struct msi_domain_info *info = msi_get_domain_info(domain); + + return (int)(long)info->data; +} -static int hpet_msi_set_affinity(struct irq_data *data, - const struct cpumask *mask, bool force) +static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - struct msi_msg msg; - unsigned int dest; - int ret; + hpet_msi_write(data->handler_data, msg); +} - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; +static struct irq_chip hpet_msi_controller = { + .name = "HPET-MSI", + .irq_unmask = hpet_msi_unmask, + .irq_mask = hpet_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_write_msi_msg = hpet_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; - hpet_msi_read(data->handler_data, &msg); +static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->hpet_index; +} - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); +static int hpet_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) +{ + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL, + handle_edge_irq, arg->hpet_data, "edge"); - hpet_msi_write(data->handler_data, &msg); + return 0; +} - return IRQ_SET_MASK_OK_NOCOPY; +static void hpet_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); } -static struct irq_chip hpet_msi_type = { - .name = "HPET_MSI", - .irq_unmask = hpet_msi_unmask, - .irq_mask = hpet_msi_mask, - .irq_ack = apic_ack_edge, - .irq_set_affinity = hpet_msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, - .flags = IRQCHIP_SKIP_SET_WAKE, +static struct msi_domain_ops hpet_msi_domain_ops = { + .get_hwirq = hpet_msi_get_hwirq, + .msi_init = hpet_msi_init, + .msi_free = hpet_msi_free, +}; + +static struct msi_domain_info hpet_msi_domain_info = { + .ops = &hpet_msi_domain_ops, + .chip = &hpet_msi_controller, }; -int default_setup_hpet_msi(unsigned int irq, unsigned int id) +struct irq_domain *hpet_create_irq_domain(int hpet_id) { - struct irq_chip *chip = &hpet_msi_type; - struct msi_msg msg; - int ret; + struct irq_domain *parent; + struct irq_alloc_info info; + struct msi_domain_info *domain_info; + + if (x86_vector_domain == NULL) + return NULL; + + domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL); + if (!domain_info) + return NULL; + + *domain_info = hpet_msi_domain_info; + domain_info->data = (void *)(long)hpet_id; + + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.hpet_id = hpet_id; + parent = irq_remapping_get_ir_irq_domain(&info); + if (parent == NULL) + parent = x86_vector_domain; + else + hpet_msi_controller.name = "IR-HPET-MSI"; + + return msi_create_irq_domain(NULL, domain_info, parent); +} - ret = msi_compose_msg(NULL, irq, &msg, id); - if (ret < 0) - return ret; +int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev, + int dev_num) +{ + struct irq_alloc_info info; - hpet_msi_write(irq_get_handler_data(irq), &msg); - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - setup_remapped_irq(irq, irq_cfg(irq), chip); + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.hpet_data = dev; + info.hpet_id = hpet_dev_id(domain); + info.hpet_index = dev_num; - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); - return 0; + return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 6cedd7914..2683f36e4 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Enable support of hierarchical irqdomains * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,15 +13,28 @@ #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compiler.h> -#include <linux/irqdomain.h> #include <linux/slab.h> +#include <asm/irqdomain.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/i8259.h> #include <asm/desc.h> #include <asm/irq_remapping.h> +struct apic_chip_data { + struct irq_cfg cfg; + cpumask_var_t domain; + cpumask_var_t old_domain; + u8 move_in_progress : 1; +}; + +struct irq_domain *x86_vector_domain; static DEFINE_RAW_SPINLOCK(vector_lock); +static cpumask_var_t vector_cpumask; +static struct irq_chip lapic_controller; +#ifdef CONFIG_X86_IO_APIC +static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; +#endif void lock_vector_lock(void) { @@ -34,71 +49,59 @@ void unlock_vector_lock(void) raw_spin_unlock(&vector_lock); } -struct irq_cfg *irq_cfg(unsigned int irq) +static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data) { - return irq_get_chip_data(irq); + if (!irq_data) + return NULL; + + while (irq_data->parent_data) + irq_data = irq_data->parent_data; + + return irq_data->chip_data; } struct irq_cfg *irqd_cfg(struct irq_data *irq_data) { - return irq_data->chip_data; + struct apic_chip_data *data = apic_chip_data(irq_data); + + return data ? &data->cfg : NULL; } -static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) +struct irq_cfg *irq_cfg(unsigned int irq) { - struct irq_cfg *cfg; + return irqd_cfg(irq_get_irq_data(irq)); +} - cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node); - if (!cfg) +static struct apic_chip_data *alloc_apic_chip_data(int node) +{ + struct apic_chip_data *data; + + data = kzalloc_node(sizeof(*data), GFP_KERNEL, node); + if (!data) return NULL; - if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node)) - goto out_cfg; - if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node)) + if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node)) + goto out_data; + if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node)) goto out_domain; -#ifdef CONFIG_X86_IO_APIC - INIT_LIST_HEAD(&cfg->irq_2_pin); -#endif - return cfg; + return data; out_domain: - free_cpumask_var(cfg->domain); -out_cfg: - kfree(cfg); + free_cpumask_var(data->domain); +out_data: + kfree(data); return NULL; } -struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) +static void free_apic_chip_data(struct apic_chip_data *data) { - int res = irq_alloc_desc_at(at, node); - struct irq_cfg *cfg; - - if (res < 0) { - if (res != -EEXIST) - return NULL; - cfg = irq_cfg(at); - if (cfg) - return cfg; + if (data) { + free_cpumask_var(data->domain); + free_cpumask_var(data->old_domain); + kfree(data); } - - cfg = alloc_irq_cfg(at, node); - if (cfg) - irq_set_chip_data(at, cfg); - else - irq_free_desc(at); - return cfg; } -static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) -{ - if (!cfg) - return; - irq_set_chip_data(at, NULL); - free_cpumask_var(cfg->domain); - free_cpumask_var(cfg->old_domain); - kfree(cfg); -} - -static int -__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +static int __assign_irq_vector(int irq, struct apic_chip_data *d, + const struct cpumask *mask) { /* * NOTE! The local APIC isn't very good at handling @@ -114,36 +117,33 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; int cpu, err; - cpumask_var_t tmp_mask; - if (cfg->move_in_progress) + if (d->move_in_progress) return -EBUSY; - if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) - return -ENOMEM; - /* Only try and allocate irqs on cpus that are present */ err = -ENOSPC; - cpumask_clear(cfg->old_domain); + cpumask_clear(d->old_domain); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { int new_cpu, vector, offset; - apic->vector_allocation_domain(cpu, tmp_mask, mask); + apic->vector_allocation_domain(cpu, vector_cpumask, mask); - if (cpumask_subset(tmp_mask, cfg->domain)) { + if (cpumask_subset(vector_cpumask, d->domain)) { err = 0; - if (cpumask_equal(tmp_mask, cfg->domain)) + if (cpumask_equal(vector_cpumask, d->domain)) break; /* * New cpumask using the vector is a proper subset of * the current in use mask. So cleanup the vector * allocation for the members that are not used anymore. */ - cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); - cpumask_and(cfg->domain, cfg->domain, tmp_mask); + cpumask_andnot(d->old_domain, d->domain, + vector_cpumask); + d->move_in_progress = + cpumask_intersects(d->old_domain, cpu_online_mask); + cpumask_and(d->domain, d->domain, vector_cpumask); break; } @@ -157,16 +157,18 @@ next: } if (unlikely(current_vector == vector)) { - cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); - cpumask_andnot(tmp_mask, mask, cfg->old_domain); - cpu = cpumask_first_and(tmp_mask, cpu_online_mask); + cpumask_or(d->old_domain, d->old_domain, + vector_cpumask); + cpumask_andnot(vector_cpumask, mask, d->old_domain); + cpu = cpumask_first_and(vector_cpumask, + cpu_online_mask); continue; } if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) { + for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED) goto next; @@ -174,55 +176,73 @@ next: /* Found one! */ current_vector = vector; current_offset = offset; - if (cfg->vector) { - cpumask_copy(cfg->old_domain, cfg->domain); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); + if (d->cfg.vector) { + cpumask_copy(d->old_domain, d->domain); + d->move_in_progress = + cpumask_intersects(d->old_domain, cpu_online_mask); } - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) + for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) per_cpu(vector_irq, new_cpu)[vector] = irq; - cfg->vector = vector; - cpumask_copy(cfg->domain, tmp_mask); + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); err = 0; break; } - free_cpumask_var(tmp_mask); + + if (!err) { + /* cache destination APIC IDs into cfg->dest_apicid */ + err = apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid); + } return err; } -int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +static int assign_irq_vector(int irq, struct apic_chip_data *data, + const struct cpumask *mask) { int err; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, cfg, mask); + err = __assign_irq_vector(irq, data, mask); raw_spin_unlock_irqrestore(&vector_lock, flags); return err; } -void clear_irq_vector(int irq, struct irq_cfg *cfg) +static int assign_irq_vector_policy(int irq, int node, + struct apic_chip_data *data, + struct irq_alloc_info *info) +{ + if (info && info->mask) + return assign_irq_vector(irq, data, info->mask); + if (node != NUMA_NO_NODE && + assign_irq_vector(irq, data, cpumask_of_node(node)) == 0) + return 0; + return assign_irq_vector(irq, data, apic->target_cpus()); +} + +static void clear_irq_vector(int irq, struct apic_chip_data *data) { int cpu, vector; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - BUG_ON(!cfg->vector); + BUG_ON(!data->cfg.vector); - vector = cfg->vector; - for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) + vector = data->cfg.vector; + for_each_cpu_and(cpu, data->domain, cpu_online_mask) per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; - cfg->vector = 0; - cpumask_clear(cfg->domain); + data->cfg.vector = 0; + cpumask_clear(data->domain); - if (likely(!cfg->move_in_progress)) { + if (likely(!data->move_in_progress)) { raw_spin_unlock_irqrestore(&vector_lock, flags); return; } - for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { + for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) @@ -231,10 +251,95 @@ void clear_irq_vector(int irq, struct irq_cfg *cfg) break; } } - cfg->move_in_progress = 0; + data->move_in_progress = 0; raw_spin_unlock_irqrestore(&vector_lock, flags); } +void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask) +{ + memset(info, 0, sizeof(*info)); + info->mask = mask; +} + +void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) +{ + if (src) + *dst = *src; + else + memset(dst, 0, sizeof(*dst)); +} + +static void x86_vector_free_irqs(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); + if (irq_data && irq_data->chip_data) { + clear_irq_vector(virq + i, irq_data->chip_data); + free_apic_chip_data(irq_data->chip_data); +#ifdef CONFIG_X86_IO_APIC + if (virq + i < nr_legacy_irqs()) + legacy_irq_data[virq + i] = NULL; +#endif + irq_domain_reset_irq_data(irq_data); + } + } +} + +static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + struct apic_chip_data *data; + struct irq_data *irq_data; + int i, err; + + if (disable_apic) + return -ENXIO; + + /* Currently vector allocator can't guarantee contiguous allocations */ + if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1) + return -ENOSYS; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + BUG_ON(!irq_data); +#ifdef CONFIG_X86_IO_APIC + if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i]) + data = legacy_irq_data[virq + i]; + else +#endif + data = alloc_apic_chip_data(irq_data->node); + if (!data) { + err = -ENOMEM; + goto error; + } + + irq_data->chip = &lapic_controller; + irq_data->chip_data = data; + irq_data->hwirq = virq + i; + err = assign_irq_vector_policy(virq + i, irq_data->node, data, + info); + if (err) + goto error; + } + + return 0; + +error: + x86_vector_free_irqs(domain, virq, i + 1); + return err; +} + +static const struct irq_domain_ops x86_vector_domain_ops = { + .alloc = x86_vector_alloc_irqs, + .free = x86_vector_free_irqs, +}; + int __init arch_probe_nr_irqs(void) { int nr; @@ -258,8 +363,43 @@ int __init arch_probe_nr_irqs(void) return nr_legacy_irqs(); } +#ifdef CONFIG_X86_IO_APIC +static void init_legacy_irqs(void) +{ + int i, node = cpu_to_node(0); + struct apic_chip_data *data; + + /* + * For legacy IRQ's, start with assigning irq0 to irq15 to + * ISA_IRQ_VECTOR(i) for all cpu's. + */ + for (i = 0; i < nr_legacy_irqs(); i++) { + data = legacy_irq_data[i] = alloc_apic_chip_data(node); + BUG_ON(!data); + + data->cfg.vector = ISA_IRQ_VECTOR(i); + cpumask_setall(data->domain); + irq_set_chip_data(i, data); + } +} +#else +static void init_legacy_irqs(void) { } +#endif + int __init arch_early_irq_init(void) { + init_legacy_irqs(); + + x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops, + NULL); + BUG_ON(x86_vector_domain == NULL); + irq_set_default_host(x86_vector_domain); + + arch_init_msi_domain(x86_vector_domain); + arch_init_htirq_domain(x86_vector_domain); + + BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + return arch_early_ioapic_init(); } @@ -267,23 +407,17 @@ static void __setup_vector_irq(int cpu) { /* Initialize vector_irq on a new cpu */ int irq, vector; - struct irq_cfg *cfg; + struct apic_chip_data *data; - /* - * vector_lock will make sure that we don't run into irq vector - * assignments that might be happening on another cpu in parallel, - * while we setup our initial vector to irq mappings. - */ - raw_spin_lock(&vector_lock); /* Mark the inuse vectors */ for_each_active_irq(irq) { - cfg = irq_cfg(irq); - if (!cfg) + data = apic_chip_data(irq_get_irq_data(irq)); + if (!data) continue; - if (!cpumask_test_cpu(cpu, cfg->domain)) + if (!cpumask_test_cpu(cpu, data->domain)) continue; - vector = cfg->vector; + vector = data->cfg.vector; per_cpu(vector_irq, cpu)[vector] = irq; } /* Mark the free vectors */ @@ -292,20 +426,20 @@ static void __setup_vector_irq(int cpu) if (irq <= VECTOR_UNDEFINED) continue; - cfg = irq_cfg(irq); - if (!cpumask_test_cpu(cpu, cfg->domain)) + data = apic_chip_data(irq_get_irq_data(irq)); + if (!cpumask_test_cpu(cpu, data->domain)) per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; } - raw_spin_unlock(&vector_lock); } /* - * Setup the vector to irq mappings. + * Setup the vector to irq mappings. Must be called with vector_lock held. */ void setup_vector_irq(int cpu) { int irq; + lockdep_assert_held(&vector_lock); /* * On most of the platforms, legacy PIC delivers the interrupts on the * boot cpu. But there are certain platforms where PIC interrupts are @@ -314,20 +448,20 @@ void setup_vector_irq(int cpu) * legacy vector to irq mapping: */ for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq; + per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq; __setup_vector_irq(cpu); } -int apic_retrigger_irq(struct irq_data *data) +static int apic_retrigger_irq(struct irq_data *irq_data) { - struct irq_cfg *cfg = irqd_cfg(data); + struct apic_chip_data *data = apic_chip_data(irq_data); unsigned long flags; int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - cpu = cpumask_first_and(cfg->domain, cpu_online_mask); - apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); + cpu = cpumask_first_and(data->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -340,73 +474,76 @@ void apic_ack_edge(struct irq_data *data) ack_APIC_irq(); } -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int apic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) +static int apic_set_affinity(struct irq_data *irq_data, + const struct cpumask *dest, bool force) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int irq = data->irq; - int err; + struct apic_chip_data *data = irq_data->chip_data; + int err, irq = irq_data->irq; if (!config_enabled(CONFIG_SMP)) return -EPERM; - if (!cpumask_intersects(mask, cpu_online_mask)) + if (!cpumask_intersects(dest, cpu_online_mask)) return -EINVAL; - err = assign_irq_vector(irq, cfg, mask); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); + err = assign_irq_vector(irq, data, dest); if (err) { - if (assign_irq_vector(irq, cfg, data->affinity)) + struct irq_data *top = irq_get_irq_data(irq); + + if (assign_irq_vector(irq, data, top->affinity)) pr_err("Failed to recover vector for irq %d\n", irq); return err; } - cpumask_copy(data->affinity, mask); - - return 0; + return IRQ_SET_MASK_OK; } +static struct irq_chip lapic_controller = { + .irq_ack = apic_ack_edge, + .irq_set_affinity = apic_set_affinity, + .irq_retrigger = apic_retrigger_irq, +}; + #ifdef CONFIG_SMP -void send_cleanup_vector(struct irq_cfg *cfg) +static void __send_cleanup_vector(struct apic_chip_data *data) { cpumask_var_t cleanup_mask; if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { unsigned int i; - for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) + for_each_cpu_and(i, data->old_domain, cpu_online_mask) apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR); } else { - cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); + cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); free_cpumask_var(cleanup_mask); } - cfg->move_in_progress = 0; + data->move_in_progress = 0; +} + +void send_cleanup_vector(struct irq_cfg *cfg) +{ + struct apic_chip_data *data; + + data = container_of(cfg, struct apic_chip_data, cfg); + if (data->move_in_progress) + __send_cleanup_vector(data); } asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; - ack_APIC_irq(); - irq_enter(); - exit_idle(); + entering_ack_irq(); me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { int irq; unsigned int irr; struct irq_desc *desc; - struct irq_cfg *cfg; + struct apic_chip_data *data; irq = __this_cpu_read(vector_irq[vector]); @@ -417,8 +554,8 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) if (!desc) continue; - cfg = irq_cfg(irq); - if (!cfg) + data = apic_chip_data(&desc->irq_data); + if (!data) continue; raw_spin_lock(&desc->lock); @@ -427,10 +564,11 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) * Check if the irq migration is in progress. If so, we * haven't received the cleanup request yet for this irq. */ - if (cfg->move_in_progress) + if (data->move_in_progress) goto unlock; - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) + if (vector == data->cfg.vector && + cpumask_test_cpu(me, data->domain)) goto unlock; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); @@ -450,20 +588,21 @@ unlock: raw_spin_unlock(&desc->lock); } - irq_exit(); + exiting_irq(); } static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) { unsigned me; + struct apic_chip_data *data; - if (likely(!cfg->move_in_progress)) + data = container_of(cfg, struct apic_chip_data, cfg); + if (likely(!data->move_in_progress)) return; me = smp_processor_id(); - - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) - send_cleanup_vector(cfg); + if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) + __send_cleanup_vector(data); } void irq_complete_move(struct irq_cfg *cfg) @@ -475,46 +614,11 @@ void irq_force_complete_move(int irq) { struct irq_cfg *cfg = irq_cfg(irq); - if (!cfg) - return; - - __irq_complete_move(cfg, cfg->vector); + if (cfg) + __irq_complete_move(cfg, cfg->vector); } #endif -/* - * Dynamic irq allocate and deallocation. Should be replaced by irq domains! - */ -int arch_setup_hwirq(unsigned int irq, int node) -{ - struct irq_cfg *cfg; - unsigned long flags; - int ret; - - cfg = alloc_irq_cfg(irq, node); - if (!cfg) - return -ENOMEM; - - raw_spin_lock_irqsave(&vector_lock, flags); - ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); - raw_spin_unlock_irqrestore(&vector_lock, flags); - - if (!ret) - irq_set_chip_data(irq, cfg); - else - free_irq_cfg(irq, cfg); - return ret; -} - -void arch_teardown_hwirq(unsigned int irq) -{ - struct irq_cfg *cfg = irq_cfg(irq); - - free_remapped_irq(irq); - clear_irq_vector(irq, cfg); - free_irq_cfg(irq, cfg); -} - static void __init print_APIC_field(int base) { int i; diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 6fae733e9..3ffd92565 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -21,11 +21,13 @@ early_param("x2apic_phys", set_x2apic_phys_mode); static bool x2apic_fadt_phys(void) { +#ifdef CONFIG_ACPI if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { printk(KERN_DEBUG "System requires x2apic physical mode\n"); return true; } +#endif return false; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 9f6b93419..8e3d22a1a 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -41,6 +41,25 @@ void common(void) { OFFSET(pbe_orig_address, pbe, orig_address); OFFSET(pbe_next, pbe, next); +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) + BLANK(); + OFFSET(IA32_SIGCONTEXT_ax, sigcontext_ia32, ax); + OFFSET(IA32_SIGCONTEXT_bx, sigcontext_ia32, bx); + OFFSET(IA32_SIGCONTEXT_cx, sigcontext_ia32, cx); + OFFSET(IA32_SIGCONTEXT_dx, sigcontext_ia32, dx); + OFFSET(IA32_SIGCONTEXT_si, sigcontext_ia32, si); + OFFSET(IA32_SIGCONTEXT_di, sigcontext_ia32, di); + OFFSET(IA32_SIGCONTEXT_bp, sigcontext_ia32, bp); + OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp); + OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip); + + BLANK(); + OFFSET(TI_sysenter_return, thread_info, sysenter_return); + + BLANK(); + OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); +#endif + #ifdef CONFIG_PARAVIRT BLANK(); OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); @@ -49,7 +68,9 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); +#ifdef CONFIG_X86_32 OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); +#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 47703aed7..6ce39025f 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -17,17 +17,6 @@ void foo(void); void foo(void) { - OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax); - OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx); - OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx); - OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx); - OFFSET(IA32_SIGCONTEXT_si, sigcontext, si); - OFFSET(IA32_SIGCONTEXT_di, sigcontext, di); - OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp); - OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp); - OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip); - BLANK(); - OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); @@ -37,10 +26,6 @@ void foo(void) OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); BLANK(); - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - OFFSET(TI_cpu, thread_info, cpu); - BLANK(); - OFFSET(PT_EBX, pt_regs, bx); OFFSET(PT_ECX, pt_regs, cx); OFFSET(PT_EDX, pt_regs, dx); @@ -60,9 +45,6 @@ void foo(void) OFFSET(PT_OLDSS, pt_regs, ss); BLANK(); - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext); - BLANK(); - OFFSET(saved_context_gdt_desc, saved_context, gdt_desc); BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 5ce6f2da8..d8f42f902 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -29,27 +29,6 @@ int main(void) BLANK(); #endif -#ifdef CONFIG_IA32_EMULATION - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - BLANK(); - -#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry) - ENTRY(ax); - ENTRY(bx); - ENTRY(cx); - ENTRY(dx); - ENTRY(si); - ENTRY(di); - ENTRY(bp); - ENTRY(sp); - ENTRY(ip); - BLANK(); -#undef ENTRY - - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); - BLANK(); -#endif - #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); @@ -87,7 +66,7 @@ int main(void) DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); - DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1); + DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); return 0; diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c index 5de7f4c56..52c8e3c77 100644 --- a/arch/x86/kernel/bootflag.c +++ b/arch/x86/kernel/bootflag.c @@ -98,4 +98,4 @@ static int __init sbf_init(void) return 0; } -module_init(sbf_init); +arch_initcall(sbf_init); diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 83a799562..58118e207 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) { start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), PAGE_SIZE, corruption_check_size); end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e4cf63301..dd3a4baff 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -19,6 +19,13 @@ #include "cpu.h" +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX + * Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -288,10 +295,10 @@ static int nearby_node(int apicid) * Assumption: Number of cores in each internal node is the same. * (2) AMD processors supporting compute units */ -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { - u32 nodes, cores_per_cu = 1; + u32 cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -300,7 +307,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - nodes = ((ecx >> 8) & 7) + 1; + nodes_per_socket = ((ecx >> 8) & 7) + 1; node_id = ecx & 7; /* get compute unit information */ @@ -311,18 +318,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes = ((value >> 3) & 7) + 1; + nodes_per_socket = ((value >> 3) & 7) + 1; node_id = value & 7; } else return; /* fixup multi-node processor information */ - if (nodes > 1) { + if (nodes_per_socket > 1) { u32 cores_per_node; u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes; + cores_per_node = c->x86_max_cores / nodes_per_socket; cus_per_node = cores_per_node / cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ @@ -341,7 +348,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) */ static void amd_detect_cmp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); @@ -366,6 +373,12 @@ u16 amd_get_nb_id(int cpu) } EXPORT_SYMBOL_GPL(amd_get_nb_id); +u32 amd_get_nodes_per_socket(void) +{ + return nodes_per_socket; +} +EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); + static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -420,7 +433,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) static void early_init_amd_mc(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned bits, ecx; /* Multi core CPU? */ @@ -520,8 +533,16 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) - /* check CPU config space for extended APIC ID */ - if (cpu_has_apic && c->x86 >= 0xf) { + /* + * ApicID can always be treated as an 8-bit value for AMD APIC versions + * >= 0x10, but even old K8s came out of reset with version 0x10. So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally for families + * after 16h. + */ + if (cpu_has_apic && c->x86 > 0x16) { + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } else if (cpu_has_apic && c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ unsigned int val; val = read_pci_config(0, 24, 0, 0x68); if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 03445346e..bd17db15a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,57 +12,11 @@ #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> -static double __initdata x = 4195835.0; -static double __initdata y = 3145727.0; - -/* - * This used to check for exceptions.. - * However, it turns out that to support that, - * the XMM trap handlers basically had to - * be buggy. So let's have a correct XMM trap - * handler, and forget about printing out - * some status at boot. - * - * We should really only care about bugs here - * anyway. Not features. - */ -static void __init check_fpu(void) -{ - s32 fdiv_bug; - - kernel_fpu_begin(); - - /* - * trap_init() enabled FXSR and company _before_ testing for FP - * problems here. - * - * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug - */ - __asm__("fninit\n\t" - "fldl %1\n\t" - "fdivl %2\n\t" - "fmull %2\n\t" - "fldl %1\n\t" - "fsubp %%st,%%st(1)\n\t" - "fistpl %0\n\t" - "fwait\n\t" - "fninit" - : "=m" (*&fdiv_bug) - : "m" (*&x), "m" (*&y)); - - kernel_fpu_end(); - - if (fdiv_bug) { - set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); - pr_warn("Hmm, FPU with FDIV bug\n"); - } -} - void __init check_bugs(void) { identify_boot_cpu(); @@ -85,10 +39,5 @@ void __init check_bugs(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); + fpu__init_check_bugs(); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a62cf04da..cb9e5df42 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/percpu.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/init.h> @@ -31,8 +32,7 @@ #include <asm/setup.h> #include <asm/apic.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mtrr.h> #include <linux/numa.h> #include <asm/asm.h> @@ -145,32 +145,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); -static int __init x86_xsave_setup(char *s) +static int __init x86_mpx_setup(char *s) { + /* require an exact match without trailing characters */ if (strlen(s)) return 0; - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - return 1; -} -__setup("noxsave", x86_xsave_setup); -static int __init x86_xsaveopt_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - return 1; -} -__setup("noxsaveopt", x86_xsaveopt_setup); + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_MPX)) + return 1; -static int __init x86_xsaves_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_MPX); + pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n"); return 1; } -__setup("noxsaves", x86_xsaves_setup); +__setup("nompx", x86_mpx_setup); #ifdef CONFIG_X86_32 static int cachesize_override = -1; @@ -183,14 +172,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_fxsr_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FXSR); - setup_clear_cpu_cap(X86_FEATURE_XMM); - return 1; -} -__setup("nofxsr", x86_fxsr_setup); - static int __init x86_sep_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_SEP); @@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; static void get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; - char *p, *q; + char *p, *q, *s; if (c->extended_cpuid_level < 0x80000004) return; @@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c) cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); c->x86_model_id[48] = 0; - /* - * Intel chips right-justify this string for some dumb reason; - * undo that brain damage: - */ - p = q = &c->x86_model_id[0]; + /* Trim whitespace */ + p = q = s = &c->x86_model_id[0]; + while (*p == ' ') p++; - if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + + while (*p) { + /* Note the last non-whitespace index */ + if (!isspace(*p)) + s = q; + + *q++ = *p++; } + + *(s + 1) = '\0'; } void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) @@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) void detect_ht(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP u32 eax, ebx, ecx, edx; int index_msb, core_bits; static bool printed; @@ -759,7 +742,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); - fpu_detect(c); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -771,6 +753,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); setup_force_cpu_cap(X86_FEATURE_ALWAYS); + fpu__init_system(c); } void __init early_cpu_init(void) @@ -844,7 +827,7 @@ static void generic_identify(struct cpuinfo_x86 *c) if (c->cpuid_level >= 0x00000001) { c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 -# ifdef CONFIG_X86_HT +# ifdef CONFIG_SMP c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); # else c->apicid = c->initial_apicid; @@ -1026,7 +1009,7 @@ void enable_sep_cpu(void) (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), 0); - wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0); + wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); out: put_cpu(); @@ -1122,7 +1105,7 @@ void print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", strim(c->x86_model_id)); + printk(KERN_CONT "%s", c->x86_model_id); else printk(KERN_CONT "%d86", c->x86); @@ -1155,10 +1138,6 @@ static __init int setup_disablecpuid(char *arg) } __setup("clearcpuid=", setup_disablecpuid); -DEFINE_PER_CPU(unsigned long, kernel_stack) = - (unsigned long)&init_thread_union + THREAD_SIZE; -EXPORT_PER_CPU_SYMBOL(kernel_stack); - #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, @@ -1183,8 +1162,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); - /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware @@ -1208,10 +1185,10 @@ void syscall_init(void) * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); - wrmsrl(MSR_LSTAR, system_call); + wrmsrl(MSR_LSTAR, entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, entry_SYSCALL_compat); /* * This only works on Intel CPUs. * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. @@ -1220,7 +1197,7 @@ void syscall_init(void) */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, ignore_sysret); wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); @@ -1275,7 +1252,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); /* * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find @@ -1434,12 +1410,12 @@ void cpu_init(void) load_sp0(t, ¤t->thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); if (is_uv_system()) uv_cpu_init(); @@ -1483,7 +1459,7 @@ void cpu_init(void) load_sp0(t, thread); set_tss_desc(cpu, t); load_TR_desc(); - load_LDT(&init_mm.context); + load_mm_ldt(&init_mm); t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); @@ -1495,7 +1471,7 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); } #endif diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index ba2546f0d..50163fa90 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -27,7 +27,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) { - bool allow_fast_string = true; + u64 misc_enable; /* Unmask CPUID levels if masked: */ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { @@ -126,28 +126,17 @@ static void early_init_intel(struct cpuinfo_x86 *c) * Ingo Molnar reported a Pentium D (model 6) and a Xeon * (model 2) with the same problem. */ - if (c->x86 == 15) { - allow_fast_string = false; - + if (c->x86 == 15) if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) pr_info("kmemcheck: Disabling fast string operations\n"); - } #endif /* - * If BIOS didn't enable fast string operation, try to enable - * it ourselves. If that fails, then clear the fast string - * and enhanced fast string CPU capabilities. + * If fast string is not enabled in IA32_MISC_ENABLE for any reason, + * clear the fast string and enhanced fast string CPU capabilities. */ if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { - u64 misc_enable; - - if (allow_fast_string && - msr_set_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) - pr_info(FW_WARN "IA32_MISC_ENABLE.FAST_STRING_ENABLE was not set\n"); - rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) { printk(KERN_INFO "Disabled fast string operations\n"); @@ -504,24 +493,6 @@ static void init_intel(struct cpuinfo_x86 *c) wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); } } - - /* Enable monitor/mwait if BIOS didn't do it for us. */ - if (!cpu_has(c, X86_FEATURE_MWAIT) && cpu_has(c, X86_FEATURE_XMM3) - && c->x86 >= 6 && !(c->x86 == 6 && c->x86_model < 0x1c) - && !(c->x86 == 0xf && c->x86_model < 3)) { - /* - * Some non-SSE3 cpus will #GP. We check for that, - * but it can't hurt to be safe. - */ - msr_set_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_MWAIT_BIT); - - /* Re-read monitor capability. */ - if (cpuid_ecx(1) & 0x8) { - set_cpu_cap(c, X86_FEATURE_MWAIT); - - printk(KERN_WARNING FW_WARN "IA32_MISC_ENABLE.ENABLE_MONITOR_FSM was not set\n"); - } - } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index edcb0e28c..be4febc58 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned int cpu = c->cpu_index; #endif @@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l2) { l2 = new_l2; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l2_id; #endif } if (new_l3) { l3 = new_l3; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l3_id; #endif } -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP /* * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in * turns means that the only possibility is SMT (as indicated in diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 20190bdac..df919ff10 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -53,9 +53,12 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ - rcu_dereference_index_check((p), \ - rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex)) +({ \ + rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious rcu_dereference_check_mce() usage"); \ + smp_load_acquire(&(p)); \ +}) #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -1050,6 +1053,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) char *msg = "Unknown"; u64 recover_paddr = ~0ull; int flags = MF_ACTION_REQUIRED; + int lmce = 0; prev_state = ist_enter(regs); @@ -1077,11 +1081,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) kill_it = 1; /* - * Go through all the banks in exclusion of the other CPUs. - * This way we don't report duplicated events on shared banks - * because the first one to see it will clear it. + * Check if this MCE is signaled to only this logical processor */ - order = mce_start(&no_way_out); + if (m.mcgstatus & MCG_STATUS_LMCES) + lmce = 1; + else { + /* + * Go through all the banks in exclusion of the other CPUs. + * This way we don't report duplicated events on shared banks + * because the first one to see it will clear it. + * If this is a Local MCE, then no need to perform rendezvous. + */ + order = mce_start(&no_way_out); + } + for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) @@ -1158,8 +1171,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) * Do most of the synchronization with other CPUs. * When there's any problem use only local no_way_out state. */ - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (!lmce) { + if (mce_end(order) < 0) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } else { + /* + * Local MCE skipped calling mce_reign() + * If we found a fatal error, we need to panic here. + */ + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) + mce_panic("Machine check from unknown source", + NULL, NULL); + } /* * At insane "tolerant" levels we take no action. Otherwise @@ -1640,10 +1663,16 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_intel_feature_init(c); mce_adjust_timer = cmci_intel_adjust_timer; break; - case X86_VENDOR_AMD: + + case X86_VENDOR_AMD: { + u32 ebx = cpuid_ebx(0x80000007); + mce_amd_feature_init(c); - mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1; + mce_flags.overflow_recov = !!(ebx & BIT(0)); + mce_flags.succor = !!(ebx & BIT(1)); break; + } + default: break; } @@ -1887,7 +1916,7 @@ out: static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (rcu_access_index(mcelog.next)) + if (READ_ONCE(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; @@ -1932,8 +1961,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp, } EXPORT_SYMBOL_GPL(register_mce_write_callback); -ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) { if (mce_write) return mce_write(filp, ubuf, usize, off); @@ -1979,6 +2008,7 @@ void mce_disable_bank(int bank) /* * mce=off Disables machine check * mce=no_cmci Disables CMCI + * mce=no_lmce Disables LMCE * mce=dont_log_ce Clears corrected events silently, no log created for CEs. * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared. * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) @@ -2002,6 +2032,8 @@ static int __init mcheck_enable(char *str) cfg->disabled = true; else if (!strcmp(str, "no_cmci")) cfg->cmci_disabled = true; + else if (!strcmp(str, "no_lmce")) + cfg->lmce_disabled = true; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) @@ -2011,11 +2043,8 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bios_cmci_threshold")) cfg->bios_cmci_threshold = true; else if (isdigit(str[0])) { - get_option(&str, &(cfg->tolerant)); - if (*str == ',') { - ++str; + if (get_option(&str, &cfg->tolerant) == 2) get_option(&str, &(cfg->monarch_timeout)); - } } else { pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 55ad9b37c..e99b15077 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1,19 +1,13 @@ /* - * (c) 2005-2012 Advanced Micro Devices, Inc. + * (c) 2005-2015 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html * * Written by Jacob Shin - AMD, Inc. - * * Maintained by: Borislav Petkov <bp@alien8.de> * - * April 2006 - * - added support for AMD Family 0x10 processors - * May 2012 - * - major scrubbing - * - * All MC4_MISCi registers are shared between multi-cores + * All MC4_MISCi registers are shared between cores on a node. */ #include <linux/interrupt.h> #include <linux/notifier.h> @@ -32,6 +26,7 @@ #include <asm/idle.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/trace/irq_vectors.h> #define NR_BLOCKS 9 #define THRESHOLD_MAX 0xFFF @@ -47,6 +42,13 @@ #define MASK_BLKPTR_LO 0xFF000000 #define MCG_XBLK_ADDR 0xC0000400 +/* Deferred error settings */ +#define MSR_CU_DEF_ERR 0xC0000410 +#define MASK_DEF_LVTOFF 0x000000F0 +#define MASK_DEF_INT_TYPE 0x00000006 +#define DEF_LVT_OFF 0x2 +#define DEF_INT_TYPE_APIC 0x2 + static const char * const th_names[] = { "load_store", "insn_fetch", @@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ static void amd_threshold_interrupt(void); +static void amd_deferred_error_interrupt(void); + +static void default_deferred_error_interrupt(void) +{ + pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR); +} +void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; /* * CPU Initialization @@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset) threshold_restart_bank(&tr); }; -static int setup_APIC_mce(int reserved, int new) +static int setup_APIC_mce_threshold(int reserved, int new) { if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR, APIC_EILVT_MSG_FIX, 0)) @@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new) return reserved; } +static int setup_APIC_deferred_error(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; +} + +static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) +{ + u32 low = 0, high = 0; + int def_offset = -1, def_new; + + if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high)) + return; + + def_new = (low & MASK_DEF_LVTOFF) >> 4; + if (!(low & MASK_DEF_LVTOFF)) { + pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n"); + def_new = DEF_LVT_OFF; + low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4); + } + + def_offset = setup_APIC_deferred_error(def_offset, def_new); + if ((def_offset == def_new) && + (deferred_error_int_vector != amd_deferred_error_interrupt)) + deferred_error_int_vector = amd_deferred_error_interrupt; + + low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC; + wrmsr(MSR_CU_DEF_ERR, low, high); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) b.interrupt_enable = 1; new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce(offset, new); + offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) @@ -262,6 +304,73 @@ init: mce_threshold_block_init(&b, offset); } } + + if (mce_flags.succor) + deferred_error_interrupt_enable(c); +} + +static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +{ + struct mce m; + u64 status; + + rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + if (!(status & MCI_STATUS_VAL)) + return; + + mce_setup(&m); + + m.status = status; + m.bank = bank; + + if (threshold_err) + m.misc = misc; + + if (m.status & MCI_STATUS_ADDRV) + rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr); + + mce_log(&m); + wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); +} + +static inline void __smp_deferred_error_interrupt(void) +{ + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); +} + +asmlinkage __visible void smp_deferred_error_interrupt(void) +{ + entering_irq(); + __smp_deferred_error_interrupt(); + exiting_ack_irq(); +} + +asmlinkage __visible void smp_trace_deferred_error_interrupt(void) +{ + entering_irq(); + trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); + __smp_deferred_error_interrupt(); + trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); + exiting_ack_irq(); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) +{ + u64 status; + unsigned int bank; + + for (bank = 0; bank < mca_cfg.banks; ++bank) { + rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + + if (!(status & MCI_STATUS_VAL) || + !(status & MCI_STATUS_DEFERRED)) + continue; + + __log_error(bank, false, 0); + break; + } } /* @@ -273,12 +382,12 @@ init: * the interrupt goes off when error_count reaches threshold_limit. * the handler will simply log mcelog w/ software defined bank number. */ + static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; int cpu = smp_processor_id(); unsigned int bank, block; - struct mce m; /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { @@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void) return; log: - mce_setup(&m); - rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); - if (!(m.status & MCI_STATUS_VAL)) - return; - m.misc = ((u64)high << 32) | low; - m.bank = bank; - mce_log(&m); - - wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); + __log_error(bank, true, ((u64)high << 32) | low); } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index b4a41cf03..844f56c56 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -91,6 +91,36 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +static bool lmce_supported(void) +{ + u64 tmp; + + if (mca_cfg.lmce_disabled) + return false; + + rdmsrl(MSR_IA32_MCG_CAP, tmp); + + /* + * LMCE depends on recovery support in the processor. Hence both + * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP. + */ + if ((tmp & (MCG_SER_P | MCG_LMCE_P)) != + (MCG_SER_P | MCG_LMCE_P)) + return false; + + /* + * BIOS should indicate support for LMCE by setting bit 20 in + * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will + * generate a #GP fault. + */ + rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp); + if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) == + (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) + return true; + + return false; +} + bool mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) @@ -405,8 +435,22 @@ static void intel_init_cmci(void) cmci_recheck(); } +void intel_init_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + + if (!(val & MCG_EXT_CTL_LMCE_EN)) + wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); intel_init_cmci(); + intel_init_lmce(); } diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 816a25c90..5d1fb6061 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -228,7 +228,23 @@ static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) } } -void __init load_ucode_amd_bsp(void) +static bool __init load_builtin_amd_microcode(struct cpio_data *cp, + unsigned int family) +{ +#ifdef CONFIG_X86_64 + char fw_name[36] = "/*(DEBLOBBED)*/"; + + if (family >= 0x15) + snprintf(fw_name, sizeof(fw_name), + "/*(DEBLOBBED)*/", family); + + return get_builtin_firmware(cp, fw_name); +#else + return false; +#endif +} + +void __init load_ucode_amd_bsp(unsigned int family) { struct cpio_data cp; void **data; @@ -243,8 +259,10 @@ void __init load_ucode_amd_bsp(void) #endif cp = find_ucode_in_initrd(); - if (!cp.data) - return; + if (!cp.data) { + if (!load_builtin_amd_microcode(&cp, family)) + return; + } *data = cp.data; *size = cp.size; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 36a83617e..6236a54a6 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -1,74 +1,16 @@ /* - * Intel CPU Microcode Update Driver for Linux + * CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> + * 2013-2015 Borislav Petkov <bp@alien8.de> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. + * This driver allows to upgrade microcode on x86 processors. * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: - * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index a413a69cb..8ebc421d6 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -3,6 +3,7 @@ * * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> * H Peter Anvin" <hpa@zytor.com> + * (C) 2015 Borislav Petkov <bp@alien8.de> * * This driver allows to early upgrade microcode on Intel processors * belonging to IA-32 family - PentiumPro, Pentium II, @@ -17,6 +18,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> +#include <linux/firmware.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/microcode_amd.h> @@ -43,9 +45,29 @@ static bool __init check_loader_disabled_bsp(void) return *res; } +extern struct builtin_fw __start_builtin_fw[]; +extern struct builtin_fw __end_builtin_fw[]; + +bool get_builtin_firmware(struct cpio_data *cd, const char *name) +{ +#ifdef CONFIG_FW_LOADER + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { + if (!strcmp(name, b_fw->name)) { + cd->size = b_fw->size; + cd->data = b_fw->data; + return true; + } + } +#endif + return false; +} + void __init load_ucode_bsp(void) { - int vendor, family; + int vendor; + unsigned int family; if (check_loader_disabled_bsp()) return; @@ -63,7 +85,7 @@ void __init load_ucode_bsp(void) break; case X86_VENDOR_AMD: if (family >= 0x10) - load_ucode_amd_bsp(); + load_ucode_amd_bsp(family); break; default: break; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a493d9d5a..2869d81ff 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -1,74 +1,13 @@ /* - * Intel CPU Microcode Update Driver for Linux + * Intel CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: - * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -124,7 +63,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) cpf = cpu_sig.pf; crev = cpu_sig.rev; - return get_matching_microcode(csig, cpf, crev, mc_intel); + return has_newer_microcode(mc_intel, csig, cpf, crev); } static int apply_microcode_intel(int cpu) @@ -226,7 +165,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, csig = uci->cpu_sig.sig; cpf = uci->cpu_sig.pf; - if (get_matching_microcode(csig, cpf, new_rev, mc)) { + if (has_newer_microcode(mc, csig, cpf, new_rev)) { vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 4d843f80e..6b5021fc3 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -59,10 +59,10 @@ load_microcode_early(struct microcode_intel **saved, ucode_ptr = saved[i]; mc_hdr = (struct microcode_header_intel *)ucode_ptr; - ret = get_matching_microcode(uci->cpu_sig.sig, - uci->cpu_sig.pf, - new_rev, - ucode_ptr); + ret = has_newer_microcode(ucode_ptr, + uci->cpu_sig.sig, + uci->cpu_sig.pf, + new_rev); if (!ret) continue; @@ -246,7 +246,7 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr, unsigned int num_saved) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - unsigned int sig, pf, new_rev; + unsigned int sig, pf; int found = 0, i; mc_hdr = (struct microcode_header_intel *)ucode_ptr; @@ -255,14 +255,13 @@ static unsigned int _save_mc(struct microcode_intel **mc_saved, mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; sig = mc_saved_hdr->sig; pf = mc_saved_hdr->pf; - new_rev = mc_hdr->rev; - if (!get_matching_sig(sig, pf, new_rev, ucode_ptr)) + if (!find_matching_signature(ucode_ptr, sig, pf)) continue; found = 1; - if (!revision_is_newer(mc_hdr, new_rev)) + if (mc_hdr->rev <= mc_saved_hdr->rev) continue; /* @@ -522,6 +521,27 @@ out: EXPORT_SYMBOL_GPL(save_mc_for_early); #endif +static bool __init load_builtin_intel_microcode(struct cpio_data *cp) +{ +#ifdef CONFIG_X86_64 + unsigned int eax = 0x00000001, ebx, ecx = 0, edx; + unsigned int family, model, stepping; + char name[30]; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + family = __x86_family(eax); + model = x86_model(eax); + stepping = eax & 0xf; + + sprintf(name, "/*(DEBLOBBED)*/", family, model, stepping); + + return get_builtin_firmware(cp, name); +#else + return false; +#endif +} + static __initdata char ucode_name[] = "/*(DEBLOBBED)*/"; static __init enum ucode_state scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, @@ -540,8 +560,10 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.size = 0; cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) - return UCODE_ERROR; + if (!cd.data) { + if (!load_builtin_intel_microcode(&cd)) + return UCODE_ERROR; + } return get_matching_model_microcode(0, start, cd.data, cd.size, mc_saved_data, initrd, uci); diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index cd47a510a..1883d252f 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -31,11 +31,18 @@ #include <asm/processor.h> #include <asm/msr.h> -static inline int -update_match_cpu(unsigned int csig, unsigned int cpf, - unsigned int sig, unsigned int pf) +static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, + unsigned int s2, unsigned int p2) { - return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1; + if (s1 != s2) + return false; + + /* Processor flags are either both 0 ... */ + if (!p1 && !p2) + return true; + + /* ... or they intersect. */ + return p1 & p2; } int microcode_sanity_check(void *mc, int print_err) @@ -124,27 +131,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check); /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) +int find_matching_signature(void *mc, unsigned int csig, int cpf) { - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - int ext_sigcount, i; + struct microcode_header_intel *mc_hdr = mc; + struct extended_sigtable *ext_hdr; struct extended_signature *ext_sig; + int i; - if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf)) + if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) return 1; /* Look for ext. headers: */ - if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) + if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) return 0; - ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; + ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; - for (i = 0; i < ext_sigcount; i++) { - if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf)) + for (i = 0; i < ext_hdr->count; i++) { + if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) return 1; ext_sig++; } @@ -154,13 +159,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc) +int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) { struct microcode_header_intel *mc_hdr = mc; - if (!revision_is_newer(mc_hdr, rev)) + if (mc_hdr->rev <= new_rev) return 0; - return get_matching_sig(csig, cpf, rev, mc); + return find_matching_signature(mc, csig, cpf); } -EXPORT_SYMBOL_GPL(get_matching_microcode); +EXPORT_SYMBOL_GPL(has_newer_microcode); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 939155ffd..aad4bd84b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -39,14 +39,12 @@ void hyperv_vector_handler(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - irq_enter(); - exit_idle(); - + entering_irq(); inc_irq_stat(irq_hv_callback_count); if (vmbus_handler) vmbus_handler(); - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 5f90b85ff..70d7c93f4 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, continue; base = range_state[i].base_pfn; if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed && - (mtrr_state.enabled & 1)) { + (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { /* Var MTRR contains UC entry below 1M? Skip it: */ printk(BIOS_BUG_MSG, i); if (base + size <= (1<<(20-PAGE_SHIFT))) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 7d74f7b3c..3b533cf37 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr) return 0; } -/* - * Error/Semi-error returns: - * 0xFF - when MTRR is not enabled - * *repeat == 1 implies [start:end] spanned across MTRR range and type returned - * corresponds only to [start:*partial_end]. - * Caller has to lookup again for [*partial_end:end]. +/** + * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries + * + * Return the MTRR fixed memory type of 'start'. + * + * MTRR fixed entries are divided into the following ways: + * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges + * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges + * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges + * + * Return Values: + * MTRR_TYPE_(type) - Matched memory type + * MTRR_TYPE_INVALID - Unmatched + */ +static u8 mtrr_type_lookup_fixed(u64 start, u64 end) +{ + int idx; + + if (start >= 0x100000) + return MTRR_TYPE_INVALID; + + /* 0x0 - 0x7FFFF */ + if (start < 0x80000) { + idx = 0; + idx += (start >> 16); + return mtrr_state.fixed_ranges[idx]; + /* 0x80000 - 0xBFFFF */ + } else if (start < 0xC0000) { + idx = 1 * 8; + idx += ((start - 0x80000) >> 14); + return mtrr_state.fixed_ranges[idx]; + } + + /* 0xC0000 - 0xFFFFF */ + idx = 3 * 8; + idx += ((start - 0xC0000) >> 12); + return mtrr_state.fixed_ranges[idx]; +} + +/** + * mtrr_type_lookup_variable - look up memory type in MTRR variable entries + * + * Return Value: + * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched) + * + * Output Arguments: + * repeat - Set to 1 when [start:end] spanned across MTRR range and type + * returned corresponds only to [start:*partial_end]. Caller has + * to lookup again for [*partial_end:end]. + * + * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the + * region is fully covered by a single MTRR entry or the default + * type. */ -static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) +static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, + int *repeat, u8 *uniform) { int i; u64 base, mask; u8 prev_match, curr_match; *repeat = 0; - if (!mtrr_state_set) - return 0xFF; - - if (!mtrr_state.enabled) - return 0xFF; + *uniform = 1; - /* Make end inclusive end, instead of exclusive */ + /* Make end inclusive instead of exclusive */ end--; - /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state.have_fixed && (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state.fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state.fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state.fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - if (!(mtrr_state.enabled & 2)) - return mtrr_state.def_type; - - prev_match = 0xFF; + prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; + unsigned short start_state, end_state, inclusive; if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11))) continue; @@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) start_state = ((start & mask) == (base & mask)); end_state = ((end & mask) == (base & mask)); + inclusive = ((start < base) && (end > base)); - if (start_state != end_state) { + if ((start_state != end_state) || inclusive) { /* * We have start:end spanning across an MTRR. - * We split the region into - * either - * (start:mtrr_end) (mtrr_end:end) - * or - * (start:mtrr_start) (mtrr_start:end) + * We split the region into either + * + * - start_state:1 + * (start:mtrr_end)(mtrr_end:end) + * - end_state:1 + * (start:mtrr_start)(mtrr_start:end) + * - inclusive:1 + * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end) + * * depending on kind of overlap. - * Return the type for first region and a pointer to - * the start of second region so that caller will - * lookup again on the second region. - * Note: This way we handle multiple overlaps as well. + * + * Return the type of the first region and a pointer + * to the start of next region so that caller will be + * advised to lookup again after having adjusted start + * and end. + * + * Note: This way we handle overlaps with multiple + * entries and the default type properly. */ if (start_state) *partial_end = base + get_mtrr_size(mask); @@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) end = *partial_end - 1; /* end is inclusive */ *repeat = 1; + *uniform = 0; } if ((start & mask) != (base & mask)) continue; curr_match = mtrr_state.var_ranges[i].base_lo & 0xff; - if (prev_match == 0xFF) { + if (prev_match == MTRR_TYPE_INVALID) { prev_match = curr_match; continue; } + *uniform = 0; if (check_type_overlap(&prev_match, &curr_match)) return curr_match; } - if (mtrr_tom2) { - if (start >= (1ULL<<32) && (end < mtrr_tom2)) - return MTRR_TYPE_WRBACK; - } - - if (prev_match != 0xFF) + if (prev_match != MTRR_TYPE_INVALID) return prev_match; return mtrr_state.def_type; } -/* - * Returns the effective MTRR type for the region - * Error return: - * 0xFF - when MTRR is not enabled +/** + * mtrr_type_lookup - look up memory type in MTRR + * + * Return Values: + * MTRR_TYPE_(type) - The effective MTRR type for the region + * MTRR_TYPE_INVALID - MTRR is disabled + * + * Output Argument: + * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the + * region is fully covered by a single MTRR entry or the default + * type. */ -u8 mtrr_type_lookup(u64 start, u64 end) +u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { - u8 type, prev_type; + u8 type, prev_type, is_uniform = 1, dummy; int repeat; u64 partial_end; - type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + if (!mtrr_state_set) + return MTRR_TYPE_INVALID; + + if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) + return MTRR_TYPE_INVALID; + + /* + * Look up the fixed ranges first, which take priority over + * the variable ranges. + */ + if ((start < 0x100000) && + (mtrr_state.have_fixed) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { + is_uniform = 0; + type = mtrr_type_lookup_fixed(start, end); + goto out; + } + + /* + * Look up the variable ranges. Look of multiple ranges matching + * this address and pick type as per MTRR precedence. + */ + type = mtrr_type_lookup_variable(start, end, &partial_end, + &repeat, &is_uniform); /* * Common path is with repeat = 0. * However, we can have cases where [start:end] spans across some - * MTRR range. Do repeated lookups for that case here. + * MTRR ranges and/or the default type. Do repeated lookups for + * that case here. */ while (repeat) { prev_type = type; start = partial_end; - type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + is_uniform = 0; + type = mtrr_type_lookup_variable(start, end, &partial_end, + &repeat, &dummy); if (check_type_overlap(&prev_type, &type)) - return type; + goto out; } + if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2)) + type = MTRR_TYPE_WRBACK; + +out: + *uniform = is_uniform; return type; } @@ -347,7 +408,9 @@ static void __init print_mtrr_state(void) mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { pr_debug("MTRR fixed ranges %sabled:\n", - mtrr_state.enabled & 1 ? "en" : "dis"); + ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? + "en" : "dis"); print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); for (i = 0; i < 2; ++i) print_fixed(0x80000 + i * 0x20000, 0x04000, @@ -360,7 +423,7 @@ static void __init print_mtrr_state(void) print_fixed_last(); } pr_debug("MTRR variable ranges %sabled:\n", - mtrr_state.enabled & 2 ? "en" : "dis"); + mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { @@ -382,7 +445,7 @@ static void __init print_mtrr_state(void) } /* Grab all of the MTRR state for this CPU into *state */ -void __init get_mtrr_state(void) +bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; unsigned long flags; @@ -426,6 +489,8 @@ void __init get_mtrr_state(void) post_set(); local_irq_restore(flags); + + return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } /* Some BIOS's are messed up and don't set all MTRRs the same! */ diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index ea5f363a1..e7ed0d8eb 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -59,6 +59,12 @@ #define MTRR_TO_PHYS_WC_OFFSET 1000 u32 num_var_ranges; +static bool __mtrr_enabled; + +static bool mtrr_enabled(void) +{ + return __mtrr_enabled; +} unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; static DEFINE_MUTEX(mtrr_mutex); @@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, int i, replace, error; mtrr_type ltype; - if (!mtrr_if) + if (!mtrr_enabled()) return -ENXIO; error = mtrr_if->validate_add_page(base, size, type); @@ -435,6 +441,8 @@ static int mtrr_check(unsigned long base, unsigned long size) int mtrr_add(unsigned long base, unsigned long size, unsigned int type, bool increment) { + if (!mtrr_enabled()) + return -ENODEV; if (mtrr_check(base, size)) return -EINVAL; return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type, @@ -463,8 +471,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) unsigned long lbase, lsize; int error = -EINVAL; - if (!mtrr_if) - return -ENXIO; + if (!mtrr_enabled()) + return -ENODEV; max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ @@ -523,6 +531,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) */ int mtrr_del(int reg, unsigned long base, unsigned long size) { + if (!mtrr_enabled()) + return -ENODEV; if (mtrr_check(base, size)) return -EINVAL; return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT); @@ -538,6 +548,9 @@ EXPORT_SYMBOL(mtrr_del); * attempts to add a WC MTRR covering size bytes starting at base and * logs an error if this fails. * + * The called should provide a power of two size on an equivalent + * power of two boundary. + * * Drivers must store the return value to pass to mtrr_del_wc_if_needed, * but drivers should not try to interpret that return value. */ @@ -545,7 +558,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size) { int ret; - if (pat_enabled) + if (pat_enabled() || !mtrr_enabled()) return 0; /* Success! (We don't need to do anything.) */ ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true); @@ -577,7 +590,7 @@ void arch_phys_wc_del(int handle) EXPORT_SYMBOL(arch_phys_wc_del); /* - * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value + * arch_phys_wc_index - translates arch_phys_wc_add's return value * @handle: Return value from arch_phys_wc_add * * This will turn the return value from arch_phys_wc_add into an mtrr @@ -587,14 +600,14 @@ EXPORT_SYMBOL(arch_phys_wc_del); * in printk line. Alas there is an illegitimate use in some ancient * drm ioctls. */ -int phys_wc_to_mtrr_index(int handle) +int arch_phys_wc_index(int handle) { if (handle < MTRR_TO_PHYS_WC_OFFSET) return -1; else return handle - MTRR_TO_PHYS_WC_OFFSET; } -EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index); +EXPORT_SYMBOL_GPL(arch_phys_wc_index); /* * HACK ALERT! @@ -734,10 +747,12 @@ void __init mtrr_bp_init(void) } if (mtrr_if) { + __mtrr_enabled = true; set_num_var_ranges(); init_table(); if (use_intel()) { - get_mtrr_state(); + /* BIOS may override */ + __mtrr_enabled = get_mtrr_state(); if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; @@ -745,10 +760,16 @@ void __init mtrr_bp_init(void) } } } + + if (!mtrr_enabled()) + pr_info("MTRR: Disabled\n"); } void mtrr_ap_init(void) { + if (!mtrr_enabled()) + return; + if (!use_intel() || mtrr_aps_delayed_init) return; /* @@ -774,6 +795,9 @@ void mtrr_save_state(void) { int first_cpu; + if (!mtrr_enabled()) + return; + get_online_cpus(); first_cpu = cpumask_first(cpu_online_mask); smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); @@ -782,6 +806,8 @@ void mtrr_save_state(void) void set_mtrr_aps_delayed_init(void) { + if (!mtrr_enabled()) + return; if (!use_intel()) return; @@ -793,7 +819,7 @@ void set_mtrr_aps_delayed_init(void) */ void mtrr_aps_init(void) { - if (!use_intel()) + if (!use_intel() || !mtrr_enabled()) return; /* @@ -810,7 +836,7 @@ void mtrr_aps_init(void) void mtrr_bp_restore(void) { - if (!use_intel()) + if (!use_intel() || !mtrr_enabled()) return; mtrr_if->set_all(); @@ -818,7 +844,7 @@ void mtrr_bp_restore(void) static int __init mtrr_init_finialize(void) { - if (!mtrr_if) + if (!mtrr_enabled()) return 0; if (use_intel()) { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index df5e41f31..951884dcc 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -51,7 +51,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); -void get_mtrr_state(void); +bool get_mtrr_state(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index aa4e3a74e..9469dfa55 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) } static atomic_t active_events; +static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC @@ -271,6 +272,7 @@ msr_fail: static void hw_perf_event_destroy(struct perf_event *event) { x86_release_hardware(); + atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) @@ -324,16 +326,16 @@ int x86_reserve_hardware(void) { int err = 0; - if (!atomic_inc_not_zero(&active_events)) { + if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); - if (atomic_read(&active_events) == 0) { + if (atomic_read(&pmc_refcount) == 0) { if (!reserve_pmc_hardware()) err = -EBUSY; else reserve_ds_buffers(); } if (!err) - atomic_inc(&active_events); + atomic_inc(&pmc_refcount); mutex_unlock(&pmc_reserve_mutex); } @@ -342,7 +344,7 @@ int x86_reserve_hardware(void) void x86_release_hardware(void) { - if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { + if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { release_pmc_hardware(); release_ds_buffers(); mutex_unlock(&pmc_reserve_mutex); @@ -355,28 +357,30 @@ void x86_release_hardware(void) */ int x86_add_exclusive(unsigned int what) { - int ret = -EBUSY, i; - - if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) - return 0; + int i; - mutex_lock(&pmc_reserve_mutex); - for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { - if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) - goto out; + if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { + mutex_lock(&pmc_reserve_mutex); + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { + if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) + goto fail_unlock; + } + atomic_inc(&x86_pmu.lbr_exclusive[what]); + mutex_unlock(&pmc_reserve_mutex); } - atomic_inc(&x86_pmu.lbr_exclusive[what]); - ret = 0; + atomic_inc(&active_events); + return 0; -out: +fail_unlock: mutex_unlock(&pmc_reserve_mutex); - return ret; + return -EBUSY; } void x86_del_exclusive(unsigned int what) { atomic_dec(&x86_pmu.lbr_exclusive[what]); + atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -557,6 +561,7 @@ static int __x86_pmu_event_init(struct perf_event *event) if (err) return err; + atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; @@ -895,10 +900,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } - } - - if (!assign || unsched) { - + } else { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -1111,13 +1113,16 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || + local64_read(&hwc->prev_count) != (u64)-left) { + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + } /* * Due to erratum on certan cpu we need @@ -1429,6 +1434,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) u64 finish_clock; int ret; + /* + * All PMUs/events that share this PMI handler should make sure to + * increment active_events for their events. + */ if (!atomic_read(&active_events)) return NMI_DONE; @@ -2170,21 +2179,25 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + struct ldt_struct *ldt; + if (idx > LDT_ENTRIES) return 0; - if (idx > current->active_mm->context.size) + /* IRQs are off, so this synchronizes with smp_store_release */ + ldt = lockless_dereference(current->active_mm->context.ldt); + if (!ldt || idx > ldt->size) return 0; - desc = current->active_mm->context.ldt; + desc = &ldt->entries[idx]; } else { if (idx > GDT_ENTRIES) return 0; - desc = raw_cpu_ptr(gdt_page.gdt); + desc = raw_cpu_ptr(gdt_page.gdt) + idx; } - return get_desc_base(desc + idx); + return get_desc_base(desc); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index f068695ea..3e7fd27df 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -75,6 +75,8 @@ struct event_constraint { #define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ struct amd_nb { @@ -88,6 +90,18 @@ struct amd_nb { #define MAX_PEBS_EVENTS 8 /* + * Flags PEBS can handle without an PMI. + * + * TID can only be handled by flushing at context switch. + * + */ +#define PEBS_FREERUNNING_FLAGS \ + (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ + PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ + PERF_SAMPLE_TRANSACTION) + +/* * A debug store configuration. * * We only support architectures that use 64bit fields. @@ -133,7 +147,6 @@ enum intel_excl_state_type { }; struct intel_excl_states { - enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; enum intel_excl_state_type state[X86_PMC_IDX_MAX]; bool sched_started; /* true if scheduling has started */ }; @@ -527,10 +540,10 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); - void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); - void (*start_scheduling)(struct cpu_hw_events *cpuc); + void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); + void (*stop_scheduling)(struct cpu_hw_events *cpuc); struct event_constraint *event_constraints; @@ -870,6 +883,8 @@ void intel_pmu_pebs_enable_all(void); void intel_pmu_pebs_disable_all(void); +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2813ea0f1..6326ae24e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1903,9 +1903,8 @@ static void intel_start_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1916,10 +1915,9 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; xl->sched_started = true; @@ -1928,22 +1926,41 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) * in stop_event_scheduling() * makes scheduling appear as a transaction */ - WARN_ON_ONCE(!irqs_disabled()); raw_spin_lock(&excl_cntrs->lock); +} - /* - * save initial state of sibling thread - */ - memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = cpuc->event_constraint[idx]; + struct intel_excl_states *xl; + int tid = cpuc->excl_thread_id; + + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + if (WARN_ON_ONCE(!excl_cntrs)) + return; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + xl = &excl_cntrs->states[tid]; + + lockdep_assert_held(&excl_cntrs->lock); + + if (c->flags & PERF_X86_EVENT_EXCL) + xl->state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xl->state[cntr] = INTEL_EXCL_SHARED; } static void intel_stop_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1953,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; - /* - * make new sibling thread state visible - */ - memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); - xl->sched_started = false; /* * release shared state lock (acquired in intel_start_scheduling()) @@ -1975,12 +1986,10 @@ static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { - struct event_constraint *cx; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; - int is_excl, i; + struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* alternate */ + int is_excl, i; /* * validating a group does not require @@ -1992,27 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return c; - /* - * event requires exclusive counter access - * across HT threads - */ - is_excl = c->flags & PERF_X86_EVENT_EXCL; - if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { - event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; - if (!cpuc->n_excl++) - WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); - } - - /* - * xl = state of current HT - * xlo = state of sibling HT - */ - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - cx = c; /* * because we modify the constraint, we need @@ -2023,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * been cloned (marked dynamic) */ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - - /* sanity check */ - if (idx < 0) - return &emptyconstraint; + struct event_constraint *cx; /* * grab pre-allocated constraint entry @@ -2037,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * initialize dynamic constraint * with static constraint */ - memcpy(cx, c, sizeof(*cx)); + *cx = *c; /* * mark constraint as dynamic, so we * can free it later on */ cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; } /* @@ -2054,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, */ /* + * state of sibling HT + */ + xlo = &excl_cntrs->states[tid ^ 1]; + + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { + event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; + if (!cpuc->n_excl++) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); + } + + /* * Modify static constraint with current dynamic * state of thread * @@ -2061,37 +2065,37 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ - for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) - __clear_bit(i, cx->idxmsk); + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, c->idxmsk); /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) - __clear_bit(i, cx->idxmsk); + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, c->idxmsk); } /* * recompute actual bit weight for scheduling algorithm */ - cx->weight = hweight64(cx->idxmsk64); + c->weight = hweight64(c->idxmsk64); /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (cx->weight == 0) - cx = &emptyconstraint; + if (c->weight == 0) + c = &emptyconstraint; - return cx; + return c; } static struct event_constraint * @@ -2124,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, { struct hw_perf_event *hwc = &event->hw; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xlo, *xl; - unsigned long flags = 0; /* keep compiler happy */ int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; + struct intel_excl_states *xl; /* * nothing needed if in group validation mode @@ -2135,13 +2137,9 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, if (cpuc->is_fake) return; - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) { hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT; if (!--cpuc->n_excl) @@ -2149,22 +2147,25 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, } /* - * put_constraint may be called from x86_schedule_events() - * which already has the lock held so here make locking - * conditional + * If event was actually assigned, then mark the counter state as + * unused now. */ - if (!xl->sched_started) - raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + if (hwc->idx >= 0) { + xl = &excl_cntrs->states[tid]; - /* - * if event was actually assigned, then mark the - * counter state as unused now - */ - if (hwc->idx >= 0) - xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional. + */ + if (!xl->sched_started) + raw_spin_lock(&excl_cntrs->lock); - if (!xl->sched_started) - raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); + xl->state[hwc->idx] = INTEL_EXCL_UNUSED; + + if (!xl->sched_started) + raw_spin_unlock(&excl_cntrs->lock); + } } static void @@ -2196,41 +2197,6 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc, intel_put_excl_constraints(cpuc, event); } -static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) -{ - struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct event_constraint *c = cpuc->event_constraint[idx]; - struct intel_excl_states *xlo, *xl; - int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; - int is_excl; - - if (cpuc->is_fake || !c) - return; - - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) - return; - - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) - return; - - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); - - if (cntr >= 0) { - if (is_excl) - xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; - else - xlo->init_state[cntr] = INTEL_EXCL_SHARED; - } -} - static void intel_pebs_aliases_core2(struct perf_event *event) { if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { @@ -2294,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; - if (event->attr.precise_ip && x86_pmu.pebs_aliases) - x86_pmu.pebs_aliases(event); + if (event->attr.precise_ip) { + if (!event->attr.freq) { + event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; + if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS)) + event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + } + if (x86_pmu.pebs_aliases) + x86_pmu.pebs_aliases(event); + } if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); @@ -2544,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) { struct intel_excl_cntrs *c; - int i; c = kzalloc_node(sizeof(struct intel_excl_cntrs), GFP_KERNEL, cpu_to_node(cpu)); if (c) { raw_spin_lock_init(&c->lock); - for (i = 0; i < X86_PMC_IDX_MAX; i++) { - c->states[0].state[i] = INTEL_EXCL_UNUSED; - c->states[0].init_state[i] = INTEL_EXCL_UNUSED; - - c->states[1].state[i] = INTEL_EXCL_UNUSED; - c->states[1].init_state[i] = INTEL_EXCL_UNUSED; - } c->core_id = -1; } return c; @@ -2569,7 +2534,7 @@ static int intel_pmu_cpu_prepare(int cpu) if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) - return NOTIFY_BAD; + goto err; } if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { @@ -2577,18 +2542,27 @@ static int intel_pmu_cpu_prepare(int cpu) cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); if (!cpuc->constraint_list) - return NOTIFY_BAD; + goto err_shared_regs; cpuc->excl_cntrs = allocate_excl_cntrs(cpu); - if (!cpuc->excl_cntrs) { - kfree(cpuc->constraint_list); - kfree(cpuc->shared_regs); - return NOTIFY_BAD; - } + if (!cpuc->excl_cntrs) + goto err_constraint_list; + cpuc->excl_thread_id = 0; } return NOTIFY_OK; + +err_constraint_list: + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + +err_shared_regs: + kfree(cpuc->shared_regs); + cpuc->shared_regs = NULL; + +err: + return NOTIFY_BAD; } static void intel_pmu_cpu_starting(int cpu) @@ -2611,7 +2585,7 @@ static void intel_pmu_cpu_starting(int cpu) if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; @@ -2629,7 +2603,7 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_excl_cntrs *c; c = per_cpu(cpu_hw_events, i).excl_cntrs; @@ -2677,6 +2651,15 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + if (x86_pmu.pebs_active) + intel_pmu_pebs_sched_task(ctx, sched_in); + if (x86_pmu.lbr_nr) + intel_pmu_lbr_sched_task(ctx, sched_in); +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -2766,7 +2749,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .sched_task = intel_pmu_lbr_sched_task, + .sched_task = intel_pmu_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2939,8 +2922,8 @@ static __init void intel_ht_bug(void) { x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; - x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.stop_scheduling = intel_stop_scheduling; } @@ -3388,7 +3371,7 @@ static __init int fixup_ht_bug(void) if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) return 0; - w = cpumask_weight(topology_thread_cpumask(cpu)); + w = cpumask_weight(topology_sibling_cpumask(cpu)); if (w > 1) { pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); return 0; @@ -3398,8 +3381,8 @@ static __init int fixup_ht_bug(void) x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); - x86_pmu.commit_scheduling = NULL; x86_pmu.start_scheduling = NULL; + x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; watchdog_nmi_enable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c index 7795f3f8b..43dd672d7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -530,5 +530,4 @@ static __init int bts_init(void) return perf_pmu_register(&bts_pmu, "intel_bts", -1); } - -module_init(bts_init); +arch_initcall(bts_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index cb77b11bc..377e8f8ed 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -13,16 +13,35 @@ #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d -static unsigned int cqm_max_rmid = -1; +static u32 cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -struct intel_cqm_state { - raw_spinlock_t lock; - int rmid; - int cnt; +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @rmid_usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 rmid; + u32 closid; + int rmid_usecnt; }; -static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Both functions which modify the state + * (intel_cqm_event_start and intel_cqm_event_stop) are called with + * interrupts disabled, which is sufficient for the protection. + */ +static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. @@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask; * near-zero occupancy value, i.e. no cachelines are tagged with this * RMID, once __intel_cqm_rmid_rotate() returns. */ -static unsigned int intel_cqm_rotation_rmid; +static u32 intel_cqm_rotation_rmid; #define INVALID_RMID (-1) @@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid; * Likewise, an rmid value of -1 is used to indicate "no rmid currently * assigned" and is used as part of the rotation code. */ -static inline bool __rmid_valid(unsigned int rmid) +static inline bool __rmid_valid(u32 rmid) { if (!rmid || rmid == INVALID_RMID) return false; @@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid) return true; } -static u64 __rmid_read(unsigned int rmid) +static u64 __rmid_read(u32 rmid) { u64 val; @@ -102,7 +121,7 @@ enum rmid_recycle_state { }; struct cqm_rmid_entry { - unsigned int rmid; + u32 rmid; enum rmid_recycle_state state; struct list_head list; unsigned long queue_time; @@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru); */ static struct cqm_rmid_entry **cqm_rmid_ptrs; -static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) { struct cqm_rmid_entry *entry; @@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid) * * We expect to be called with cache_mutex held. */ -static int __get_rmid(void) +static u32 __get_rmid(void) { struct cqm_rmid_entry *entry; @@ -177,7 +196,7 @@ static int __get_rmid(void) return entry->rmid; } -static void __put_rmid(unsigned int rmid) +static void __put_rmid(u32 rmid) { struct cqm_rmid_entry *entry; @@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b) } struct rmid_read { - unsigned int rmid; + u32 rmid; atomic64_t value; }; @@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info); /* * Exchange the RMID of a group of events. */ -static unsigned int -intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) { struct perf_event *event; - unsigned int old_rmid = group->hw.cqm_rmid; struct list_head *head = &group->hw.cqm_group_entry; + u32 old_rmid = group->hw.cqm_rmid; lockdep_assert_held(&cache_mutex); @@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg) * If we have group events waiting for an RMID that don't conflict with * events already running, assign @rmid. */ -static bool intel_cqm_sched_in_event(unsigned int rmid) +static bool intel_cqm_sched_in_event(u32 rmid) { struct perf_event *leader, *event; @@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available) static void __intel_cqm_pick_and_rotate(struct perf_event *next) { struct perf_event *rotor; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next) static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) { struct perf_event *group, *g; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event, struct perf_event **group) { struct perf_event *iter; - unsigned int rmid; bool conflict = false; + u32 rmid; list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { rmid = iter->hw.cqm_rmid; @@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event, static void intel_cqm_event_read(struct perf_event *event) { unsigned long flags; - unsigned int rmid; + u32 rmid; u64 val; /* @@ -969,55 +987,48 @@ out: static void intel_cqm_event_start(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned int rmid = event->hw.cqm_rmid; - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 rmid = event->hw.cqm_rmid; if (!(event->hw.cqm_state & PERF_HES_STOPPED)) return; event->hw.cqm_state &= ~PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); - - if (state->cnt++) - WARN_ON_ONCE(state->rmid != rmid); - else + if (state->rmid_usecnt++) { + if (!WARN_ON_ONCE(state->rmid != rmid)) + return; + } else { WARN_ON_ONCE(state->rmid); + } state->rmid = rmid; - wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); - - raw_spin_unlock_irqrestore(&state->lock, flags); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); } static void intel_cqm_event_stop(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); if (event->hw.cqm_state & PERF_HES_STOPPED) return; event->hw.cqm_state |= PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); intel_cqm_event_read(event); - if (!--state->cnt) { + if (!--state->rmid_usecnt) { state->rmid = 0; - wrmsrl(MSR_IA32_PQR_ASSOC, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); } else { WARN_ON_ONCE(!state->rmid); } - - raw_spin_unlock_irqrestore(&state->lock, flags); } static int intel_cqm_event_add(struct perf_event *event, int mode) { unsigned long flags; - unsigned int rmid; + u32 rmid; raw_spin_lock_irqsave(&cache_lock, flags); @@ -1032,11 +1043,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode) return 0; } -static void intel_cqm_event_del(struct perf_event *event, int mode) -{ - intel_cqm_event_stop(event, mode); -} - static void intel_cqm_event_destroy(struct perf_event *event) { struct perf_event *group_other = NULL; @@ -1065,7 +1071,7 @@ static void intel_cqm_event_destroy(struct perf_event *event) list_replace(&event->hw.cqm_groups_entry, &group_other->hw.cqm_groups_entry); } else { - unsigned int rmid = event->hw.cqm_rmid; + u32 rmid = event->hw.cqm_rmid; if (__rmid_valid(rmid)) __put_rmid(rmid); @@ -1229,7 +1235,7 @@ static struct pmu intel_cqm_pmu = { .task_ctx_nr = perf_sw_context, .event_init = intel_cqm_event_init, .add = intel_cqm_event_add, - .del = intel_cqm_event_del, + .del = intel_cqm_event_stop, .start = intel_cqm_event_start, .stop = intel_cqm_event_stop, .read = intel_cqm_event_read, @@ -1249,14 +1255,14 @@ static inline void cqm_pick_event_reader(int cpu) cpumask_set_cpu(cpu, &cqm_cpumask); } -static void intel_cqm_cpu_prepare(unsigned int cpu) +static void intel_cqm_cpu_starting(unsigned int cpu) { - struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); - raw_spin_lock_init(&state->lock); state->rmid = 0; - state->cnt = 0; + state->closid = 0; + state->rmid_usecnt = 0; WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); @@ -1290,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb, unsigned int cpu = (unsigned long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - intel_cqm_cpu_prepare(cpu); - break; case CPU_DOWN_PREPARE: intel_cqm_cpu_exit(cpu); break; case CPU_STARTING: + intel_cqm_cpu_starting(cpu); cqm_pick_event_reader(cpu); break; } @@ -1367,7 +1371,7 @@ static int __init intel_cqm_init(void) goto out; for_each_online_cpu(i) { - intel_cqm_cpu_prepare(i); + intel_cqm_cpu_starting(i); cqm_pick_event_reader(i); } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 7f73b3553..71fc40238 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -11,7 +11,7 @@ #define BTS_RECORD_SIZE 24 #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); - int max, thresh = 1; /* always use a single PEBS record */ + int max; void *buffer, *ibuffer; if (!x86_pmu.pebs) @@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu) ds->pebs_absolute_maximum = ds->pebs_buffer_base + max * x86_pmu.pebs_record_size; - ds->pebs_interrupt_threshold = ds->pebs_buffer_base + - thresh * x86_pmu.pebs_record_size; - return 0; } @@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void) return 1; } +static inline void intel_pmu_drain_pebs_buffer(void) +{ + struct pt_regs regs; + + x86_pmu.drain_pebs(®s); +} + +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + if (!sched_in) + intel_pmu_drain_pebs_buffer(); +} + /* * PEBS */ @@ -684,25 +694,66 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } +static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc) +{ + return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1)); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + bool first_pebs; + u64 threshold; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + first_pebs = !pebs_is_enabled(cpuc); cpuc->pebs_enabled |= 1ULL << hwc->idx; if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + + /* + * When the event is constrained enough we can use a larger + * threshold and run the event with less frequent PMI. + */ + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) { + threshold = ds->pebs_absolute_maximum - + x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + + if (first_pebs) + perf_sched_cb_inc(event->ctx->pmu); + } else { + threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + /* + * If not all events can use larger buffer, + * roll back to threshold = 1 + */ + if (!first_pebs && + (ds->pebs_interrupt_threshold > threshold)) + perf_sched_cb_dec(event->ctx->pmu); + } + + /* Use auto-reload if possible to save a MSR write in the PMI */ + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + ds->pebs_event_reset[hwc->idx] = + (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } + + if (first_pebs || ds->pebs_interrupt_threshold > threshold) + ds->pebs_interrupt_threshold = threshold; } void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -711,6 +762,13 @@ void intel_pmu_pebs_disable(struct perf_event *event) else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); + if (ds->pebs_interrupt_threshold > + ds->pebs_buffer_base + x86_pmu.pebs_record_size) { + intel_pmu_drain_pebs_buffer(); + if (!pebs_is_enabled(cpuc)) + perf_sched_cb_dec(event->ctx->pmu); + } + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) return txn; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, void *__pebs) +static void setup_pebs_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) { #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ @@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event, */ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_hsw *pebs = __pebs; - struct perf_sample_data data; - struct pt_regs regs; u64 sample_type; int fll, fst, dsrc; int fl = event->hw.flags; - if (!intel_pmu_save_and_restart(event)) + if (pebs == NULL) return; sample_type = event->attr.sample_type; @@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event, fll = fl & PERF_X86_EVENT_PEBS_LDLAT; fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); - perf_sample_data_init(&data, 0, event->hw.last_period); + perf_sample_data_init(data, 0, event->hw.last_period); - data.period = event->hw.last_period; + data->period = event->hw.last_period; /* * Use latency for weight (only avail with PEBS-LL) */ if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; + data->weight = pebs->lat; /* * data.data_src encodes the data source @@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, val = precise_datala_hsw(event, pebs->dse); else if (fst) val = precise_store_data(pebs->dse); - data.data_src.val = val; + data->data_src.val = val; } /* @@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ - regs = *iregs; - regs.flags = pebs->flags; - set_linear_ip(®s, pebs->ip); - regs.bp = pebs->bp; - regs.sp = pebs->sp; + *regs = *iregs; + regs->flags = pebs->flags; + set_linear_ip(regs, pebs->ip); + regs->bp = pebs->bp; + regs->sp = pebs->sp; if (sample_type & PERF_SAMPLE_REGS_INTR) { - regs.ax = pebs->ax; - regs.bx = pebs->bx; - regs.cx = pebs->cx; - regs.dx = pebs->dx; - regs.si = pebs->si; - regs.di = pebs->di; - regs.bp = pebs->bp; - regs.sp = pebs->sp; - - regs.flags = pebs->flags; + regs->ax = pebs->ax; + regs->bx = pebs->bx; + regs->cx = pebs->cx; + regs->dx = pebs->dx; + regs->si = pebs->si; + regs->di = pebs->di; + regs->bp = pebs->bp; + regs->sp = pebs->sp; + + regs->flags = pebs->flags; #ifndef CONFIG_X86_32 - regs.r8 = pebs->r8; - regs.r9 = pebs->r9; - regs.r10 = pebs->r10; - regs.r11 = pebs->r11; - regs.r12 = pebs->r12; - regs.r13 = pebs->r13; - regs.r14 = pebs->r14; - regs.r15 = pebs->r15; + regs->r8 = pebs->r8; + regs->r9 = pebs->r9; + regs->r10 = pebs->r10; + regs->r11 = pebs->r11; + regs->r12 = pebs->r12; + regs->r13 = pebs->r13; + regs->r14 = pebs->r14; + regs->r15 = pebs->r15; #endif } if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs->real_ip; - regs.flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) - regs.flags |= PERF_EFLAGS_EXACT; + regs->ip = pebs->real_ip; + regs->flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; else - regs.flags &= ~PERF_EFLAGS_EXACT; + regs->flags &= ~PERF_EFLAGS_EXACT; if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) - data.addr = pebs->dla; + data->addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data.weight = intel_hsw_weight(pebs); + data->weight = intel_hsw_weight(pebs); if (sample_type & PERF_SAMPLE_TRANSACTION) - data.txn = intel_hsw_transaction(pebs); + data->txn = intel_hsw_transaction(pebs); } if (has_branch_stack(event)) - data.br_stack = &cpuc->lbr_stack; + data->br_stack = &cpuc->lbr_stack; +} + +static inline void * +get_next_pebs_record_by_bit(void *base, void *top, int bit) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + void *at; + u64 pebs_status; + + if (base == NULL) + return NULL; + + for (at = base; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; + + if (test_bit(bit, (unsigned long *)&p->status)) { + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) + return at; - if (perf_event_overflow(event, &data, ®s)) + if (p->status == (1 << bit)) + return at; + + /* clear non-PEBS bit and re-check */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status == (1 << bit)) + return at; + } + } + return NULL; +} + +static void __intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + void *base, void *top, + int bit, int count) +{ + struct perf_sample_data data; + struct pt_regs regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + + if (!intel_pmu_save_and_restart(event) && + !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + return; + + while (count > 1) { + setup_pebs_sample_data(event, iregs, at, &data, ®s); + perf_event_output(event, &data, ®s); + at += x86_pmu.pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + count--; + } + + setup_pebs_sample_data(event, iregs, at, &data, ®s); + + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, ®s)) { x86_pmu_stop(event, 0); + return; + } + } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) @@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = top - at; + n = (top - at) / x86_pmu.pebs_record_size; if (n <= 0) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); - at += n - 1; - - __intel_pmu_pebs_event(event, iregs, at); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct perf_event *event = NULL; - void *at, *top; - u64 status = 0; - int bit; + struct perf_event *event; + void *base, *at, *top; + short counts[MAX_PEBS_EVENTS] = {}; + short error[MAX_PEBS_EVENTS] = {}; + int bit, i; if (!x86_pmu.pebs_active) return; - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(at > top)) + if (unlikely(base >= top)) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, - "Unexpected number of pebs records %ld\n", - (long)(top - at) / x86_pmu.pebs_record_size); - - for (; at < top; at += x86_pmu.pebs_record_size) { + for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; - for_each_set_bit(bit, (unsigned long *)&p->status, - x86_pmu.max_pebs_events) { - event = cpuc->events[bit]; - if (!test_bit(bit, cpuc->active_mask)) - continue; - - WARN_ON_ONCE(!event); + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) { + for_each_set_bit(bit, (unsigned long *)&p->status, + MAX_PEBS_EVENTS) + counts[bit]++; - if (!event->attr.precise_ip) - continue; + continue; + } - if (__test_and_set_bit(bit, (unsigned long *)&status)) + bit = find_first_bit((unsigned long *)&p->status, + x86_pmu.max_pebs_events); + if (bit >= x86_pmu.max_pebs_events) + continue; + if (!test_bit(bit, cpuc->active_mask)) + continue; + /* + * The PEBS hardware does not deal well with the situation + * when events happen near to each other and multiple bits + * are set. But it should happen rarely. + * + * If these events include one PEBS and multiple non-PEBS + * events, it doesn't impact PEBS record. The record will + * be handled normally. (slow path) + * + * If these events include two or more PEBS events, the + * records for the events can be collapsed into a single + * one, and it's not possible to reconstruct all events + * that caused the PEBS record. It's called collision. + * If collision happened, the record will be dropped. + * + */ + if (p->status != (1 << bit)) { + u64 pebs_status; + + /* slow path */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status != (1 << bit)) { + for_each_set_bit(i, (unsigned long *)&pebs_status, + MAX_PEBS_EVENTS) + error[i]++; continue; - - break; + } } + counts[bit]++; + } - if (!event || bit >= x86_pmu.max_pebs_events) + for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + if ((counts[bit] == 0) && (error[bit] == 0)) continue; + event = cpuc->events[bit]; + WARN_ON_ONCE(!event); + WARN_ON_ONCE(!event->attr.precise_ip); - __intel_pmu_pebs_event(event, iregs, at); + /* log dropped samples number */ + if (error[bit]) + perf_log_lost_samples(event, error[bit]); + + if (counts[bit]) { + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit]); + } } } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 94e5b506c..452a7bd2d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -96,6 +96,7 @@ enum { X86_BR_NO_TX = 1 << 14,/* not in transaction */ X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ + X86_BR_IND_JMP = 1 << 17,/* indirect jump */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -113,6 +114,7 @@ enum { X86_BR_IRQ |\ X86_BR_ABORT |\ X86_BR_IND_CALL |\ + X86_BR_IND_JMP |\ X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; - if (!x86_pmu.lbr_nr) - return; - /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush @@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) X86_BR_CALL_STACK; } + if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) + mask |= X86_BR_IND_JMP; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) break; case 4: case 5: - ret = X86_BR_JMP; + ret = X86_BR_IND_JMP; break; } break; @@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { */ [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_RETURN | LBR_CALL_STACK, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; /* core */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 123ff1bb2..183de7196 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ -static bool pt_is_running(void) -{ - u64 ctl; - - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - - return !!(ctl & RTIT_CTL_TRACEEN); -} - static void pt_config(struct perf_event *event) { u64 reg; @@ -609,7 +600,12 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) * @handle: Current output handle. * * Place INT and STOP marks to prevent overwriting old data that the consumer - * hasn't yet collected. + * hasn't yet collected and waking up the consumer after a certain fraction of + * the buffer has filled up. Only needed and sensible for non-snapshot counters. + * + * This obviously relies on buf::head to figure out buffer markers, so it has + * to be called after pt_buffer_reset_offsets() and before the hardware tracing + * is enabled. */ static int pt_buffer_reset_markers(struct pt_buffer *buf, struct perf_output_handle *handle) @@ -618,9 +614,6 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, unsigned long head = local64_read(&buf->head); unsigned long idx, npages, wakeup; - if (buf->snapshot) - return 0; - /* can't stop in the middle of an output region */ if (buf->output_off + handle->size + 1 < sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) @@ -674,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) struct topa *cur = buf->first, *prev = buf->last; struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), *te_prev = TOPA_ENTRY(prev, prev->last - 1); - int pg = 0, idx = 0, ntopa = 0; + int pg = 0, idx = 0; while (pg < buf->nr_pages) { int tidx; @@ -689,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) /* advance to next topa table */ idx = 0; cur = list_entry(cur->list.next, struct topa, list); - ntopa++; - } else + } else { idx++; + } te_cur = TOPA_ENTRY(cur, idx); } @@ -703,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) * @head: Write pointer (aux_head) from AUX buffer. * * Find the ToPA table and entry corresponding to given @head and set buffer's - * "current" pointers accordingly. + * "current" pointers accordingly. This is done after we have obtained the + * current aux_head position from a successful call to perf_aux_output_begin() + * to make sure the hardware is writing to the right place. + * + * This function modifies buf::{cur,cur_idx,output_off} that will be programmed + * into PT msrs when the tracing is enabled and buf::head and buf::data_size, + * which are used to determine INT and STOP markers' locations by a subsequent + * call to pt_buffer_reset_markers(). */ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) { @@ -901,6 +901,7 @@ void intel_pt_interrupt(void) } pt_buffer_reset_offsets(buf, pt->handle.head); + /* snapshot counters don't use PMI, so it's safe */ ret = pt_buffer_reset_markers(buf, &pt->handle); if (ret) { perf_aux_output_end(&pt->handle, 0, true); @@ -923,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); - if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; } @@ -954,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode) event->hw.state = PERF_HES_STOPPED; if (mode & PERF_EF_UPDATE) { - struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); if (!buf) @@ -1106,5 +1106,4 @@ static __init int pt_init(void) return ret; } - -module_init(pt_init); +arch_initcall(pt_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 358c54ad2..5cbd4e64f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -204,9 +204,8 @@ again: static void rapl_start_hrtimer(struct rapl_pmu *pmu) { - __hrtimer_start_range_ns(&pmu->hrtimer, - pmu->timer_interval, 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&pmu->hrtimer, pmu->timer_interval, + HRTIMER_MODE_REL_PINNED); } static void rapl_stop_hrtimer(struct rapl_pmu *pmu) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 90b7c501c..21b5e38c9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -233,9 +233,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { - __hrtimer_start_range_ns(&box->hrtimer, - ns_to_ktime(box->hrtimer_duration), 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), + HRTIMER_MODE_REL_PINNED); } void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) @@ -922,6 +921,9 @@ static int __init uncore_pci_init(void) case 69: /* Haswell Celeron */ ret = hsw_uncore_pci_init(); break; + case 61: /* Broadwell */ + ret = bdw_uncore_pci_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index ceac8f5dc..0f77f0a19 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -325,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty; int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); +int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 4562e9e22..b005a78c7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -7,6 +7,7 @@ #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 +#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id bdw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = { .id_table = hsw_uncore_pci_ids, }; +static struct pci_driver bdw_uncore_pci_driver = { + .name = "bdw_uncore", + .id_table = bdw_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ + IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ { /* end marker */ } }; @@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int bdw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e7d8c7608..18ca99f27 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, { #ifdef CONFIG_SMP seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu))); + seq_printf(m, "siblings\t: %d\n", + cpumask_weight(topology_core_cpumask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c76d3e37c..e068d6683 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -22,6 +22,7 @@ #include <linux/elfcore.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/processor.h> #include <asm/hardirq.h> diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 6367a780c..1f4acd68b 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -4,7 +4,6 @@ #include <linux/bootmem.h> #include <linux/export.h> #include <linux/io.h> -#include <linux/irqdomain.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/of.h> @@ -17,6 +16,7 @@ #include <linux/of_pci.h> #include <linux/initrd.h> +#include <asm/irqdomain.h> #include <asm/hpet.h> #include <asm/apic.h> #include <asm/pci_x86.h> @@ -65,7 +65,7 @@ static int __init add_bus_probe(void) return of_platform_bus_probe(NULL, ce4100_ids, NULL); } -module_init(add_bus_probe); +device_initcall(add_bus_probe); #ifdef CONFIG_PCI struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) @@ -196,38 +196,31 @@ static struct of_ioapic_type of_ioapic_type[] = }, }; -static int ioapic_xlate(struct irq_domain *domain, - struct device_node *controller, - const u32 *intspec, u32 intsize, - irq_hw_number_t *out_hwirq, u32 *out_type) +static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { + struct of_phandle_args *irq_data = (void *)arg; struct of_ioapic_type *it; - u32 line, idx, gsi; + struct irq_alloc_info tmp; - if (WARN_ON(intsize < 2)) + if (WARN_ON(irq_data->args_count < 2)) return -EINVAL; - - line = intspec[0]; - - if (intspec[1] >= ARRAY_SIZE(of_ioapic_type)) + if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = &of_ioapic_type[intspec[1]]; + it = &of_ioapic_type[irq_data->args[1]]; + ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); + tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); + tmp.ioapic_pin = irq_data->args[0]; - idx = (u32)(long)domain->host_data; - gsi = mp_pin_to_gsi(idx, line); - if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0))) - return -EBUSY; - - *out_hwirq = line; - *out_type = it->out_type; - return 0; + return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp); } -const struct irq_domain_ops ioapic_irq_domain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, - .xlate = ioapic_xlate, +static const struct irq_domain_ops ioapic_irq_domain_ops = { + .alloc = dt_irqdomain_alloc, + .free = mp_irqdomain_free, + .activate = mp_irqdomain_activate, + .deactivate = mp_irqdomain_deactivate, }; static void __init dtb_add_ioapic(struct device_node *dn) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index e2ce85db2..a102564d0 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PMEM: case E820_PRAM: printk(KERN_CONT "persistent (type %u)", type); break; @@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent RAM"; + case E820_PRAM: return "Persistent Memory (legacy)"; + case E820_PMEM: return "Persistent Memory"; default: return "reserved"; } } +static bool do_mark_busy(u32 type, struct resource *res) +{ + /* this is the legacy bios/dos rom-shadow + mmio region */ + if (res->start < (1ULL<<20)) + return true; + + /* + * Treat persistent memory like device memory, i.e. reserve it + * for exclusive use of a driver + */ + switch (type) { + case E820_RESERVED: + case E820_PRAM: + case E820_PMEM: + return false; + default: + return true; + } +} + /* * Mark e820 reserved areas as busy for the resource manager. */ @@ -952,9 +974,7 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (((e820.map[i].type != E820_RESERVED) && - (e820.map[i].type != E820_PRAM)) || - res->start < (1ULL<<20)) { + if (do_mark_busy(e820.map[i].type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } @@ -1123,7 +1143,8 @@ void __init memblock_find_dma_reserve(void) nr_pages += end_pfn - start_pfn; } - for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) { + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) { start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); if (start_pfn < end_pfn) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index fe9f0b79a..9f9cc682e 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -546,6 +546,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_BDW_D_IDS(&gen8_stolen_funcs), INTEL_CHV_IDS(&chv_stolen_funcs), INTEL_SKL_IDS(&gen9_stolen_funcs), + INTEL_BXT_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) @@ -627,8 +628,12 @@ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID, QFLAG_APPLY_ONCE, intel_graphics_stolen }, /* - * HPET on current version of Baytrail platform has accuracy - * problems, disable it for now: + * HPET on the current version of the Baytrail platform has accuracy + * problems: it will halt in deep idle state - so we disable it. + * + * More details can be found in section 18.10.1.3 of the datasheet: + * + * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 62b9e04d4..6c413d0c0 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -177,7 +177,9 @@ static __init void early_serial_init(char *s) } if (*s) { - if (kstrtoul(s, 0, &baud) < 0 || baud == 0) + baud = simple_strtoull(s, &e, 0); + + if (baud == 0 || s == e) baud = DEFAULT_BAUD; } diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S deleted file mode 100644 index 1c309763e..000000000 --- a/arch/x86/kernel/entry_32.S +++ /dev/null @@ -1,1401 +0,0 @@ -/* - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -/* - * entry.S contains the system-call and fault low-level handling routines. - * This also contains the timer-interrupt handler, as well as all interrupts - * and faults that can result in a task-switch. - * - * NOTE: This code handles signal-recognition, which happens every time - * after a timer-interrupt and after each system call. - * - * I changed all the .align's to 4 (16 byte alignment), as that's faster - * on a 486. - * - * Stack layout in 'syscall_exit': - * ptrace needs to have all regs on the stack. - * if the order here is changed, it needs to be - * updated in fork.c:copy_process, signal.c:do_signal, - * ptrace.c and ptrace.h - * - * 0(%esp) - %ebx - * 4(%esp) - %ecx - * 8(%esp) - %edx - * C(%esp) - %esi - * 10(%esp) - %edi - * 14(%esp) - %ebp - * 18(%esp) - %eax - * 1C(%esp) - %ds - * 20(%esp) - %es - * 24(%esp) - %fs - * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS - * 2C(%esp) - orig_eax - * 30(%esp) - %eip - * 34(%esp) - %cs - * 38(%esp) - %eflags - * 3C(%esp) - %oldesp - * 40(%esp) - %oldss - * - * "current" is in register %ebx during any slow entries. - */ - -#include <linux/linkage.h> -#include <linux/err.h> -#include <asm/thread_info.h> -#include <asm/irqflags.h> -#include <asm/errno.h> -#include <asm/segment.h> -#include <asm/smp.h> -#include <asm/page_types.h> -#include <asm/percpu.h> -#include <asm/dwarf2.h> -#include <asm/processor-flags.h> -#include <asm/ftrace.h> -#include <asm/irq_vectors.h> -#include <asm/cpufeature.h> -#include <asm/alternative-asm.h> -#include <asm/asm.h> -#include <asm/smap.h> - -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_LE 0x40000000 - -#ifndef CONFIG_AUDITSYSCALL -#define sysenter_audit syscall_trace_entry -#define sysexit_audit syscall_exit_work -#endif - - .section .entry.text, "ax" - -/* - * We use macros for low-level operations which need to be overridden - * for paravirtualization. The following will never clobber any registers: - * INTERRUPT_RETURN (aka. "iret") - * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") - * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). - * - * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must - * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). - * Allowing a register to be clobbered can shrink the paravirt replacement - * enough to patch inline, increasing performance. - */ - -#ifdef CONFIG_PREEMPT -#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF -#else -#define preempt_stop(clobbers) -#define resume_kernel restore_all -#endif - -.macro TRACE_IRQS_IRET -#ifdef CONFIG_TRACE_IRQFLAGS - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off? - jz 1f - TRACE_IRQS_ON -1: -#endif -.endm - -/* - * User gs save/restore - * - * %gs is used for userland TLS and kernel only uses it for stack - * canary which is required to be at %gs:20 by gcc. Read the comment - * at the top of stackprotector.h for more info. - * - * Local labels 98 and 99 are used. - */ -#ifdef CONFIG_X86_32_LAZY_GS - - /* unfortunately push/pop can't be no-op */ -.macro PUSH_GS - pushl_cfi $0 -.endm -.macro POP_GS pop=0 - addl $(4 + \pop), %esp - CFI_ADJUST_CFA_OFFSET -(4 + \pop) -.endm -.macro POP_GS_EX -.endm - - /* all the rest are no-op */ -.macro PTGS_TO_GS -.endm -.macro PTGS_TO_GS_EX -.endm -.macro GS_TO_REG reg -.endm -.macro REG_TO_PTGS reg -.endm -.macro SET_KERNEL_GS reg -.endm - -#else /* CONFIG_X86_32_LAZY_GS */ - -.macro PUSH_GS - pushl_cfi %gs - /*CFI_REL_OFFSET gs, 0*/ -.endm - -.macro POP_GS pop=0 -98: popl_cfi %gs - /*CFI_RESTORE gs*/ - .if \pop <> 0 - add $\pop, %esp - CFI_ADJUST_CFA_OFFSET -\pop - .endif -.endm -.macro POP_GS_EX -.pushsection .fixup, "ax" -99: movl $0, (%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b,99b) -.endm - -.macro PTGS_TO_GS -98: mov PT_GS(%esp), %gs -.endm -.macro PTGS_TO_GS_EX -.pushsection .fixup, "ax" -99: movl $0, PT_GS(%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b,99b) -.endm - -.macro GS_TO_REG reg - movl %gs, \reg - /*CFI_REGISTER gs, \reg*/ -.endm -.macro REG_TO_PTGS reg - movl \reg, PT_GS(%esp) - /*CFI_REL_OFFSET gs, PT_GS*/ -.endm -.macro SET_KERNEL_GS reg - movl $(__KERNEL_STACK_CANARY), \reg - movl \reg, %gs -.endm - -#endif /* CONFIG_X86_32_LAZY_GS */ - -.macro SAVE_ALL - cld - PUSH_GS - pushl_cfi %fs - /*CFI_REL_OFFSET fs, 0;*/ - pushl_cfi %es - /*CFI_REL_OFFSET es, 0;*/ - pushl_cfi %ds - /*CFI_REL_OFFSET ds, 0;*/ - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ebp - CFI_REL_OFFSET ebp, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 - movl $(__USER_DS), %edx - movl %edx, %ds - movl %edx, %es - movl $(__KERNEL_PERCPU), %edx - movl %edx, %fs - SET_KERNEL_GS %edx -.endm - -.macro RESTORE_INT_REGS - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %ecx - CFI_RESTORE ecx - popl_cfi %edx - CFI_RESTORE edx - popl_cfi %esi - CFI_RESTORE esi - popl_cfi %edi - CFI_RESTORE edi - popl_cfi %ebp - CFI_RESTORE ebp - popl_cfi %eax - CFI_RESTORE eax -.endm - -.macro RESTORE_REGS pop=0 - RESTORE_INT_REGS -1: popl_cfi %ds - /*CFI_RESTORE ds;*/ -2: popl_cfi %es - /*CFI_RESTORE es;*/ -3: popl_cfi %fs - /*CFI_RESTORE fs;*/ - POP_GS \pop -.pushsection .fixup, "ax" -4: movl $0, (%esp) - jmp 1b -5: movl $0, (%esp) - jmp 2b -6: movl $0, (%esp) - jmp 3b -.popsection - _ASM_EXTABLE(1b,4b) - _ASM_EXTABLE(2b,5b) - _ASM_EXTABLE(3b,6b) - POP_GS_EX -.endm - -.macro RING0_INT_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 3*4 - /*CFI_OFFSET cs, -2*4;*/ - CFI_OFFSET eip, -3*4 -.endm - -.macro RING0_EC_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 4*4 - /*CFI_OFFSET cs, -2*4;*/ - CFI_OFFSET eip, -3*4 -.endm - -.macro RING0_PTREGS_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, PT_OLDESP-PT_EBX - /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/ - CFI_OFFSET eip, PT_EIP-PT_OLDESP - /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/ - /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/ - CFI_OFFSET eax, PT_EAX-PT_OLDESP - CFI_OFFSET ebp, PT_EBP-PT_OLDESP - CFI_OFFSET edi, PT_EDI-PT_OLDESP - CFI_OFFSET esi, PT_ESI-PT_OLDESP - CFI_OFFSET edx, PT_EDX-PT_OLDESP - CFI_OFFSET ecx, PT_ECX-PT_OLDESP - CFI_OFFSET ebx, PT_EBX-PT_OLDESP -.endm - -ENTRY(ret_from_fork) - CFI_STARTPROC - pushl_cfi %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl_cfi %eax - pushl_cfi $0x0202 # Reset kernel eflags - popfl_cfi - jmp syscall_exit - CFI_ENDPROC -END(ret_from_fork) - -ENTRY(ret_from_kernel_thread) - CFI_STARTPROC - pushl_cfi %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl_cfi %eax - pushl_cfi $0x0202 # Reset kernel eflags - popfl_cfi - movl PT_EBP(%esp),%eax - call *PT_EBX(%esp) - movl $0,PT_EAX(%esp) - jmp syscall_exit - CFI_ENDPROC -ENDPROC(ret_from_kernel_thread) - -/* - * Return to user mode is not as complex as all this looks, - * but we want the default path for a system call return to - * go as quickly as possible which is why some of this is - * less clear than it otherwise should be. - */ - - # userspace resumption stub bypassing syscall exit tracing - ALIGN - RING0_PTREGS_FRAME -ret_from_exception: - preempt_stop(CLBR_ANY) -ret_from_intr: - GET_THREAD_INFO(%ebp) -#ifdef CONFIG_VM86 - movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax -#else - /* - * We can be coming here from child spawned by kernel_thread(). - */ - movl PT_CS(%esp), %eax - andl $SEGMENT_RPL_MASK, %eax -#endif - cmpl $USER_RPL, %eax - jb resume_kernel # not returning to v8086 or userspace - -ENTRY(resume_userspace) - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done on - # int/exception return? - jne work_pending - jmp restore_all -END(ret_from_exception) - -#ifdef CONFIG_PREEMPT -ENTRY(resume_kernel) - DISABLE_INTERRUPTS(CLBR_ANY) -need_resched: - cmpl $0,PER_CPU_VAR(__preempt_count) - jnz restore_all - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all - call preempt_schedule_irq - jmp need_resched -END(resume_kernel) -#endif - CFI_ENDPROC - -/* SYSENTER_RETURN points to after the "sysenter" instruction in - the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ - - # sysenter call handler stub -ENTRY(ia32_sysenter_target) - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 0 - CFI_REGISTER esp, ebp - movl TSS_sysenter_sp0(%esp),%esp -sysenter_past_esp: - /* - * Interrupts are disabled here, but we can't trace it until - * enough kernel state to call TRACE_IRQS_OFF can be called - but - * we immediately enable interrupts at that point anyway. - */ - pushl_cfi $__USER_DS - /*CFI_REL_OFFSET ss, 0*/ - pushl_cfi %ebp - CFI_REL_OFFSET esp, 0 - pushfl_cfi - orl $X86_EFLAGS_IF, (%esp) - pushl_cfi $__USER_CS - /*CFI_REL_OFFSET cs, 0*/ - /* - * Push current_thread_info()->sysenter_return to the stack. - * A tiny bit of offset fixup is necessary: TI_sysenter_return - * is relative to thread_info, which is at the bottom of the - * kernel stack page. 4*4 means the 4 words pushed above; - * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; - * and THREAD_SIZE takes us to the bottom. - */ - pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) - CFI_REL_OFFSET eip, 0 - - pushl_cfi %eax - SAVE_ALL - ENABLE_INTERRUPTS(CLBR_NONE) - -/* - * Load the potential sixth argument from user stack. - * Careful about security. - */ - cmpl $__PAGE_OFFSET-3,%ebp - jae syscall_fault - ASM_STAC -1: movl (%ebp),%ebp - ASM_CLAC - movl %ebp,PT_EBP(%esp) - _ASM_EXTABLE(1b,syscall_fault) - - GET_THREAD_INFO(%ebp) - - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz sysenter_audit -sysenter_do_call: - cmpl $(NR_syscalls), %eax - jae sysenter_badsys - call *sys_call_table(,%eax,4) -sysenter_after_call: - movl %eax,PT_EAX(%esp) - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx - jnz sysexit_audit -sysenter_exit: -/* if something modifies registers it must also disable sysexit */ - movl PT_EIP(%esp), %edx - movl PT_OLDESP(%esp), %ecx - xorl %ebp,%ebp - TRACE_IRQS_ON -1: mov PT_FS(%esp), %fs - PTGS_TO_GS - ENABLE_INTERRUPTS_SYSEXIT - -#ifdef CONFIG_AUDITSYSCALL -sysenter_audit: - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) - jnz syscall_trace_entry - /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ - movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ - /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ - pushl_cfi PT_ESI(%esp) /* a3: 5th arg */ - pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */ - call __audit_syscall_entry - popl_cfi %ecx /* get that remapped edx off the stack */ - popl_cfi %ecx /* get that remapped esi off the stack */ - movl PT_EAX(%esp),%eax /* reload syscall number */ - jmp sysenter_do_call - -sysexit_audit: - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - movl %eax,%edx /* second arg, syscall return value */ - cmpl $-MAX_ERRNO,%eax /* is it an error ? */ - setbe %al /* 1 if so, 0 if not */ - movzbl %al,%eax /* zero-extend that */ - call __audit_syscall_exit - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - movl PT_EAX(%esp),%eax /* reload syscall return value */ - jmp sysenter_exit -#endif - - CFI_ENDPROC -.pushsection .fixup,"ax" -2: movl $0,PT_FS(%esp) - jmp 1b -.popsection - _ASM_EXTABLE(1b,2b) - PTGS_TO_GS_EX -ENDPROC(ia32_sysenter_target) - - # system call handler stub -ENTRY(system_call) - RING0_INT_FRAME # can't unwind into user space anyway - ASM_CLAC - pushl_cfi %eax # save orig_eax - SAVE_ALL - GET_THREAD_INFO(%ebp) - # system call tracing in operation / emulation - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz syscall_trace_entry - cmpl $(NR_syscalls), %eax - jae syscall_badsys -syscall_call: - call *sys_call_table(,%eax,4) -syscall_after_call: - movl %eax,PT_EAX(%esp) # store the return value -syscall_exit: - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx # current->work - jnz syscall_exit_work - -restore_all: - TRACE_IRQS_IRET -restore_all_notrace: -#ifdef CONFIG_X86_ESPFIX32 - movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS - # Warning: PT_OLDSS(%esp) contains the wrong/random values if we - # are returning to the kernel. - # See comments in process.c:copy_thread() for details. - movb PT_OLDSS(%esp), %ah - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax - cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax - CFI_REMEMBER_STATE - je ldt_ss # returning to user-space with LDT SS -#endif -restore_nocheck: - RESTORE_REGS 4 # skip orig_eax/error_code -irq_return: - INTERRUPT_RETURN -.section .fixup,"ax" -ENTRY(iret_exc) - pushl $0 # no error code - pushl $do_iret_error - jmp error_code -.previous - _ASM_EXTABLE(irq_return,iret_exc) - -#ifdef CONFIG_X86_ESPFIX32 - CFI_RESTORE_STATE -ldt_ss: -#ifdef CONFIG_PARAVIRT - /* - * The kernel can't run on a non-flat stack if paravirt mode - * is active. Rather than try to fixup the high bits of - * ESP, bypass this code entirely. This may break DOSemu - * and/or Wine support in a paravirt VM, although the option - * is still available to implement the setting of the high - * 16-bits in the INTERRUPT_RETURN paravirt-op. - */ - cmpl $0, pv_info+PARAVIRT_enabled - jne restore_nocheck -#endif - -/* - * Setup and switch to ESPFIX stack - * - * We're returning to userspace with a 16 bit stack. The CPU will not - * restore the high word of ESP for us on executing iret... This is an - * "official" bug of all the x86-compatible CPUs, which we can work - * around to make dosemu and wine happy. We do this by preloading the - * high word of ESP with the high word of the userspace ESP while - * compensating for the offset by changing to the ESPFIX segment with - * a base address that matches for the difference. - */ -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) - mov %esp, %edx /* load kernel esp */ - mov PT_OLDESP(%esp), %eax /* load userspace esp */ - mov %dx, %ax /* eax: new kernel esp */ - sub %eax, %edx /* offset (low word is 0) */ - shr $16, %edx - mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ - mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ - pushl_cfi $__ESPFIX_SS - pushl_cfi %eax /* new kernel esp */ - /* Disable interrupts, but do not irqtrace this section: we - * will soon execute iret and the tracer was already set to - * the irqstate after the iret */ - DISABLE_INTERRUPTS(CLBR_EAX) - lss (%esp), %esp /* switch to espfix segment */ - CFI_ADJUST_CFA_OFFSET -8 - jmp restore_nocheck -#endif - CFI_ENDPROC -ENDPROC(system_call) - - # perform work that needs to be done immediately before resumption - ALIGN - RING0_PTREGS_FRAME # can't unwind into user space anyway -work_pending: - testb $_TIF_NEED_RESCHED, %cl - jz work_notifysig -work_resched: - call schedule - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done other - # than syscall tracing? - jz restore_all - testb $_TIF_NEED_RESCHED, %cl - jnz work_resched - -work_notifysig: # deal with pending signals and - # notify-resume requests -#ifdef CONFIG_VM86 - testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) - movl %esp, %eax - jnz work_notifysig_v86 # returning to kernel-space or - # vm86-space -1: -#else - movl %esp, %eax -#endif - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - movb PT_CS(%esp), %bl - andb $SEGMENT_RPL_MASK, %bl - cmpb $USER_RPL, %bl - jb resume_kernel - xorl %edx, %edx - call do_notify_resume - jmp resume_userspace - -#ifdef CONFIG_VM86 - ALIGN -work_notifysig_v86: - pushl_cfi %ecx # save ti_flags for do_notify_resume - call save_v86_state # %eax contains pt_regs pointer - popl_cfi %ecx - movl %eax, %esp - jmp 1b -#endif -END(work_pending) - - # perform syscall exit tracing - ALIGN -syscall_trace_entry: - movl $-ENOSYS,PT_EAX(%esp) - movl %esp, %eax - call syscall_trace_enter - /* What it returned is what we'll actually use. */ - cmpl $(NR_syscalls), %eax - jnae syscall_call - jmp syscall_exit -END(syscall_trace_entry) - - # perform syscall exit tracing - ALIGN -syscall_exit_work: - testl $_TIF_WORK_SYSCALL_EXIT, %ecx - jz work_pending - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call - # schedule() instead - movl %esp, %eax - call syscall_trace_leave - jmp resume_userspace -END(syscall_exit_work) - CFI_ENDPROC - - RING0_INT_FRAME # can't unwind into user space anyway -syscall_fault: - ASM_CLAC - GET_THREAD_INFO(%ebp) - movl $-EFAULT,PT_EAX(%esp) - jmp resume_userspace -END(syscall_fault) - -syscall_badsys: - movl $-ENOSYS,%eax - jmp syscall_after_call -END(syscall_badsys) - -sysenter_badsys: - movl $-ENOSYS,%eax - jmp sysenter_after_call -END(sysenter_badsys) - CFI_ENDPROC - -.macro FIXUP_ESPFIX_STACK -/* - * Switch back for ESPFIX stack to the normal zerobased stack - * - * We can't call C functions using the ESPFIX stack. This code reads - * the high word of the segment base from the GDT and swiches to the - * normal stack and adjusts ESP with the matching offset. - */ -#ifdef CONFIG_X86_ESPFIX32 - /* fixup the stack */ - mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ - mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ - shl $16, %eax - addl %esp, %eax /* the adjusted stack pointer */ - pushl_cfi $__KERNEL_DS - pushl_cfi %eax - lss (%esp), %esp /* switch to the normal stack segment */ - CFI_ADJUST_CFA_OFFSET -8 -#endif -.endm -.macro UNWIND_ESPFIX_STACK -#ifdef CONFIG_X86_ESPFIX32 - movl %ss, %eax - /* see if on espfix stack */ - cmpw $__ESPFIX_SS, %ax - jne 27f - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - /* switch to normal stack */ - FIXUP_ESPFIX_STACK -27: -#endif -.endm - -/* - * Build the entry stubs with some assembler magic. - * We pack 1 stub into every 8-byte block. - */ - .align 8 -ENTRY(irq_entries_start) - RING0_INT_FRAME - vector=FIRST_EXTERNAL_VECTOR - .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) - pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ - vector=vector+1 - jmp common_interrupt - CFI_ADJUST_CFA_OFFSET -4 - .align 8 - .endr -END(irq_entries_start) - -/* - * the CPU automatically disables interrupts when executing an IRQ vector, - * so IRQ-flags tracing has to follow that: - */ - .p2align CONFIG_X86_L1_CACHE_SHIFT -common_interrupt: - ASM_CLAC - addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ - SAVE_ALL - TRACE_IRQS_OFF - movl %esp,%eax - call do_IRQ - jmp ret_from_intr -ENDPROC(common_interrupt) - CFI_ENDPROC - -#define BUILD_INTERRUPT3(name, nr, fn) \ -ENTRY(name) \ - RING0_INT_FRAME; \ - ASM_CLAC; \ - pushl_cfi $~(nr); \ - SAVE_ALL; \ - TRACE_IRQS_OFF \ - movl %esp,%eax; \ - call fn; \ - jmp ret_from_intr; \ - CFI_ENDPROC; \ -ENDPROC(name) - - -#ifdef CONFIG_TRACING -#define TRACE_BUILD_INTERRUPT(name, nr) \ - BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) -#else -#define TRACE_BUILD_INTERRUPT(name, nr) -#endif - -#define BUILD_INTERRUPT(name, nr) \ - BUILD_INTERRUPT3(name, nr, smp_##name); \ - TRACE_BUILD_INTERRUPT(name, nr) - -/* The include is where all of the SMP etc. interrupts come from */ -#include <asm/entry_arch.h> - -ENTRY(coprocessor_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_coprocessor_error - jmp error_code - CFI_ENDPROC -END(coprocessor_error) - -ENTRY(simd_coprocessor_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 -#ifdef CONFIG_X86_INVD_BUG - /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ - ALTERNATIVE "pushl_cfi $do_general_protection", \ - "pushl $do_simd_coprocessor_error", \ - X86_FEATURE_XMM -#else - pushl_cfi $do_simd_coprocessor_error -#endif - jmp error_code - CFI_ENDPROC -END(simd_coprocessor_error) - -ENTRY(device_not_available) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $-1 # mark this as an int - pushl_cfi $do_device_not_available - jmp error_code - CFI_ENDPROC -END(device_not_available) - -#ifdef CONFIG_PARAVIRT -ENTRY(native_iret) - iret - _ASM_EXTABLE(native_iret, iret_exc) -END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) -#endif - -ENTRY(overflow) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_overflow - jmp error_code - CFI_ENDPROC -END(overflow) - -ENTRY(bounds) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_bounds - jmp error_code - CFI_ENDPROC -END(bounds) - -ENTRY(invalid_op) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_invalid_op - jmp error_code - CFI_ENDPROC -END(invalid_op) - -ENTRY(coprocessor_segment_overrun) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_coprocessor_segment_overrun - jmp error_code - CFI_ENDPROC -END(coprocessor_segment_overrun) - -ENTRY(invalid_TSS) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_invalid_TSS - jmp error_code - CFI_ENDPROC -END(invalid_TSS) - -ENTRY(segment_not_present) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_segment_not_present - jmp error_code - CFI_ENDPROC -END(segment_not_present) - -ENTRY(stack_segment) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_stack_segment - jmp error_code - CFI_ENDPROC -END(stack_segment) - -ENTRY(alignment_check) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_alignment_check - jmp error_code - CFI_ENDPROC -END(alignment_check) - -ENTRY(divide_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 # no error code - pushl_cfi $do_divide_error - jmp error_code - CFI_ENDPROC -END(divide_error) - -#ifdef CONFIG_X86_MCE -ENTRY(machine_check) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi machine_check_vector - jmp error_code - CFI_ENDPROC -END(machine_check) -#endif - -ENTRY(spurious_interrupt_bug) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_spurious_interrupt_bug - jmp error_code - CFI_ENDPROC -END(spurious_interrupt_bug) - -#ifdef CONFIG_XEN -/* Xen doesn't set %esp to be precisely what the normal sysenter - entrypoint expects, so fix it up before using the normal path. */ -ENTRY(xen_sysenter_target) - RING0_INT_FRAME - addl $5*4, %esp /* remove xen-provided frame */ - CFI_ADJUST_CFA_OFFSET -5*4 - jmp sysenter_past_esp - CFI_ENDPROC - -ENTRY(xen_hypervisor_callback) - CFI_STARTPROC - pushl_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - TRACE_IRQS_OFF - - /* Check to see if we got the event in the critical - region in xen_iret_direct, after we've reenabled - events and checked for pending events. This simulates - iret instruction's behaviour where it delivers a - pending interrupt when enabling interrupts. */ - movl PT_EIP(%esp),%eax - cmpl $xen_iret_start_crit,%eax - jb 1f - cmpl $xen_iret_end_crit,%eax - jae 1f - - jmp xen_iret_crit_fixup - -ENTRY(xen_do_upcall) -1: mov %esp, %eax - call xen_evtchn_do_upcall -#ifndef CONFIG_PREEMPT - call xen_maybe_preempt_hcall -#endif - jmp ret_from_intr - CFI_ENDPROC -ENDPROC(xen_hypervisor_callback) - -# Hypervisor uses this for application faults while it executes. -# We get here for two reasons: -# 1. Fault while reloading DS, ES, FS or GS -# 2. Fault while executing IRET -# Category 1 we fix up by reattempting the load, and zeroing the segment -# register if the load fails. -# Category 2 we fix up by jumping to do_iret_error. We cannot use the -# normal Linux return path in this case because if we use the IRET hypercall -# to pop the stack frame we end up in an infinite loop of failsafe callbacks. -# We distinguish between categories by maintaining a status value in EAX. -ENTRY(xen_failsafe_callback) - CFI_STARTPROC - pushl_cfi %eax - movl $1,%eax -1: mov 4(%esp),%ds -2: mov 8(%esp),%es -3: mov 12(%esp),%fs -4: mov 16(%esp),%gs - /* EAX == 0 => Category 1 (Bad segment) - EAX != 0 => Category 2 (Bad IRET) */ - testl %eax,%eax - popl_cfi %eax - lea 16(%esp),%esp - CFI_ADJUST_CFA_OFFSET -16 - jz 5f - jmp iret_exc -5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - jmp ret_from_exception - CFI_ENDPROC - -.section .fixup,"ax" -6: xorl %eax,%eax - movl %eax,4(%esp) - jmp 1b -7: xorl %eax,%eax - movl %eax,8(%esp) - jmp 2b -8: xorl %eax,%eax - movl %eax,12(%esp) - jmp 3b -9: xorl %eax,%eax - movl %eax,16(%esp) - jmp 4b -.previous - _ASM_EXTABLE(1b,6b) - _ASM_EXTABLE(2b,7b) - _ASM_EXTABLE(3b,8b) - _ASM_EXTABLE(4b,9b) -ENDPROC(xen_failsafe_callback) - -BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - xen_evtchn_do_upcall) - -#endif /* CONFIG_XEN */ - -#if IS_ENABLED(CONFIG_HYPERV) - -BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - hyperv_vector_handler) - -#endif /* CONFIG_HYPERV */ - -#ifdef CONFIG_FUNCTION_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE - -ENTRY(mcount) - ret -END(mcount) - -ENTRY(ftrace_caller) - pushl %eax - pushl %ecx - pushl %edx - pushl $0 /* Pass NULL as regs pointer */ - movl 4*4(%esp), %eax - movl 0x4(%ebp), %edx - movl function_trace_op, %ecx - subl $MCOUNT_INSN_SIZE, %eax - -.globl ftrace_call -ftrace_call: - call ftrace_stub - - addl $4,%esp /* skip NULL pointer */ - popl %edx - popl %ecx - popl %eax -ftrace_ret: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - jmp ftrace_stub -#endif - -.globl ftrace_stub -ftrace_stub: - ret -END(ftrace_caller) - -ENTRY(ftrace_regs_caller) - pushf /* push flags before compare (in cs location) */ - - /* - * i386 does not save SS and ESP when coming from kernel. - * Instead, to get sp, ®s->sp is used (see ptrace.h). - * Unfortunately, that means eflags must be at the same location - * as the current return ip is. We move the return ip into the - * ip location, and move flags into the return ip location. - */ - pushl 4(%esp) /* save return ip into ip slot */ - - pushl $0 /* Load 0 into orig_ax */ - pushl %gs - pushl %fs - pushl %es - pushl %ds - pushl %eax - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - pushl %ecx - pushl %ebx - - movl 13*4(%esp), %eax /* Get the saved flags */ - movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ - /* clobbering return ip */ - movl $__KERNEL_CS,13*4(%esp) - - movl 12*4(%esp), %eax /* Load ip (1st parameter) */ - subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ - movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ - pushl %esp /* Save pt_regs as 4th parameter */ - -GLOBAL(ftrace_regs_call) - call ftrace_stub - - addl $4, %esp /* Skip pt_regs */ - movl 14*4(%esp), %eax /* Move flags back into cs */ - movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ - movl 12*4(%esp), %eax /* Get return ip from regs->ip */ - movl %eax, 14*4(%esp) /* Put return ip back for ret */ - - popl %ebx - popl %ecx - popl %edx - popl %esi - popl %edi - popl %ebp - popl %eax - popl %ds - popl %es - popl %fs - popl %gs - addl $8, %esp /* Skip orig_ax and ip */ - popf /* Pop flags at end (no addl to corrupt flags) */ - jmp ftrace_ret - - popf - jmp ftrace_stub -#else /* ! CONFIG_DYNAMIC_FTRACE */ - -ENTRY(mcount) - cmpl $__PAGE_OFFSET, %esp - jb ftrace_stub /* Paging not enabled yet? */ - - cmpl $ftrace_stub, ftrace_trace_function - jnz trace -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpl $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpl $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif -.globl ftrace_stub -ftrace_stub: - ret - - /* taken from glibc */ -trace: - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - movl 0x4(%ebp), %edx - subl $MCOUNT_INSN_SIZE, %eax - - call *ftrace_trace_function - - popl %edx - popl %ecx - popl %eax - jmp ftrace_stub -END(mcount) -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FUNCTION_TRACER */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - lea 0x4(%ebp), %edx - movl (%ebp), %ecx - subl $MCOUNT_INSN_SIZE, %eax - call prepare_ftrace_return - popl %edx - popl %ecx - popl %eax - ret -END(ftrace_graph_caller) - -.globl return_to_handler -return_to_handler: - pushl %eax - pushl %edx - movl %ebp, %eax - call ftrace_return_to_handler - movl %eax, %ecx - popl %edx - popl %eax - jmp *%ecx -#endif - -#ifdef CONFIG_TRACING -ENTRY(trace_page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $trace_do_page_fault - jmp error_code - CFI_ENDPROC -END(trace_page_fault) -#endif - -ENTRY(page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_page_fault - ALIGN -error_code: - /* the function address is in %gs's slot on the stack */ - pushl_cfi %fs - /*CFI_REL_OFFSET fs, 0*/ - pushl_cfi %es - /*CFI_REL_OFFSET es, 0*/ - pushl_cfi %ds - /*CFI_REL_OFFSET ds, 0*/ - pushl_cfi_reg eax - pushl_cfi_reg ebp - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg edx - pushl_cfi_reg ecx - pushl_cfi_reg ebx - cld - movl $(__KERNEL_PERCPU), %ecx - movl %ecx, %fs - UNWIND_ESPFIX_STACK - GS_TO_REG %ecx - movl PT_GS(%esp), %edi # get the function address - movl PT_ORIG_EAX(%esp), %edx # get the error code - movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart - REG_TO_PTGS %ecx - SET_KERNEL_GS %ecx - movl $(__USER_DS), %ecx - movl %ecx, %ds - movl %ecx, %es - TRACE_IRQS_OFF - movl %esp,%eax # pt_regs pointer - call *%edi - jmp ret_from_exception - CFI_ENDPROC -END(page_fault) - -/* - * Debug traps and NMI can happen at the one SYSENTER instruction - * that sets up the real kernel stack. Check here, since we can't - * allow the wrong stack to be used. - * - * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have - * already pushed 3 words if it hits on the sysenter instruction: - * eflags, cs and eip. - * - * We just load the right stack, and push the three (known) values - * by hand onto the new stack - while updating the return eip past - * the instruction that would have done it for sysenter. - */ -.macro FIX_STACK offset ok label - cmpw $__KERNEL_CS, 4(%esp) - jne \ok -\label: - movl TSS_sysenter_sp0 + \offset(%esp), %esp - CFI_DEF_CFA esp, 0 - CFI_UNDEFINED eip - pushfl_cfi - pushl_cfi $__KERNEL_CS - pushl_cfi $sysenter_past_esp - CFI_REL_OFFSET eip, 0 -.endm - -ENTRY(debug) - RING0_INT_FRAME - ASM_CLAC - cmpl $ia32_sysenter_target,(%esp) - jne debug_stack_correct - FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn -debug_stack_correct: - pushl_cfi $-1 # mark this as an int - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # error code 0 - movl %esp,%eax # pt_regs pointer - call do_debug - jmp ret_from_exception - CFI_ENDPROC -END(debug) - -/* - * NMI is doubly nasty. It can happen _while_ we're handling - * a debug fault, and the debug fault hasn't yet been able to - * clear up the stack. So we first check whether we got an - * NMI on the sysenter entry path, but after that we need to - * check whether we got an NMI on the debug path where the debug - * fault happened on the sysenter path. - */ -ENTRY(nmi) - RING0_INT_FRAME - ASM_CLAC -#ifdef CONFIG_X86_ESPFIX32 - pushl_cfi %eax - movl %ss, %eax - cmpw $__ESPFIX_SS, %ax - popl_cfi %eax - je nmi_espfix_stack -#endif - cmpl $ia32_sysenter_target,(%esp) - je nmi_stack_fixup - pushl_cfi %eax - movl %esp,%eax - /* Do not access memory above the end of our stack page, - * it might not exist. - */ - andl $(THREAD_SIZE-1),%eax - cmpl $(THREAD_SIZE-20),%eax - popl_cfi %eax - jae nmi_stack_correct - cmpl $ia32_sysenter_target,12(%esp) - je nmi_debug_stack_check -nmi_stack_correct: - /* We have a RING0_INT_FRAME here */ - pushl_cfi %eax - SAVE_ALL - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_nmi - jmp restore_all_notrace - CFI_ENDPROC - -nmi_stack_fixup: - RING0_INT_FRAME - FIX_STACK 12, nmi_stack_correct, 1 - jmp nmi_stack_correct - -nmi_debug_stack_check: - /* We have a RING0_INT_FRAME here */ - cmpw $__KERNEL_CS,16(%esp) - jne nmi_stack_correct - cmpl $debug,(%esp) - jb nmi_stack_correct - cmpl $debug_esp_fix_insn,(%esp) - ja nmi_stack_correct - FIX_STACK 24, nmi_stack_correct, 1 - jmp nmi_stack_correct - -#ifdef CONFIG_X86_ESPFIX32 -nmi_espfix_stack: - /* We have a RING0_INT_FRAME here. - * - * create the pointer to lss back - */ - pushl_cfi %ss - pushl_cfi %esp - addl $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl_cfi 16(%esp) - .endr - pushl_cfi %eax - SAVE_ALL - FIXUP_ESPFIX_STACK # %eax == %esp - xorl %edx,%edx # zero error code - call do_nmi - RESTORE_REGS - lss 12+4(%esp), %esp # back to espfix stack - CFI_ADJUST_CFA_OFFSET -24 - jmp irq_return -#endif - CFI_ENDPROC -END(nmi) - -ENTRY(int3) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $-1 # mark this as an int - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_int3 - jmp ret_from_exception - CFI_ENDPROC -END(int3) - -ENTRY(general_protection) - RING0_EC_FRAME - pushl_cfi $do_general_protection - jmp error_code - CFI_ENDPROC -END(general_protection) - -#ifdef CONFIG_KVM_GUEST -ENTRY(async_page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_async_page_fault - jmp error_code - CFI_ENDPROC -END(async_page_fault) -#endif - diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S deleted file mode 100644 index 4bd6c1975..000000000 --- a/arch/x86/kernel/entry_64.S +++ /dev/null @@ -1,1733 +0,0 @@ -/* - * linux/arch/x86_64/entry.S - * - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs - * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> - */ - -/* - * entry.S contains the system-call and fault low-level handling routines. - * - * Some of this is documented in Documentation/x86/entry_64.txt - * - * NOTE: This code handles signal-recognition, which happens every time - * after an interrupt and after each system call. - * - * A note on terminology: - * - iret frame: Architecture defined interrupt frame from SS to RIP - * at the top of the kernel process stack. - * - * Some macro usage: - * - CFI macros are used to generate dwarf2 unwind information for better - * backtraces. They don't change any code. - * - ENTRY/END Define functions in the symbol table. - * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. - * - idtentry - Define exception entry points. - */ - -#include <linux/linkage.h> -#include <asm/segment.h> -#include <asm/cache.h> -#include <asm/errno.h> -#include <asm/dwarf2.h> -#include <asm/calling.h> -#include <asm/asm-offsets.h> -#include <asm/msr.h> -#include <asm/unistd.h> -#include <asm/thread_info.h> -#include <asm/hw_irq.h> -#include <asm/page_types.h> -#include <asm/irqflags.h> -#include <asm/paravirt.h> -#include <asm/percpu.h> -#include <asm/asm.h> -#include <asm/context_tracking.h> -#include <asm/smap.h> -#include <asm/pgtable_types.h> -#include <linux/err.h> - -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_64BIT 0x80000000 -#define __AUDIT_ARCH_LE 0x40000000 - - .code64 - .section .entry.text, "ax" - - -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret64) - swapgs - sysretq -ENDPROC(native_usergs_sysret64) -#endif /* CONFIG_PARAVIRT */ - - -.macro TRACE_IRQS_IRETQ -#ifdef CONFIG_TRACE_IRQFLAGS - bt $9,EFLAGS(%rsp) /* interrupts off? */ - jnc 1f - TRACE_IRQS_ON -1: -#endif -.endm - -/* - * When dynamic function tracer is enabled it will add a breakpoint - * to all locations that it is about to modify, sync CPUs, update - * all the code, sync CPUs, then remove the breakpoints. In this time - * if lockdep is enabled, it might jump back into the debug handler - * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF). - * - * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to - * make sure the stack pointer does not get reset back to the top - * of the debug stack, and instead just reuses the current stack. - */ -#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS) - -.macro TRACE_IRQS_OFF_DEBUG - call debug_stack_set_zero - TRACE_IRQS_OFF - call debug_stack_reset -.endm - -.macro TRACE_IRQS_ON_DEBUG - call debug_stack_set_zero - TRACE_IRQS_ON - call debug_stack_reset -.endm - -.macro TRACE_IRQS_IRETQ_DEBUG - bt $9,EFLAGS(%rsp) /* interrupts off? */ - jnc 1f - TRACE_IRQS_ON_DEBUG -1: -.endm - -#else -# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF -# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON -# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ -#endif - -/* - * empty frame - */ - .macro EMPTY_FRAME start=1 offset=0 - .if \start - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,8+\offset - .else - CFI_DEF_CFA_OFFSET 8+\offset - .endif - .endm - -/* - * initial frame state for interrupts (and exceptions without error code) - */ - .macro INTR_FRAME start=1 offset=0 - EMPTY_FRAME \start, 5*8+\offset - /*CFI_REL_OFFSET ss, 4*8+\offset*/ - CFI_REL_OFFSET rsp, 3*8+\offset - /*CFI_REL_OFFSET rflags, 2*8+\offset*/ - /*CFI_REL_OFFSET cs, 1*8+\offset*/ - CFI_REL_OFFSET rip, 0*8+\offset - .endm - -/* - * initial frame state for exceptions with error code (and interrupts - * with vector already pushed) - */ - .macro XCPT_FRAME start=1 offset=0 - INTR_FRAME \start, 1*8+\offset - .endm - -/* - * frame that enables passing a complete pt_regs to a C function. - */ - .macro DEFAULT_FRAME start=1 offset=0 - XCPT_FRAME \start, ORIG_RAX+\offset - CFI_REL_OFFSET rdi, RDI+\offset - CFI_REL_OFFSET rsi, RSI+\offset - CFI_REL_OFFSET rdx, RDX+\offset - CFI_REL_OFFSET rcx, RCX+\offset - CFI_REL_OFFSET rax, RAX+\offset - CFI_REL_OFFSET r8, R8+\offset - CFI_REL_OFFSET r9, R9+\offset - CFI_REL_OFFSET r10, R10+\offset - CFI_REL_OFFSET r11, R11+\offset - CFI_REL_OFFSET rbx, RBX+\offset - CFI_REL_OFFSET rbp, RBP+\offset - CFI_REL_OFFSET r12, R12+\offset - CFI_REL_OFFSET r13, R13+\offset - CFI_REL_OFFSET r14, R14+\offset - CFI_REL_OFFSET r15, R15+\offset - .endm - -/* - * 64bit SYSCALL instruction entry. Up to 6 arguments in registers. - * - * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, - * then loads new ss, cs, and rip from previously programmed MSRs. - * rflags gets masked by a value from another MSR (so CLD and CLAC - * are not needed). SYSCALL does not save anything on the stack - * and does not change rsp. - * - * Registers on entry: - * rax system call number - * rcx return address - * r11 saved rflags (note: r11 is callee-clobbered register in C ABI) - * rdi arg0 - * rsi arg1 - * rdx arg2 - * r10 arg3 (needs to be moved to rcx to conform to C ABI) - * r8 arg4 - * r9 arg5 - * (note: r12-r15,rbp,rbx are callee-preserved in C ABI) - * - * Only called from user space. - * - * When user can change pt_regs->foo always force IRET. That is because - * it deals with uncanonical addresses better. SYSRET has trouble - * with them due to bugs in both AMD and Intel CPUs. - */ - -ENTRY(system_call) - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rip,rcx - /*CFI_REGISTER rflags,r11*/ - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - SWAPGS_UNSAFE_STACK - /* - * A hypervisor implementation might want to use a label - * after the swapgs, so that it can do the swapgs - * for the guest and jump here on syscall. - */ -GLOBAL(system_call_after_swapgs) - - movq %rsp,PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack),%rsp - - /* Construct struct pt_regs on stack */ - pushq_cfi $__USER_DS /* pt_regs->ss */ - pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ - /* - * Re-enable interrupts. - * We use 'rsp_scratch' as a scratch space, hence irq-off block above - * must execute atomically in the face of possible interrupt-driven - * task preemption. We must enable interrupts only after we're done - * with using rsp_scratch: - */ - ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %r11 /* pt_regs->flags */ - pushq_cfi $__USER_CS /* pt_regs->cs */ - pushq_cfi %rcx /* pt_regs->ip */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi $-ENOSYS /* pt_regs->ax */ - pushq_cfi_reg r8 /* pt_regs->r8 */ - pushq_cfi_reg r9 /* pt_regs->r9 */ - pushq_cfi_reg r10 /* pt_regs->r10 */ - pushq_cfi_reg r11 /* pt_regs->r11 */ - sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 6*8 - - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz tracesys -system_call_fastpath: -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max,%rax -#else - andl $__SYSCALL_MASK,%eax - cmpl $__NR_syscall_max,%eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10,%rcx - call *sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) -1: -/* - * Syscall return path ending with SYSRET (fast path). - * Has incompletely filled pt_regs. - */ - LOCKDEP_SYS_EXIT - /* - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - DISABLE_INTERRUPTS(CLBR_NONE) - - /* - * We must check ti flags with interrupts (or at least preemption) - * off because we must *never* return to userspace without - * processing exit work that is enqueued if we're preempted here. - * In particular, returning to userspace with any of the one-shot - * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is - * very bad. - */ - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ - - CFI_REMEMBER_STATE - - RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RIP(%rsp),%rcx - CFI_REGISTER rip,rcx - movq EFLAGS(%rsp),%r11 - /*CFI_REGISTER rflags,r11*/ - movq RSP(%rsp),%rsp - /* - * 64bit SYSRET restores rip from rcx, - * rflags from r11 (but RF and VM bits are forced to 0), - * cs and ss are loaded from MSRs. - * Restoration of rflags re-enables interrupts. - * - * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss - * descriptor is not reinitialized. This means that we should - * avoid SYSRET with SS == NULL, which could happen if we schedule, - * exit the kernel, and re-enter using an interrupt vector. (All - * interrupt entries on x86_64 set SS to NULL.) We prevent that - * from happening by reloading SS in __switch_to. (Actually - * detecting the failure in 64-bit userspace is tricky but can be - * done.) - */ - USERGS_SYSRET64 - - CFI_RESTORE_STATE - - /* Do syscall entry tracing */ -tracesys: - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - call syscall_trace_enter_phase1 - test %rax, %rax - jnz tracesys_phase2 /* if needed, run the slow path */ - RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ - movq ORIG_RAX(%rsp), %rax - jmp system_call_fastpath /* and return to the fast path */ - -tracesys_phase2: - SAVE_EXTRA_REGS - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - movq %rax,%rdx - call syscall_trace_enter_phase2 - - /* - * Reload registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_entry_phase2() returned - * the value it wants us to use in the table lookup. - */ - RESTORE_C_REGS_EXCEPT_RAX - RESTORE_EXTRA_REGS -#if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max,%rax -#else - andl $__SYSCALL_MASK,%eax - cmpl $__NR_syscall_max,%eax -#endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10,%rcx /* fixup for C */ - call *sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) -1: - /* Use IRET because user could have changed pt_regs->foo */ - -/* - * Syscall return path ending with IRET. - * Has correct iret frame. - */ -GLOBAL(int_ret_from_sys_call) - DISABLE_INTERRUPTS(CLBR_NONE) -int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */ - TRACE_IRQS_OFF - movl $_TIF_ALLWORK_MASK,%edi - /* edi: mask to check */ -GLOBAL(int_with_check) - LOCKDEP_SYS_EXIT_IRQ - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%edx - andl %edi,%edx - jnz int_careful - andl $~TS_COMPAT,TI_status(%rcx) - jmp syscall_return - - /* Either reschedule or signal or syscall exit tracking needed. */ - /* First do a reschedule test. */ - /* edx: work, edi: workmask */ -int_careful: - bt $TIF_NEED_RESCHED,%edx - jnc int_very_careful - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi - SCHEDULE_USER - popq_cfi %rdi - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - - /* handle signals and tracing -- both require a full pt_regs */ -int_very_careful: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - /* Check for syscall exit trace */ - testl $_TIF_WORK_SYSCALL_EXIT,%edx - jz int_signal - pushq_cfi %rdi - leaq 8(%rsp),%rdi # &ptregs -> arg1 - call syscall_trace_leave - popq_cfi %rdi - andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi - jmp int_restore_rest - -int_signal: - testl $_TIF_DO_NOTIFY_MASK,%edx - jz 1f - movq %rsp,%rdi # &ptregs -> arg1 - xorl %esi,%esi # oldset -> arg2 - call do_notify_resume -1: movl $_TIF_WORK_MASK,%edi -int_restore_rest: - RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - -syscall_return: - /* The IRETQ could re-enable interrupts: */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_IRETQ - - /* - * Try to use SYSRET instead of IRET if we're returning to - * a completely clean 64-bit userspace context. - */ - movq RCX(%rsp),%rcx - cmpq %rcx,RIP(%rsp) /* RCX == RIP */ - jne opportunistic_sysret_failed - - /* - * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP - * in kernel space. This essentially lets the user take over - * the kernel, since userspace controls RSP. It's not worth - * testing for canonicalness exactly -- this check detects any - * of the 17 high bits set, which is true for non-canonical - * or kernel addresses. (This will pessimize vsyscall=native. - * Big deal.) - * - * If virtual addresses ever become wider, this will need - * to be updated to remain correct on both old and new CPUs. - */ - .ifne __VIRTUAL_MASK_SHIFT - 47 - .error "virtual address width changed -- SYSRET checks need update" - .endif - shr $__VIRTUAL_MASK_SHIFT, %rcx - jnz opportunistic_sysret_failed - - cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */ - jne opportunistic_sysret_failed - - movq R11(%rsp),%r11 - cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */ - jne opportunistic_sysret_failed - - /* - * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, - * restoring TF results in a trap from userspace immediately after - * SYSRET. This would cause an infinite loop whenever #DB happens - * with register state that satisfies the opportunistic SYSRET - * conditions. For example, single-stepping this user code: - * - * movq $stuck_here,%rcx - * pushfq - * popq %r11 - * stuck_here: - * - * would never get past 'stuck_here'. - */ - testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz opportunistic_sysret_failed - - /* nothing to check for RSP */ - - cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */ - jne opportunistic_sysret_failed - - /* - * We win! This label is here just for ease of understanding - * perf profiles. Nothing jumps here. - */ -syscall_return_via_sysret: - CFI_REMEMBER_STATE - /* r11 is already restored (see code above) */ - RESTORE_C_REGS_EXCEPT_R11 - movq RSP(%rsp),%rsp - USERGS_SYSRET64 - CFI_RESTORE_STATE - -opportunistic_sysret_failed: - SWAPGS - jmp restore_c_regs_and_iret - CFI_ENDPROC -END(system_call) - - - .macro FORK_LIKE func -ENTRY(stub_\func) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 /* offset 8: return address */ - SAVE_EXTRA_REGS 8 - jmp sys_\func - CFI_ENDPROC -END(stub_\func) - .endm - - FORK_LIKE clone - FORK_LIKE fork - FORK_LIKE vfork - -ENTRY(stub_execve) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - call sys_execve -return_from_execve: - testl %eax, %eax - jz 1f - /* exec failed, can use fast SYSRET code path in this case */ - ret -1: - /* must use IRET code path (pt_regs->cs may have changed) */ - addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 - ZERO_EXTRA_REGS - movq %rax,RAX(%rsp) - jmp int_ret_from_sys_call - CFI_ENDPROC -END(stub_execve) -/* - * Remaining execve stubs are only 7 bytes long. - * ENTRY() often aligns to 16 bytes, which in this case has no benefits. - */ - .align 8 -GLOBAL(stub_execveat) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - call sys_execveat - jmp return_from_execve - CFI_ENDPROC -END(stub_execveat) - -#ifdef CONFIG_X86_X32_ABI - .align 8 -GLOBAL(stub_x32_execve) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - call compat_sys_execve - jmp return_from_execve - CFI_ENDPROC -END(stub_x32_execve) - .align 8 -GLOBAL(stub_x32_execveat) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - call compat_sys_execveat - jmp return_from_execve - CFI_ENDPROC -END(stub_x32_execveat) -#endif - -#ifdef CONFIG_IA32_EMULATION - .align 8 -GLOBAL(stub32_execve) - CFI_STARTPROC - call compat_sys_execve - jmp return_from_execve - CFI_ENDPROC -END(stub32_execve) - .align 8 -GLOBAL(stub32_execveat) - CFI_STARTPROC - call compat_sys_execveat - jmp return_from_execve - CFI_ENDPROC -END(stub32_execveat) -#endif - -/* - * sigreturn is special because it needs to restore all registers on return. - * This cannot be done with SYSRET, so use the IRET return path instead. - */ -ENTRY(stub_rt_sigreturn) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - /* - * SAVE_EXTRA_REGS result is not normally needed: - * sigreturn overwrites all pt_regs->GPREGS. - * But sigreturn can fail (!), and there is no easy way to detect that. - * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error, - * we SAVE_EXTRA_REGS here. - */ - SAVE_EXTRA_REGS 8 - call sys_rt_sigreturn -return_from_stub: - addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 - RESTORE_EXTRA_REGS - movq %rax,RAX(%rsp) - jmp int_ret_from_sys_call - CFI_ENDPROC -END(stub_rt_sigreturn) - -#ifdef CONFIG_X86_X32_ABI -ENTRY(stub_x32_rt_sigreturn) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 - SAVE_EXTRA_REGS 8 - call sys32_x32_rt_sigreturn - jmp return_from_stub - CFI_ENDPROC -END(stub_x32_rt_sigreturn) -#endif - -/* - * A newly forked process directly context switches into this address. - * - * rdi: prev task we switched from - */ -ENTRY(ret_from_fork) - DEFAULT_FRAME - - LOCK ; btr $TIF_FORK,TI_flags(%r8) - - pushq_cfi $0x0002 - popfq_cfi # reset kernel eflags - - call schedule_tail # rdi: 'prev' task parameter - - RESTORE_EXTRA_REGS - - testl $3,CS(%rsp) # from kernel_thread? - - /* - * By the time we get here, we have no idea whether our pt_regs, - * ti flags, and ti status came from the 64-bit SYSCALL fast path, - * the slow path, or one of the ia32entry paths. - * Use IRET code path to return, since it can safely handle - * all of the above. - */ - jnz int_ret_from_sys_call - - /* We came from kernel_thread */ - /* nb: we depend on RESTORE_EXTRA_REGS above */ - movq %rbp, %rdi - call *%rbx - movl $0, RAX(%rsp) - RESTORE_EXTRA_REGS - jmp int_ret_from_sys_call - CFI_ENDPROC -END(ret_from_fork) - -/* - * Build the entry stubs with some assembler magic. - * We pack 1 stub into every 8-byte block. - */ - .align 8 -ENTRY(irq_entries_start) - INTR_FRAME - vector=FIRST_EXTERNAL_VECTOR - .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) - pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */ - vector=vector+1 - jmp common_interrupt - CFI_ADJUST_CFA_OFFSET -8 - .align 8 - .endr - CFI_ENDPROC -END(irq_entries_start) - -/* - * Interrupt entry/exit. - * - * Interrupt entry points save only callee clobbered registers in fast path. - * - * Entry runs with interrupts off. - */ - -/* 0(%rsp): ~(interrupt number) */ - .macro interrupt func - cld - /* - * Since nothing in interrupt handling code touches r12...r15 members - * of "struct pt_regs", and since interrupts can nest, we can save - * four stack slots and simultaneously provide - * an unwind-friendly stack layout by saving "truncated" pt_regs - * exactly up to rbp slot, without these members. - */ - ALLOC_PT_GPREGS_ON_STACK -RBP - SAVE_C_REGS -RBP - /* this goes to 0(%rsp) for unwinder, not for saving the value: */ - SAVE_EXTRA_REGS_RBP -RBP - - leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */ - - testl $3, CS-RBP(%rsp) - je 1f - SWAPGS -1: - /* - * Save previous stack pointer, optionally switch to interrupt stack. - * irq_count is used to check if a CPU is already on an interrupt stack - * or not. While this is essentially redundant with preempt_count it is - * a little cheaper to use a separate counter in the PDA (short of - * moving irq_enter into assembly, which would be too much work) - */ - movq %rsp, %rsi - incl PER_CPU_VAR(irq_count) - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - CFI_DEF_CFA_REGISTER rsi - pushq %rsi - /* - * For debugger: - * "CFA (Current Frame Address) is the value on stack + offset" - */ - CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ - 0x77 /* DW_OP_breg7 (rsp) */, 0, \ - 0x06 /* DW_OP_deref */, \ - 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \ - 0x22 /* DW_OP_plus */ - /* We entered an interrupt context - irqs are off: */ - TRACE_IRQS_OFF - - call \func - .endm - - /* - * The interrupt stubs push (~vector+0x80) onto the stack and - * then jump to common_interrupt. - */ - .p2align CONFIG_X86_L1_CACHE_SHIFT -common_interrupt: - XCPT_FRAME - ASM_CLAC - addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ - interrupt do_IRQ - /* 0(%rsp): old RSP */ -ret_from_intr: - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - decl PER_CPU_VAR(irq_count) - - /* Restore saved previous stack */ - popq %rsi - CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */ - /* return code expects complete pt_regs - adjust rsp accordingly: */ - leaq -RBP(%rsi),%rsp - CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET RBP - - testl $3,CS(%rsp) - je retint_kernel - /* Interrupt came from user space */ - - GET_THREAD_INFO(%rcx) - /* - * %rcx: thread info. Interrupts off. - */ -retint_with_reschedule: - movl $_TIF_WORK_MASK,%edi -retint_check: - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - andl %edi,%edx - CFI_REMEMBER_STATE - jnz retint_careful - -retint_swapgs: /* return to user-space */ - /* - * The iretq could re-enable interrupts: - */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_IRETQ - - SWAPGS - jmp restore_c_regs_and_iret - -/* Returning to kernel space */ -retint_kernel: -#ifdef CONFIG_PREEMPT - /* Interrupts are off */ - /* Check if we need preemption */ - bt $9,EFLAGS(%rsp) /* interrupts were off? */ - jnc 1f -0: cmpl $0,PER_CPU_VAR(__preempt_count) - jnz 1f - call preempt_schedule_irq - jmp 0b -1: -#endif - /* - * The iretq could re-enable interrupts: - */ - TRACE_IRQS_IRETQ - -/* - * At this label, code paths which return to kernel and to user, - * which come from interrupts/exception and from syscalls, merge. - */ -restore_c_regs_and_iret: - RESTORE_C_REGS - REMOVE_PT_GPREGS_FROM_STACK 8 - INTERRUPT_RETURN - -ENTRY(native_iret) - /* - * Are we returning to a stack segment from the LDT? Note: in - * 64-bit mode SS:RSP on the exception stack is always valid. - */ -#ifdef CONFIG_X86_ESPFIX64 - testb $4,(SS-RIP)(%rsp) - jnz native_irq_return_ldt -#endif - -.global native_irq_return_iret -native_irq_return_iret: - /* - * This may fault. Non-paranoid faults on return to userspace are - * handled by fixup_bad_iret. These include #SS, #GP, and #NP. - * Double-faults due to espfix64 are handled in do_double_fault. - * Other faults here are fatal. - */ - iretq - -#ifdef CONFIG_X86_ESPFIX64 -native_irq_return_ldt: - pushq_cfi %rax - pushq_cfi %rdi - SWAPGS - movq PER_CPU_VAR(espfix_waddr),%rdi - movq %rax,(0*8)(%rdi) /* RAX */ - movq (2*8)(%rsp),%rax /* RIP */ - movq %rax,(1*8)(%rdi) - movq (3*8)(%rsp),%rax /* CS */ - movq %rax,(2*8)(%rdi) - movq (4*8)(%rsp),%rax /* RFLAGS */ - movq %rax,(3*8)(%rdi) - movq (6*8)(%rsp),%rax /* SS */ - movq %rax,(5*8)(%rdi) - movq (5*8)(%rsp),%rax /* RSP */ - movq %rax,(4*8)(%rdi) - andl $0xffff0000,%eax - popq_cfi %rdi - orq PER_CPU_VAR(espfix_stack),%rax - SWAPGS - movq %rax,%rsp - popq_cfi %rax - jmp native_irq_return_iret -#endif - - /* edi: workmask, edx: work */ -retint_careful: - CFI_RESTORE_STATE - bt $TIF_NEED_RESCHED,%edx - jnc retint_signal - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi - SCHEDULE_USER - popq_cfi %rdi - GET_THREAD_INFO(%rcx) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp retint_check - -retint_signal: - testl $_TIF_DO_NOTIFY_MASK,%edx - jz retint_swapgs - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - movq $-1,ORIG_RAX(%rsp) - xorl %esi,%esi # oldset - movq %rsp,%rdi # &pt_regs - call do_notify_resume - RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - jmp retint_with_reschedule - - CFI_ENDPROC -END(common_interrupt) - -/* - * APIC interrupts. - */ -.macro apicinterrupt3 num sym do_sym -ENTRY(\sym) - INTR_FRAME - ASM_CLAC - pushq_cfi $~(\num) -.Lcommon_\sym: - interrupt \do_sym - jmp ret_from_intr - CFI_ENDPROC -END(\sym) -.endm - -#ifdef CONFIG_TRACING -#define trace(sym) trace_##sym -#define smp_trace(sym) smp_trace_##sym - -.macro trace_apicinterrupt num sym -apicinterrupt3 \num trace(\sym) smp_trace(\sym) -.endm -#else -.macro trace_apicinterrupt num sym do_sym -.endm -#endif - -.macro apicinterrupt num sym do_sym -apicinterrupt3 \num \sym \do_sym -trace_apicinterrupt \num \sym -.endm - -#ifdef CONFIG_SMP -apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \ - irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt -apicinterrupt3 REBOOT_VECTOR \ - reboot_interrupt smp_reboot_interrupt -#endif - -#ifdef CONFIG_X86_UV -apicinterrupt3 UV_BAU_MESSAGE \ - uv_bau_message_intr1 uv_bau_message_interrupt -#endif -apicinterrupt LOCAL_TIMER_VECTOR \ - apic_timer_interrupt smp_apic_timer_interrupt -apicinterrupt X86_PLATFORM_IPI_VECTOR \ - x86_platform_ipi smp_x86_platform_ipi - -#ifdef CONFIG_HAVE_KVM -apicinterrupt3 POSTED_INTR_VECTOR \ - kvm_posted_intr_ipi smp_kvm_posted_intr_ipi -#endif - -#ifdef CONFIG_X86_MCE_THRESHOLD -apicinterrupt THRESHOLD_APIC_VECTOR \ - threshold_interrupt smp_threshold_interrupt -#endif - -#ifdef CONFIG_X86_THERMAL_VECTOR -apicinterrupt THERMAL_APIC_VECTOR \ - thermal_interrupt smp_thermal_interrupt -#endif - -#ifdef CONFIG_SMP -apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ - call_function_single_interrupt smp_call_function_single_interrupt -apicinterrupt CALL_FUNCTION_VECTOR \ - call_function_interrupt smp_call_function_interrupt -apicinterrupt RESCHEDULE_VECTOR \ - reschedule_interrupt smp_reschedule_interrupt -#endif - -apicinterrupt ERROR_APIC_VECTOR \ - error_interrupt smp_error_interrupt -apicinterrupt SPURIOUS_APIC_VECTOR \ - spurious_interrupt smp_spurious_interrupt - -#ifdef CONFIG_IRQ_WORK -apicinterrupt IRQ_WORK_VECTOR \ - irq_work_interrupt smp_irq_work_interrupt -#endif - -/* - * Exception entry points. - */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) - -.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 -ENTRY(\sym) - /* Sanity check */ - .if \shift_ist != -1 && \paranoid == 0 - .error "using shift_ist requires paranoid=1" - .endif - - .if \has_error_code - XCPT_FRAME - .else - INTR_FRAME - .endif - - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - - .ifeq \has_error_code - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - .endif - - ALLOC_PT_GPREGS_ON_STACK - - .if \paranoid - .if \paranoid == 1 - CFI_REMEMBER_STATE - testl $3, CS(%rsp) /* If coming from userspace, switch */ - jnz 1f /* stacks. */ - .endif - call paranoid_entry - .else - call error_entry - .endif - /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ - - DEFAULT_FRAME 0 - - .if \paranoid - .if \shift_ist != -1 - TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ - .else - TRACE_IRQS_OFF - .endif - .endif - - movq %rsp,%rdi /* pt_regs pointer */ - - .if \has_error_code - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ - .else - xorl %esi,%esi /* no error code */ - .endif - - .if \shift_ist != -1 - subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) - .endif - - call \do_sym - - .if \shift_ist != -1 - addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) - .endif - - /* these procedures expect "no swapgs" flag in ebx */ - .if \paranoid - jmp paranoid_exit - .else - jmp error_exit - .endif - - .if \paranoid == 1 - CFI_RESTORE_STATE - /* - * Paranoid entry from userspace. Switch stacks and treat it - * as a normal entry. This means that paranoid handlers - * run in real process context if user_mode(regs). - */ -1: - call error_entry - - DEFAULT_FRAME 0 - - movq %rsp,%rdi /* pt_regs pointer */ - call sync_regs - movq %rax,%rsp /* switch stack */ - - movq %rsp,%rdi /* pt_regs pointer */ - - .if \has_error_code - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ - .else - xorl %esi,%esi /* no error code */ - .endif - - call \do_sym - - jmp error_exit /* %ebx: no swapgs flag */ - .endif - - CFI_ENDPROC -END(\sym) -.endm - -#ifdef CONFIG_TRACING -.macro trace_idtentry sym do_sym has_error_code:req -idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code -idtentry \sym \do_sym has_error_code=\has_error_code -.endm -#else -.macro trace_idtentry sym do_sym has_error_code:req -idtentry \sym \do_sym has_error_code=\has_error_code -.endm -#endif - -idtentry divide_error do_divide_error has_error_code=0 -idtentry overflow do_overflow has_error_code=0 -idtentry bounds do_bounds has_error_code=0 -idtentry invalid_op do_invalid_op has_error_code=0 -idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=2 -idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 -idtentry invalid_TSS do_invalid_TSS has_error_code=1 -idtentry segment_not_present do_segment_not_present has_error_code=1 -idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 -idtentry coprocessor_error do_coprocessor_error has_error_code=0 -idtentry alignment_check do_alignment_check has_error_code=1 -idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 - - - /* Reload gs selector with exception handling */ - /* edi: new selector */ -ENTRY(native_load_gs_index) - CFI_STARTPROC - pushfq_cfi - DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) - SWAPGS -gs_change: - movl %edi,%gs -2: mfence /* workaround */ - SWAPGS - popfq_cfi - ret - CFI_ENDPROC -END(native_load_gs_index) - - _ASM_EXTABLE(gs_change,bad_gs) - .section .fixup,"ax" - /* running with kernelgs */ -bad_gs: - SWAPGS /* switch back to user gs */ - xorl %eax,%eax - movl %eax,%gs - jmp 2b - .previous - -/* Call softirq on interrupt stack. Interrupts are off. */ -ENTRY(do_softirq_own_stack) - CFI_STARTPROC - pushq_cfi %rbp - CFI_REL_OFFSET rbp,0 - mov %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - incl PER_CPU_VAR(irq_count) - cmove PER_CPU_VAR(irq_stack_ptr),%rsp - push %rbp # backlink for old unwinder - call __do_softirq - leaveq - CFI_RESTORE rbp - CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET -8 - decl PER_CPU_VAR(irq_count) - ret - CFI_ENDPROC -END(do_softirq_own_stack) - -#ifdef CONFIG_XEN -idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 - -/* - * A note on the "critical region" in our callback handler. - * We want to avoid stacking callback handlers due to events occurring - * during handling of the last event. To do this, we keep events disabled - * until we've done all processing. HOWEVER, we must enable events before - * popping the stack frame (can't be done atomically) and so it would still - * be possible to get enough handler activations to overflow the stack. - * Although unlikely, bugs of that kind are hard to track down, so we'd - * like to avoid the possibility. - * So, on entry to the handler we detect whether we interrupted an - * existing activation in its critical region -- if so, we pop the current - * activation and restart the handler using the previous one. - */ -ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) - CFI_STARTPROC -/* - * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will - * see the correct pointer to the pt_regs - */ - movq %rdi, %rsp # we don't return, adjust the stack frame - CFI_ENDPROC - DEFAULT_FRAME -11: incl PER_CPU_VAR(irq_count) - movq %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - pushq %rbp # backlink for old unwinder - call xen_evtchn_do_upcall - popq %rsp - CFI_DEF_CFA_REGISTER rsp - decl PER_CPU_VAR(irq_count) -#ifndef CONFIG_PREEMPT - call xen_maybe_preempt_hcall -#endif - jmp error_exit - CFI_ENDPROC -END(xen_do_hypervisor_callback) - -/* - * Hypervisor uses this for application faults while it executes. - * We get here for two reasons: - * 1. Fault while reloading DS, ES, FS or GS - * 2. Fault while executing IRET - * Category 1 we do not need to fix up as Xen has already reloaded all segment - * registers that could be reloaded and zeroed the others. - * Category 2 we fix up by killing the current process. We cannot use the - * normal Linux return path in this case because if we use the IRET hypercall - * to pop the stack frame we end up in an infinite loop of failsafe callbacks. - * We distinguish between categories by comparing each saved segment register - * with its current contents: any discrepancy means we in category 1. - */ -ENTRY(xen_failsafe_callback) - INTR_FRAME 1 (6*8) - /*CFI_REL_OFFSET gs,GS*/ - /*CFI_REL_OFFSET fs,FS*/ - /*CFI_REL_OFFSET es,ES*/ - /*CFI_REL_OFFSET ds,DS*/ - CFI_REL_OFFSET r11,8 - CFI_REL_OFFSET rcx,0 - movw %ds,%cx - cmpw %cx,0x10(%rsp) - CFI_REMEMBER_STATE - jne 1f - movw %es,%cx - cmpw %cx,0x18(%rsp) - jne 1f - movw %fs,%cx - cmpw %cx,0x20(%rsp) - jne 1f - movw %gs,%cx - cmpw %cx,0x28(%rsp) - jne 1f - /* All segments match their saved values => Category 2 (Bad IRET). */ - movq (%rsp),%rcx - CFI_RESTORE rcx - movq 8(%rsp),%r11 - CFI_RESTORE r11 - addq $0x30,%rsp - CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $0 /* RIP */ - pushq_cfi %r11 - pushq_cfi %rcx - jmp general_protection - CFI_RESTORE_STATE -1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ - movq (%rsp),%rcx - CFI_RESTORE rcx - movq 8(%rsp),%r11 - CFI_RESTORE r11 - addq $0x30,%rsp - CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $-1 /* orig_ax = -1 => not a system call */ - ALLOC_PT_GPREGS_ON_STACK - SAVE_C_REGS - SAVE_EXTRA_REGS - jmp error_exit - CFI_ENDPROC -END(xen_failsafe_callback) - -apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ - xen_hvm_callback_vector xen_evtchn_do_upcall - -#endif /* CONFIG_XEN */ - -#if IS_ENABLED(CONFIG_HYPERV) -apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ - hyperv_callback_vector hyperv_vector_handler -#endif /* CONFIG_HYPERV */ - -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry stack_segment do_stack_segment has_error_code=1 -#ifdef CONFIG_XEN -idtentry xen_debug do_debug has_error_code=0 -idtentry xen_int3 do_int3 has_error_code=0 -idtentry xen_stack_segment do_stack_segment has_error_code=1 -#endif -idtentry general_protection do_general_protection has_error_code=1 -trace_idtentry page_fault do_page_fault has_error_code=1 -#ifdef CONFIG_KVM_GUEST -idtentry async_page_fault do_async_page_fault has_error_code=1 -#endif -#ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) -#endif - -/* - * Save all registers in pt_regs, and switch gs if needed. - * Use slow, but surefire "are we in kernel?" check. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise - */ -ENTRY(paranoid_entry) - XCPT_FRAME 1 15*8 - cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - movl $1,%ebx - movl $MSR_GS_BASE,%ecx - rdmsr - testl %edx,%edx - js 1f /* negative -> in kernel */ - SWAPGS - xorl %ebx,%ebx -1: ret - CFI_ENDPROC -END(paranoid_entry) - -/* - * "Paranoid" exit path from exception stack. This is invoked - * only on return from non-NMI IST interrupts that came - * from kernel space. - * - * We may be returning to very strange contexts (e.g. very early - * in syscall entry), so checking for preemption here would - * be complicated. Fortunately, we there's no good reason - * to try to handle preemption here. - */ -/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ -ENTRY(paranoid_exit) - DEFAULT_FRAME - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF_DEBUG - testl %ebx,%ebx /* swapgs needed? */ - jnz paranoid_exit_no_swapgs - TRACE_IRQS_IRETQ - SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore -paranoid_exit_no_swapgs: - TRACE_IRQS_IRETQ_DEBUG -paranoid_exit_restore: - RESTORE_EXTRA_REGS - RESTORE_C_REGS - REMOVE_PT_GPREGS_FROM_STACK 8 - INTERRUPT_RETURN - CFI_ENDPROC -END(paranoid_exit) - -/* - * Save all registers in pt_regs, and switch gs if needed. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise - */ -ENTRY(error_entry) - XCPT_FRAME 1 15*8 - cld - SAVE_C_REGS 8 - SAVE_EXTRA_REGS 8 - xorl %ebx,%ebx - testl $3,CS+8(%rsp) - je error_kernelspace -error_swapgs: - SWAPGS -error_sti: - TRACE_IRQS_OFF - ret - - /* - * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. B stepping K8s sometimes report a - * truncated RIP for IRET exceptions returning to compat mode. Check - * for these here too. - */ -error_kernelspace: - CFI_REL_OFFSET rcx, RCX+8 - incl %ebx - leaq native_irq_return_iret(%rip),%rcx - cmpq %rcx,RIP+8(%rsp) - je error_bad_iret - movl %ecx,%eax /* zero extend */ - cmpq %rax,RIP+8(%rsp) - je bstep_iret - cmpq $gs_change,RIP+8(%rsp) - je error_swapgs - jmp error_sti - -bstep_iret: - /* Fix truncated RIP */ - movq %rcx,RIP+8(%rsp) - /* fall through */ - -error_bad_iret: - SWAPGS - mov %rsp,%rdi - call fixup_bad_iret - mov %rax,%rsp - decl %ebx /* Return to usergs */ - jmp error_sti - CFI_ENDPROC -END(error_entry) - - -/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ -ENTRY(error_exit) - DEFAULT_FRAME - movl %ebx,%eax - RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - testl %eax,%eax - jne retint_kernel - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - movl $_TIF_WORK_MASK,%edi - andl %edi,%edx - jnz retint_careful - jmp retint_swapgs - CFI_ENDPROC -END(error_exit) - -/* Runs on exception stack */ -ENTRY(nmi) - INTR_FRAME - PARAVIRT_ADJUST_EXCEPTION_FRAME - /* - * We allow breakpoints in NMIs. If a breakpoint occurs, then - * the iretq it performs will take us out of NMI context. - * This means that we can have nested NMIs where the next - * NMI is using the top of the stack of the previous NMI. We - * can't let it execute because the nested NMI will corrupt the - * stack of the previous NMI. NMI handlers are not re-entrant - * anyway. - * - * To handle this case we do the following: - * Check the a special location on the stack that contains - * a variable that is set when NMIs are executing. - * The interrupted task's stack is also checked to see if it - * is an NMI stack. - * If the variable is not set and the stack is not the NMI - * stack then: - * o Set the special variable on the stack - * o Copy the interrupt frame into an "outermost" location on the - * stack - * o Copy the interrupt frame into an "iret" location on the stack - * o Continue processing the NMI - * If the variable is set or the previous stack is the NMI stack: - * o Modify the "iret" location to jump to the repeat_nmi - * o return back to the first NMI - * - * Now on exit of the first NMI, we first clear the stack variable - * The NMI stack will tell any nested NMIs at that point that it is - * nested. Then we pop the stack normally with iret, and if there was - * a nested NMI that updated the copy interrupt stack frame, a - * jump will be made to the repeat_nmi code that will handle the second - * NMI. - * - * However, espfix prevents us from directly returning to userspace - * with a single IRET instruction. Similarly, IRET to user mode - * can fault. We therefore handle NMIs from user space like - * other IST entries. - */ - - /* Use %rdx as our temp variable throughout */ - pushq_cfi %rdx - CFI_REL_OFFSET rdx, 0 - - testb $3, CS-RIP+8(%rsp) - jz .Lnmi_from_kernel - - /* - * NMI from user mode. We need to run on the thread stack, but we - * can't go through the normal entry paths: NMIs are masked, and - * we don't want to enable interrupts, because then we'll end - * up in an awkward situation in which IRQs are on but NMIs - * are off. - */ - - SWAPGS - cld - movq %rsp, %rdx - movq PER_CPU_VAR(kernel_stack), %rsp - pushq 5*8(%rdx) /* pt_regs->ss */ - pushq 4*8(%rdx) /* pt_regs->rsp */ - pushq 3*8(%rdx) /* pt_regs->flags */ - pushq 2*8(%rdx) /* pt_regs->cs */ - pushq 1*8(%rdx) /* pt_regs->rip */ - pushq $-1 /* pt_regs->orig_ax */ - pushq %rdi /* pt_regs->di */ - pushq %rsi /* pt_regs->si */ - pushq (%rdx) /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx */ - pushq %rax /* pt_regs->ax */ - pushq %r8 /* pt_regs->r8 */ - pushq %r9 /* pt_regs->r9 */ - pushq %r10 /* pt_regs->r10 */ - pushq %r11 /* pt_regs->r11 */ - pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ - pushq %r12 /* pt_regs->r12 */ - pushq %r13 /* pt_regs->r13 */ - pushq %r14 /* pt_regs->r14 */ - pushq %r15 /* pt_regs->r15 */ - - /* - * At this point we no longer need to worry about stack damage - * due to nesting -- we're on the normal thread stack and we're - * done with the NMI stack. - */ - movq %rsp, %rdi - movq $-1, %rsi - call do_nmi - - /* - * Return back to user mode. We must *not* do the normal exit - * work, because we don't want to enable interrupts. Fortunately, - * do_nmi doesn't modify pt_regs. - */ - SWAPGS - jmp restore_c_regs_and_iret - -.Lnmi_from_kernel: - /* - * Here's what our stack frame will look like: - * +---------------------------------------------------------+ - * | original SS | - * | original Return RSP | - * | original RFLAGS | - * | original CS | - * | original RIP | - * +---------------------------------------------------------+ - * | temp storage for rdx | - * +---------------------------------------------------------+ - * | "NMI executing" variable | - * +---------------------------------------------------------+ - * | iret SS } Copied from "outermost" frame | - * | iret Return RSP } on each loop iteration; overwritten | - * | iret RFLAGS } by a nested NMI to force another | - * | iret CS } iteration if needed. | - * | iret RIP } | - * +---------------------------------------------------------+ - * | outermost SS } initialized in first_nmi; | - * | outermost Return RSP } will not be changed before | - * | outermost RFLAGS } NMI processing is done. | - * | outermost CS } Copied to "iret" frame on each | - * | outermost RIP } iteration. | - * +---------------------------------------------------------+ - * | pt_regs | - * +---------------------------------------------------------+ - * - * The "original" frame is used by hardware. Before re-enabling - * NMIs, we need to be done with it, and we need to leave enough - * space for the asm code here. - * - * We return by executing IRET while RSP points to the "iret" frame. - * That will either return for real or it will loop back into NMI - * processing. - * - * The "outermost" frame is copied to the "iret" frame on each - * iteration of the loop, so each iteration starts with the "iret" - * frame pointing to the final return target. - */ - - /* - * Determine whether we're a nested NMI. - * - * If we interrupted kernel code between repeat_nmi and - * end_repeat_nmi, then we are a nested NMI. We must not - * modify the "iret" frame because it's being written by - * the outer NMI. That's okay; the outer NMI handler is - * about to about to call do_nmi anyway, so we can just - * resume the outer NMI. - */ - - movq $repeat_nmi, %rdx - cmpq 8(%rsp), %rdx - ja 1f - movq $end_repeat_nmi, %rdx - cmpq 8(%rsp), %rdx - ja nested_nmi_out -1: - - /* - * Now check "NMI executing". If it's set, then we're nested. - * This will not detect if we interrupted an outer NMI just - * before IRET. - */ - cmpl $1, -8(%rsp) - je nested_nmi - - /* - * Now test if the previous stack was an NMI stack. This covers - * the case where we interrupt an outer NMI after it clears - * "NMI executing" but before IRET. We need to be careful, though: - * there is one case in which RSP could point to the NMI stack - * despite there being no NMI active: naughty userspace controls - * RSP at the very beginning of the SYSCALL targets. We can - * pull a fast one on naughty userspace, though: we program - * SYSCALL to mask DF, so userspace cannot cause DF to be set - * if it controls the kernel's RSP. We set DF before we clear - * "NMI executing". - */ - lea 6*8(%rsp), %rdx - /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */ - cmpq %rdx, 4*8(%rsp) - /* If the stack pointer is above the NMI stack, this is a normal NMI */ - ja first_nmi - subq $EXCEPTION_STKSZ, %rdx - cmpq %rdx, 4*8(%rsp) - /* If it is below the NMI stack, it is a normal NMI */ - jb first_nmi - - /* Ah, it is within the NMI stack. */ - - testb $(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp) - jz first_nmi /* RSP was user controlled. */ - - /* This is a nested NMI. */ - - CFI_REMEMBER_STATE - -nested_nmi: - /* - * Modify the "iret" frame to point to repeat_nmi, forcing another - * iteration of NMI handling. - */ - leaq -1*8(%rsp), %rdx - movq %rdx, %rsp - CFI_ADJUST_CFA_OFFSET 1*8 - leaq -10*8(%rsp), %rdx - pushq_cfi $__KERNEL_DS - pushq_cfi %rdx - pushfq_cfi - pushq_cfi $__KERNEL_CS - pushq_cfi $repeat_nmi - - /* Put stack back */ - addq $(6*8), %rsp - CFI_ADJUST_CFA_OFFSET -6*8 - -nested_nmi_out: - popq_cfi %rdx - CFI_RESTORE rdx - - /* We are returning to kernel mode, so this cannot result in a fault. */ - INTERRUPT_RETURN - - CFI_RESTORE_STATE -first_nmi: - /* Restore rdx. */ - movq (%rsp), %rdx - CFI_RESTORE rdx - - /* Set "NMI executing" on the stack. */ - pushq_cfi $1 - - /* Leave room for the "iret" frame */ - subq $(5*8), %rsp - CFI_ADJUST_CFA_OFFSET 5*8 - - /* Copy the "original" frame to the "outermost" frame */ - .rept 5 - pushq_cfi 11*8(%rsp) - .endr - CFI_DEF_CFA_OFFSET 5*8 - - /* Everything up to here is safe from nested NMIs */ - -repeat_nmi: - /* - * If there was a nested NMI, the first NMI's iret will return - * here. But NMIs are still enabled and we can take another - * nested NMI. The nested NMI checks the interrupted RIP to see - * if it is between repeat_nmi and end_repeat_nmi, and if so - * it will just return, as we are about to repeat an NMI anyway. - * This makes it safe to copy to the stack frame that a nested - * NMI will update. - * - * RSP is pointing to "outermost RIP". gsbase is unknown, but, if - * we're repeating an NMI, gsbase has the same value that it had on - * the first iteration. paranoid_entry will load the kernel - * gsbase if needed before we call do_nmi. - * - * Set "NMI executing" in case we came back here via IRET. - */ - movq $1, 10*8(%rsp) - - /* - * Copy the "outermost" frame to the "iret" frame. NMIs that nest - * here must not modify the "iret" frame while we're writing to - * it or it will end up containing garbage. - */ - addq $(10*8), %rsp - CFI_ADJUST_CFA_OFFSET -10*8 - .rept 5 - pushq_cfi -6*8(%rsp) - .endr - subq $(5*8), %rsp - CFI_DEF_CFA_OFFSET 5*8 -end_repeat_nmi: - - /* - * Everything below this point can be preempted by a nested NMI. - * If this happens, then the inner NMI will change the "iret" - * frame to point back to repeat_nmi. - */ - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - ALLOC_PT_GPREGS_ON_STACK - - /* - * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit - * as we should not be calling schedule in NMI context. - * Even with normal interrupts enabled. An NMI should not be - * setting NEED_RESCHED or anything that normal interrupts and - * exceptions might do. - */ - call paranoid_entry - DEFAULT_FRAME 0 - - /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ - movq %rsp,%rdi - movq $-1,%rsi - call do_nmi - - testl %ebx,%ebx /* swapgs needed? */ - jnz nmi_restore -nmi_swapgs: - SWAPGS_UNSAFE_STACK -nmi_restore: - RESTORE_EXTRA_REGS - RESTORE_C_REGS - - /* Point RSP at the "iret" frame. */ - REMOVE_PT_GPREGS_FROM_STACK 6*8 - - /* - * Clear "NMI executing". Set DF first so that we can easily - * distinguish the remaining code between here and IRET from - * the SYSCALL entry and exit paths. On a native kernel, we - * could just inspect RIP, but, on paravirt kernels, - * INTERRUPT_RETURN can translate into a jump into a - * hypercall page. - */ - std - movq $0, 5*8(%rsp) /* clear "NMI executing" */ - - /* - * INTERRUPT_RETURN reads the "iret" frame and exits the NMI - * stack in a single instruction. We are returning to kernel - * mode, so this cannot result in a fault. - */ - INTERRUPT_RETURN - CFI_ENDPROC -END(nmi) - -ENTRY(ignore_sysret) - CFI_STARTPROC - mov $-ENOSYS,%eax - sysret - CFI_ENDPROC -END(ignore_sysret) - diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 7cce04c98..ce95676ab 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -131,25 +131,24 @@ void __init init_espfix_bsp(void) init_espfix_random(); /* The rest is the same as for any other processor */ - init_espfix_ap(); + init_espfix_ap(0); } -void init_espfix_ap(void) +void init_espfix_ap(int cpu) { - unsigned int cpu, page; + unsigned int page; unsigned long addr; pud_t pud, *pud_p; pmd_t pmd, *pmd_p; pte_t pte, *pte_p; - int n; + int n, node; void *stack_page; pteval_t ptemask; /* We only have to do this once... */ - if (likely(this_cpu_read(espfix_stack))) + if (likely(per_cpu(espfix_stack, cpu))) return; /* Already initialized */ - cpu = smp_processor_id(); addr = espfix_base_addr(cpu); page = cpu/ESPFIX_STACKS_PER_PAGE; @@ -165,13 +164,15 @@ void init_espfix_ap(void) if (stack_page) goto unlock_done; + node = cpu_to_node(cpu); ptemask = __supported_pte_mask; pud_p = &espfix_pud_page[pud_index(addr)]; pud = *pud_p; if (!pud_present(pud)) { - pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); - SetPageTOI_Untracked(virt_to_page(pmd_p)); + struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); + + pmd_p = (pmd_t *)page_address(page); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) @@ -181,8 +182,9 @@ void init_espfix_ap(void) pmd_p = pmd_offset(&pud, addr); pmd = *pmd_p; if (!pmd_present(pmd)) { - pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); - SetPageTOI_Untracked(virt_to_page(pte_p)); + struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); + + pte_p = (pte_t *)page_address(page); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) @@ -190,8 +192,7 @@ void init_espfix_ap(void) } pte_p = pte_offset_kernel(&pmd, addr); - stack_page = (void *)__get_free_page(GFP_KERNEL); - SetPageTOI_Untracked(virt_to_page(stack_page)); + stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); @@ -202,7 +203,7 @@ void init_espfix_ap(void) unlock_done: mutex_unlock(&espfix_init_mutex); done: - this_cpu_write(espfix_stack, addr); - this_cpu_write(espfix_waddr, (unsigned long)stack_page - + (addr & ~PAGE_MASK)); + per_cpu(espfix_stack, cpu) = addr; + per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page + + (addr & ~PAGE_MASK); } diff --git a/arch/x86/kernel/fpu/Makefile b/arch/x86/kernel/fpu/Makefile new file mode 100644 index 000000000..68279efb8 --- /dev/null +++ b/arch/x86/kernel/fpu/Makefile @@ -0,0 +1,5 @@ +# +# Build rules for the FPU support code: +# + +obj-y += init.o bugs.o core.o regset.o signal.o xstate.o diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c new file mode 100644 index 000000000..dd9ca9b60 --- /dev/null +++ b/arch/x86/kernel/fpu/bugs.c @@ -0,0 +1,71 @@ +/* + * x86 FPU bug checks: + */ +#include <asm/fpu/internal.h> + +/* + * Boot time CPU/FPU FDIV bug detection code: + */ + +static double __initdata x = 4195835.0; +static double __initdata y = 3145727.0; + +/* + * This used to check for exceptions.. + * However, it turns out that to support that, + * the XMM trap handlers basically had to + * be buggy. So let's have a correct XMM trap + * handler, and forget about printing out + * some status at boot. + * + * We should really only care about bugs here + * anyway. Not features. + */ +static void __init check_fpu(void) +{ + u32 cr0_saved; + s32 fdiv_bug; + + /* We might have CR0::TS set already, clear it: */ + cr0_saved = read_cr0(); + write_cr0(cr0_saved & ~X86_CR0_TS); + + kernel_fpu_begin(); + + /* + * trap_init() enabled FXSR and company _before_ testing for FP + * problems here. + * + * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug + */ + __asm__("fninit\n\t" + "fldl %1\n\t" + "fdivl %2\n\t" + "fmull %2\n\t" + "fldl %1\n\t" + "fsubp %%st,%%st(1)\n\t" + "fistpl %0\n\t" + "fwait\n\t" + "fninit" + : "=m" (*&fdiv_bug) + : "m" (*&x), "m" (*&y)); + + kernel_fpu_end(); + + write_cr0(cr0_saved); + + if (fdiv_bug) { + set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); + pr_warn("Hmm, FPU with FDIV bug\n"); + } +} + +void __init fpu__init_check_bugs(void) +{ + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + if (cpu_has_fpu) + check_fpu(); +} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c new file mode 100644 index 000000000..d25097c3f --- /dev/null +++ b/arch/x86/kernel/fpu/core.c @@ -0,0 +1,523 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/regset.h> +#include <asm/fpu/signal.h> +#include <asm/traps.h> + +#include <linux/hardirq.h> + +/* + * Represents the initial FPU state. It's mostly (but not completely) zeroes, + * depending on the FPU hardware format: + */ +union fpregs_state init_fpstate __read_mostly; + +/* + * Track whether the kernel is using the FPU state + * currently. + * + * This flag is used: + * + * - by IRQ context code to potentially use the FPU + * if it's unused. + * + * - to debug kernel_fpu_begin()/end() correctness + */ +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +/* + * Track which context is using the FPU on the CPU: + */ +DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +static void kernel_fpu_disable(void) +{ + WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); +} + +static void kernel_fpu_enable(void) +{ + WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); +} + +static bool kernel_fpu_disabled(void) +{ + return this_cpu_read(in_kernel_fpu); +} + +/* + * Were we in an interrupt that interrupted kernel mode? + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + * + * Except for the eagerfpu case when we return true; in the likely case + * the thread has FPU but we are not going to set/clear TS. + */ +static bool interrupted_kernel_fpu_idle(void) +{ + if (kernel_fpu_disabled()) + return false; + + if (use_eager_fpu()) + return true; + + return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void __kernel_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + WARN_ON_FPU(!irq_fpu_usable()); + + kernel_fpu_disable(); + + if (fpu->fpregs_active) { + copy_fpregs_to_fpstate(fpu); + } else { + this_cpu_write(fpu_fpregs_owner_ctx, NULL); + __fpregs_activate_hw(); + } +} +EXPORT_SYMBOL(__kernel_fpu_begin); + +void __kernel_fpu_end(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (fpu->fpregs_active) + copy_kernel_to_fpregs(&fpu->state); + else + __fpregs_deactivate_hw(); + + kernel_fpu_enable(); +} +EXPORT_SYMBOL(__kernel_fpu_end); + +void kernel_fpu_begin(void) +{ + preempt_disable(); + __kernel_fpu_begin(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + __kernel_fpu_end(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); + +/* + * CR0::TS save/restore functions: + */ +int irq_ts_save(void) +{ + /* + * If in process context and not atomic, we can take a spurious DNA fault. + * Otherwise, doing clts() in process context requires disabling preemption + * or some heavy lifting like kernel_fpu_begin() + */ + if (!in_atomic()) + return 0; + + if (read_cr0() & X86_CR0_TS) { + clts(); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(irq_ts_save); + +void irq_ts_restore(int TS_state) +{ + if (TS_state) + stts(); +} +EXPORT_SYMBOL_GPL(irq_ts_restore); + +/* + * Save the FPU state (mark it for reload if necessary): + * + * This only ever gets called for the current task. + */ +void fpu__save(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + preempt_disable(); + if (fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(fpu)) + fpregs_deactivate(fpu); + } + preempt_enable(); +} +EXPORT_SYMBOL_GPL(fpu__save); + +/* + * Legacy x87 fpstate state init: + */ +static inline void fpstate_init_fstate(struct fregs_state *fp) +{ + fp->cwd = 0xffff037fu; + fp->swd = 0xffff0000u; + fp->twd = 0xffffffffu; + fp->fos = 0xffff0000u; +} + +void fpstate_init(union fpregs_state *state) +{ + if (!cpu_has_fpu) { + fpstate_init_soft(&state->soft); + return; + } + + memset(state, 0, xstate_size); + + if (cpu_has_fxsr) + fpstate_init_fxstate(&state->fxsave); + else + fpstate_init_fstate(&state->fsave); +} +EXPORT_SYMBOL_GPL(fpstate_init); + +/* + * Copy the current task's FPU state to a new task's FPU context. + * + * In both the 'eager' and the 'lazy' case we save hardware registers + * directly to the destination buffer. + */ +static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + WARN_ON_FPU(src_fpu != ¤t->thread.fpu); + + /* + * Don't let 'init optimized' areas of the XSAVE area + * leak into the child task: + */ + if (use_eager_fpu()) + memset(&dst_fpu->state.xsave, 0, xstate_size); + + /* + * Save current FPU registers directly into the child + * FPU context, without any memory-to-memory copying. + * + * If the FPU context got destroyed in the process (FNSAVE + * done on old CPUs) then copy it back into the source + * context and mark the current task for lazy restore. + * + * We have to do all this with preemption disabled, + * mostly because of the FNSAVE case, because in that + * case we must not allow preemption in the window + * between the FNSAVE and us marking the context lazy. + * + * It shouldn't be an issue as even FNSAVE is plenty + * fast in terms of critical section length. + */ + preempt_disable(); + if (!copy_fpregs_to_fpstate(dst_fpu)) { + memcpy(&src_fpu->state, &dst_fpu->state, xstate_size); + fpregs_deactivate(src_fpu); + } + preempt_enable(); +} + +int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + dst_fpu->counter = 0; + dst_fpu->fpregs_active = 0; + dst_fpu->last_cpu = -1; + + if (src_fpu->fpstate_active && cpu_has_fpu) + fpu_copy(dst_fpu, src_fpu); + + return 0; +} + +/* + * Activate the current task's in-memory FPU context, + * if it has not been used before: + */ +void fpu__activate_curr(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for the current task: */ + fpu->fpstate_active = 1; + } +} +EXPORT_SYMBOL_GPL(fpu__activate_curr); + +/* + * This function must be called before we read a task's fpstate. + * + * If the task has not used the FPU before then initialize its + * fpstate. + * + * If the task has used the FPU before then save it. + */ +void fpu__activate_fpstate_read(struct fpu *fpu) +{ + /* + * If fpregs are active (in the current CPU), then + * copy them to the fpstate: + */ + if (fpu->fpregs_active) { + fpu__save(fpu); + } else { + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for current and for stopped child tasks: */ + fpu->fpstate_active = 1; + } + } +} + +/* + * This function must be called before we write a task's fpstate. + * + * If the task has used the FPU before then unlazy it. + * If the task has not used the FPU before then initialize its fpstate. + * + * After this function call, after registers in the fpstate are + * modified and the child task has woken up, the child task will + * restore the modified FPU state from the modified context. If we + * didn't clear its lazy status here then the lazy in-registers + * state pending on its former CPU could be restored, corrupting + * the modifications. + */ +void fpu__activate_fpstate_write(struct fpu *fpu) +{ + /* + * Only stopped child tasks can be used to modify the FPU + * state in the fpstate buffer: + */ + WARN_ON_FPU(fpu == ¤t->thread.fpu); + + if (fpu->fpstate_active) { + /* Invalidate any lazy state: */ + fpu->last_cpu = -1; + } else { + fpstate_init(&fpu->state); + + /* Safe to do for stopped child tasks: */ + fpu->fpstate_active = 1; + } +} + +/* + * 'fpu__restore()' is called to copy FPU registers from + * the FPU fpstate to the live hw registers and to activate + * access to the hardware registers, so that FPU instructions + * can be used afterwards. + * + * Must be called with kernel preemption disabled (for example + * with local interrupts disabled, as it is in the case of + * do_device_not_available()). + */ +void fpu__restore(struct fpu *fpu) +{ + fpu__activate_curr(fpu); + + /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ + kernel_fpu_disable(); + fpregs_activate(fpu); + copy_kernel_to_fpregs(&fpu->state); + fpu->counter++; + kernel_fpu_enable(); +} +EXPORT_SYMBOL_GPL(fpu__restore); + +/* + * Drops current FPU state: deactivates the fpregs and + * the fpstate. NOTE: it still leaves previous contents + * in the fpregs in the eager-FPU case. + * + * This function can be used in cases where we know that + * a state-restore is coming: either an explicit one, + * or a reschedule. + */ +void fpu__drop(struct fpu *fpu) +{ + preempt_disable(); + fpu->counter = 0; + + if (fpu->fpregs_active) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } + + fpu->fpstate_active = 0; + + preempt_enable(); +} + +/* + * Clear FPU registers by setting them up from + * the init fpstate: + */ +static inline void copy_init_fpstate_to_fpregs(void) +{ + if (use_xsave()) + copy_kernel_to_xregs(&init_fpstate.xsave, -1); + else + copy_kernel_to_fxregs(&init_fpstate.fxsave); +} + +/* + * Clear the FPU state back to init state. + * + * Called by sys_execve(), by the signal handler code and by various + * error paths. + */ +void fpu__clear(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ + + if (!use_eager_fpu()) { + /* FPU state will be reallocated lazily at the first use. */ + fpu__drop(fpu); + } else { + if (!fpu->fpstate_active) { + fpu__activate_curr(fpu); + user_fpu_begin(); + } + copy_init_fpstate_to_fpregs(); + } +} + +/* + * x87 math exception handling: + */ + +static inline unsigned short get_fpu_cwd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.cwd; + } else { + return (unsigned short)fpu->state.fsave.cwd; + } +} + +static inline unsigned short get_fpu_swd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.swd; + } else { + return (unsigned short)fpu->state.fsave.swd; + } +} + +static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) +{ + if (cpu_has_xmm) { + return fpu->state.fxsave.mxcsr; + } else { + return MXCSR_DEFAULT; + } +} + +int fpu__exception_code(struct fpu *fpu, int trap_nr) +{ + int err; + + if (trap_nr == X86_TRAP_MF) { + unsigned short cwd, swd; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't synchronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(fpu); + swd = get_fpu_swd(fpu); + + err = swd & ~cwd; + } else { + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + unsigned short mxcsr = get_fpu_mxcsr(fpu); + err = ~(mxcsr >> 7) & mxcsr; + } + + if (err & 0x001) { /* Invalid op */ + /* + * swd & 0x240 == 0x040: Stack Underflow + * swd & 0x240 == 0x240: Stack Overflow + * User must clear the SF bit (0x40) if set + */ + return FPE_FLTINV; + } else if (err & 0x004) { /* Divide by Zero */ + return FPE_FLTDIV; + } else if (err & 0x008) { /* Overflow */ + return FPE_FLTOVF; + } else if (err & 0x012) { /* Denormal, Underflow */ + return FPE_FLTUND; + } else if (err & 0x020) { /* Precision */ + return FPE_FLTRES; + } + + /* + * If we're using IRQ 13, or supposedly even some trap + * X86_TRAP_MF implementations, it's possible + * we get a spurious trap, which is not an error. + */ + return 0; +} diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c new file mode 100644 index 000000000..d14e9ac32 --- /dev/null +++ b/arch/x86/kernel/fpu/init.c @@ -0,0 +1,406 @@ +/* + * x86 FPU boot time init code: + */ +#include <asm/fpu/internal.h> +#include <asm/tlbflush.h> + +#include <linux/sched.h> + +/* + * Initialize the TS bit in CR0 according to the style of context-switches + * we are using: + */ +static void fpu__init_cpu_ctx_switch(void) +{ + if (!cpu_has_eager_fpu) + stts(); + else + clts(); +} + +/* + * Initialize the registers found in all CPUs, CR0 and CR4: + */ +static void fpu__init_cpu_generic(void) +{ + unsigned long cr0; + unsigned long cr4_mask = 0; + + if (cpu_has_fxsr) + cr4_mask |= X86_CR4_OSFXSR; + if (cpu_has_xmm) + cr4_mask |= X86_CR4_OSXMMEXCPT; + if (cr4_mask) + cr4_set_bits(cr4_mask); + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ + if (!cpu_has_fpu) + cr0 |= X86_CR0_EM; + write_cr0(cr0); + + /* Flush out any pending x87 state: */ +#ifdef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) + fpstate_init_soft(¤t->thread.fpu.state.soft); + else +#endif + asm volatile ("fninit"); +} + +/* + * Enable all supported FPU features. Called when a CPU is brought online: + */ +void fpu__init_cpu(void) +{ + fpu__init_cpu_generic(); + fpu__init_cpu_xstate(); + fpu__init_cpu_ctx_switch(); +} + +/* + * The earliest FPU detection code. + * + * Set the X86_FEATURE_FPU CPU-capability bit based on + * trying to execute an actual sequence of FPU instructions: + */ +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + unsigned long cr0; + u16 fsw, fcw; + + fsw = fcw = 0xffff; + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS | X86_CR0_EM); + write_cr0(cr0); + + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); + + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + +#ifndef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) { + pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); + for (;;) + asm volatile("hlt"); + } +#endif +} + +/* + * Boot time FPU feature detection code: + */ +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; + +static void __init fpu__init_system_mxcsr(void) +{ + unsigned int mask = 0; + + if (cpu_has_fxsr) { + /* Static because GCC does not get 16-byte stack alignment right: */ + static struct fxregs_state fxregs __initdata; + + asm volatile("fxsave %0" : "+m" (fxregs)); + + mask = fxregs.mxcsr_mask; + + /* + * If zero then use the default features mask, + * which has all features set, except the + * denormals-are-zero feature bit: + */ + if (mask == 0) + mask = 0x0000ffbf; + } + mxcsr_feature_mask &= mask; +} + +/* + * Once per bootup FPU initialization sequences that will run on most x86 CPUs: + */ +static void __init fpu__init_system_generic(void) +{ + /* + * Set up the legacy init FPU context. (xstate init might overwrite this + * with a more modern format, if the CPU supports it.) + */ + fpstate_init_fxstate(&init_fpstate.fxsave); + + fpu__init_system_mxcsr(); +} + +/* + * Size of the FPU context state. All tasks in the system use the + * same context size, regardless of what portion they use. + * This is inherent to the XSAVE architecture which puts all state + * components into a single, continuous memory block: + */ +unsigned int xstate_size; +EXPORT_SYMBOL_GPL(xstate_size); + +/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ + BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + +/* + * We append the 'struct fpu' to the task_struct: + */ +static void __init fpu__init_task_struct_size(void) +{ + int task_size = sizeof(struct task_struct); + + /* + * Subtract off the static size of the register state. + * It potentially has a bunch of padding. + */ + task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state); + + /* + * Add back the dynamically-calculated register state + * size. + */ + task_size += xstate_size; + + /* + * We dynamically size 'struct fpu', so we require that + * it be at the end of 'thread_struct' and that + * 'thread_struct' be at the end of 'task_struct'. If + * you hit a compile error here, check the structure to + * see if something got added to the end. + */ + CHECK_MEMBER_AT_END_OF(struct fpu, state); + CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); + CHECK_MEMBER_AT_END_OF(struct task_struct, thread); + + arch_task_struct_size = task_size; +} + +/* + * Set up the xstate_size based on the legacy FPU context size. + * + * We set this up first, and later it will be overwritten by + * fpu__init_system_xstate() if the CPU knows about xstates. + */ +static void __init fpu__init_system_xstate_size_legacy(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + /* + * Note that xstate_size might be overwriten later during + * fpu__init_system_xstate(). + */ + + if (!cpu_has_fpu) { + /* + * Disable xsave as we do not support it if i387 + * emulation is enabled. + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + xstate_size = sizeof(struct swregs_state); + } else { + if (cpu_has_fxsr) + xstate_size = sizeof(struct fxregs_state); + else + xstate_size = sizeof(struct fregs_state); + } + /* + * Quirk: we don't yet handle the XSAVES* instructions + * correctly, as we don't correctly convert between + * standard and compacted format when interfacing + * with user-space - so disable it for now. + * + * The difference is small: with recent CPUs the + * compacted format is only marginally smaller than + * the standard FPU state format. + * + * ( This is easy to backport while we are fixing + * XSAVES* support. ) + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* + * FPU context switching strategies: + * + * Against popular belief, we don't do lazy FPU saves, due to the + * task migration complications it brings on SMP - we only do + * lazy FPU restores. + * + * 'lazy' is the traditional strategy, which is based on setting + * CR0::TS to 1 during context-switch (instead of doing a full + * restore of the FPU state), which causes the first FPU instruction + * after the context switch (whenever it is executed) to fault - at + * which point we lazily restore the FPU state into FPU registers. + * + * Tasks are of course under no obligation to execute FPU instructions, + * so it can easily happen that another context-switch occurs without + * a single FPU instruction being executed. If we eventually switch + * back to the original task (that still owns the FPU) then we have + * not only saved the restores along the way, but we also have the + * FPU ready to be used for the original task. + * + * 'eager' switching is used on modern CPUs, there we switch the FPU + * state during every context switch, regardless of whether the task + * has used FPU instructions in that time slice or not. This is done + * because modern FPU context saving instructions are able to optimize + * state saving and restoration in hardware: they can detect both + * unused and untouched FPU state and optimize accordingly. + * + * [ Note that even in 'lazy' mode we might optimize context switches + * to use 'eager' restores, if we detect that a task is using the FPU + * frequently. See the fpu->counter logic in fpu/internal.h for that. ] + */ +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; + +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + +/* + * Pick the FPU context switching strategy: + */ +static void __init fpu__init_system_ctx_switch(void) +{ + static bool on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + WARN_ON_FPU(current->thread.fpu.fpstate_active); + current_thread_info()->status = 0; + + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; + + if (xfeatures_mask & XSTATE_EAGER) { + if (eagerfpu == DISABLE) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XSTATE_EAGER); + xfeatures_mask &= ~XSTATE_EAGER; + } else { + eagerfpu = ENABLE; + } + } + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy"); +} + +/* + * Called on the boot CPU once per system bootup, to set up the initial + * FPU state that is later cloned into all processes: + */ +void __init fpu__init_system(struct cpuinfo_x86 *c) +{ + fpu__init_system_early_generic(c); + + /* + * The FPU has to be operational for some of the + * later FPU init activities: + */ + fpu__init_cpu(); + + /* + * But don't leave CR0::TS set yet, as some of the FPU setup + * methods depend on being able to execute FPU instructions + * that will fault on a set TS, such as the FXSAVE in + * fpu__init_system_mxcsr(). + */ + clts(); + + fpu__init_system_generic(); + fpu__init_system_xstate_size_legacy(); + fpu__init_system_xstate(); + fpu__init_task_struct_size(); + + fpu__init_system_ctx_switch(); +} + +/* + * Boot parameter to turn off FPU support and fall back to math-emu: + */ +static int __init no_387(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FPU); + return 1; +} +__setup("no387", no_387); + +/* + * Disable all xstate CPU features: + */ +static int __init x86_noxsave_setup(char *s) +{ + if (strlen(s)) + return 0; + + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_XSAVEC); + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); + setup_clear_cpu_cap(X86_FEATURE_AVX512F); + setup_clear_cpu_cap(X86_FEATURE_AVX512PF); + setup_clear_cpu_cap(X86_FEATURE_AVX512ER); + setup_clear_cpu_cap(X86_FEATURE_AVX512CD); + setup_clear_cpu_cap(X86_FEATURE_MPX); + + return 1; +} +__setup("noxsave", x86_noxsave_setup); + +/* + * Disable the XSAVEOPT instruction specifically: + */ +static int __init x86_noxsaveopt_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + return 1; +} +__setup("noxsaveopt", x86_noxsaveopt_setup); + +/* + * Disable the XSAVES instruction: + */ +static int __init x86_noxsaves_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + return 1; +} +__setup("noxsaves", x86_noxsaves_setup); + +/* + * Disable FX save/restore and SSE support: + */ +static int __init x86_nofxsr_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + + return 1; +} +__setup("nofxsr", x86_nofxsr_setup); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c new file mode 100644 index 000000000..dc60810c1 --- /dev/null +++ b/arch/x86/kernel/fpu/regset.c @@ -0,0 +1,356 @@ +/* + * FPU register's regset abstraction, for ptrace, core dumps, etc. + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +/* + * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, + * as the "regset->n" for the xstate regset will be updated based on the feature + * capabilites supported by the xsave. + */ +int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return target_fpu->fpstate_active ? regset->n : 0; +} + +int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; +} + +int xfpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + fpstate_sanitize_xstate(fpu); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); +} + +int xfpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + int ret; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); + + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; + + /* + * update the header bits in the xsave header, indicating the + * presence of FP and SSE state. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE; + + return ret; +} + +int xstateregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + + xsave = &fpu->state.xsave; + + /* + * Copy the 48bytes defined by the software first into the xstate + * memory layout in the thread struct, so that we can copy the entire + * xstateregs to the user using one user_regset_copyout(). + */ + memcpy(&xsave->i387.sw_reserved, + xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); + /* + * Copy the xstate memory layout. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + return ret; +} + +int xstateregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + + xsave = &fpu->state.xsave; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + xsave->header.xfeatures &= xfeatures_mask; + /* + * These bits must be zero. + */ + memset(&xsave->header.reserved, 0, 48); + + return ret; +} + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + +/* + * FPU tag word conversions. + */ + +static inline unsigned short twd_i387_to_fxsr(unsigned short twd) +{ + unsigned int tmp; /* to avoid 16 bit prefixes in the code */ + + /* Transform each pair of bits into 01 (valid) or 00 (empty) */ + tmp = ~twd; + tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ + /* and move the valid bits to the lower byte. */ + tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ + tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ + tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ + + return tmp; +} + +#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) +#define FP_EXP_TAG_VALID 0 +#define FP_EXP_TAG_ZERO 1 +#define FP_EXP_TAG_SPECIAL 2 +#define FP_EXP_TAG_EMPTY 3 + +static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave) +{ + struct _fpxreg *st; + u32 tos = (fxsave->swd >> 11) & 7; + u32 twd = (unsigned long) fxsave->twd; + u32 tag; + u32 ret = 0xffff0000u; + int i; + + for (i = 0; i < 8; i++, twd >>= 1) { + if (twd & 0x1) { + st = FPREG_ADDR(fxsave, (i - tos) & 7); + + switch (st->exponent & 0x7fff) { + case 0x7fff: + tag = FP_EXP_TAG_SPECIAL; + break; + case 0x0000: + if (!st->significand[0] && + !st->significand[1] && + !st->significand[2] && + !st->significand[3]) + tag = FP_EXP_TAG_ZERO; + else + tag = FP_EXP_TAG_SPECIAL; + break; + default: + if (st->significand[3] & 0x8000) + tag = FP_EXP_TAG_VALID; + else + tag = FP_EXP_TAG_SPECIAL; + break; + } + } else { + tag = FP_EXP_TAG_EMPTY; + } + ret |= tag << (2 * i); + } + return ret; +} + +/* + * FXSR floating point environment conversions. + */ + +void +convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + env->cwd = fxsave->cwd | 0xffff0000u; + env->swd = fxsave->swd | 0xffff0000u; + env->twd = twd_fxsr_to_i387(fxsave); + +#ifdef CONFIG_X86_64 + env->fip = fxsave->rip; + env->foo = fxsave->rdp; + /* + * should be actually ds/cs at fpu exception time, but + * that information is not available in 64bit mode. + */ + env->fcs = task_pt_regs(tsk)->cs; + if (tsk == current) { + savesegment(ds, env->fos); + } else { + env->fos = tsk->thread.ds; + } + env->fos |= 0xffff0000; +#else + env->fip = fxsave->fip; + env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); + env->foo = fxsave->foo; + env->fos = fxsave->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(to[0])); +} + +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) + +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + fxsave->cwd = env->cwd; + fxsave->swd = env->swd; + fxsave->twd = twd_i387_to_fxsr(env->twd); + fxsave->fop = (u16) ((u32) env->fcs >> 16); +#ifdef CONFIG_X86_64 + fxsave->rip = env->fip; + fxsave->rdp = env->foo; + /* cs and ds ignored */ +#else + fxsave->fip = env->fip; + fxsave->fcs = (env->fcs & 0xffff); + fxsave->foo = env->foo; + fxsave->fos = env->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(from[0])); +} + +int fpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + + fpu__activate_fpstate_read(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + fpstate_sanitize_xstate(fpu); + + if (kbuf && pos == 0 && count == sizeof(env)) { + convert_from_fxsr(kbuf, target); + return 0; + } + + convert_from_fxsr(&env, target); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); +} + +int fpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + int ret; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + if (pos > 0 || count < sizeof(env)) + convert_from_fxsr(&env, target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); + if (!ret) + convert_to_fxsr(target, &env); + + /* + * update the header bit in the xsave header, indicating the + * presence of FP. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XSTATE_FP; + return ret; +} + +/* + * FPU state for core dumps. + * This is only used for a.out dumps now. + * It is declared generically using elf_fpregset_t (which is + * struct user_i387_struct) but is in fact only used for 32-bit + * dumps, so on 64-bit it is really struct user_i387_ia32_struct. + */ +int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) +{ + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int fpvalid; + + fpvalid = fpu->fpstate_active; + if (fpvalid) + fpvalid = !fpregs_get(tsk, NULL, + 0, sizeof(struct user_i387_ia32_struct), + ufpu, NULL); + + return fpvalid; +} +EXPORT_SYMBOL(dump_fpu); + +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c new file mode 100644 index 000000000..50ec9af1b --- /dev/null +++ b/arch/x86/kernel/fpu/signal.c @@ -0,0 +1,404 @@ +/* + * FPU signal frame handling routines. + */ + +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/sigframe.h> + +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; + +/* + * Check for the presence of extended state information in the + * user fpstate pointer in the sigcontext. + */ +static inline int check_for_xstate(struct fxregs_state __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) +{ + int min_xstate_size = sizeof(struct fxregs_state) + + sizeof(struct xstate_header); + unsigned int magic2; + + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; + + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; + + /* + * Check for the presence of second magic word at the end of memory + * layout. This detects the case where the user just copied the legacy + * fpstate layout with out copying the extended state information + * in the memory layout. + */ + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; + + return 0; +} + +/* + * Signal frame handlers. + */ +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) +{ + if (use_fxsr()) { + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct user_i387_ia32_struct env; + struct _fpstate_ia32 __user *fp = buf; + + convert_from_fxsr(&env, tsk); + + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; + } else { + struct fregs_state __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) + return -1; + } + + return 0; +} + +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xregs_state __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xfeatures; + int err; + + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); + + if (!use_xsave()) + return err; + + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); + + /* + * Read the xfeatures which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures); + + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xfeatures in the xsave header. + * + * xsave aware apps can change the xfeatures in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xfeatures |= XSTATE_FPSSE; + + err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures); + + return err; +} + +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +{ + int err; + + if (use_xsave()) + err = copy_xregs_to_user(buf); + else if (use_fxsr()) + err = copy_fxregs_to_user((struct fxregs_state __user *) buf); + else + err = copy_fregs_to_user((struct fregs_state __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; +} + +/* + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. + */ +int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +{ + struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_ia32 __user *) buf) ? -1 : 1; + + if (fpregs_active()) { + /* Save the live register state to the user directly. */ + if (copy_fpregs_to_sigframe(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + copy_fxregs_to_kernel(&tsk->thread.fpu); + } else { + fpstate_sanitize_xstate(&tsk->thread.fpu); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + return 0; +} + +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xfeatures, int fx_only) +{ + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct xstate_header *header = &xsave->header; + + if (use_xsave()) { + /* These bits must be zero. */ + memset(header->reserved, 0, 48); + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + header->xfeatures = XSTATE_FPSSE; + else + header->xfeatures &= (xfeatures_mask & xfeatures); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } +} + +/* + * Restore the extended state if present. Otherwise, restore the FP/SSE state. + */ +static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) +{ + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE; + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_fxregs(buf); + } else { + u64 init_bv = xfeatures_mask & ~xbv; + if (unlikely(init_bv)) + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_xregs(buf, xbv); + } + } else if (use_fxsr()) { + return copy_user_to_fxregs(buf); + } else + return copy_user_to_fregs(buf); +} + +static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int state_size = xstate_size; + u64 xfeatures = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!buf) { + fpu__clear(fpu); + return 0; + } + + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + fpu__activate_curr(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; + + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct fxregs_state); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xfeatures = fx_sw_user.xfeatures; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct fpu *fpu = &tsk->thread.fpu; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears fpu->fpstate_active. This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * fpu->fpstate_active is again set. + */ + fpu__drop(fpu); + + if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + fpstate_init(&fpu->state); + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); + } + + fpu->fpstate_active = 1; + if (use_eager_fpu()) { + preempt_disable(); + fpu__restore(fpu); + preempt_enable(); + } + + return err; + } else { + /* + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). + */ + user_fpu_begin(); + if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) { + fpu__clear(fpu); + return -1; + } + } + + return 0; +} + +static inline int xstate_sigframe_size(void) +{ + return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; +} + +/* + * Restore FPU state from a sigframe: + */ +int fpu__restore_sig(void __user *buf, int ia32_frame) +{ + void __user *buf_fx = buf; + int size = xstate_sigframe_size(); + + if (ia32_frame && use_fxsr()) { + buf_fx = buf + sizeof(struct fregs_state); + size += sizeof(struct fregs_state); + } + + return __fpu__restore_sig(buf, buf_fx, size); +} + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size) +{ + unsigned long frame_size = xstate_sigframe_size(); + + *buf_fx = sp = round_down(sp - frame_size, 64); + if (ia32_frame && use_fxsr()) { + frame_size += sizeof(struct fregs_state); + sp -= sizeof(struct fregs_state); + } + + *size = frame_size; + + return sp; +} +/* + * Prepare the SW reserved portion of the fxsave memory layout, indicating + * the presence of the extended state information in the memory layout + * pointed by the fpstate pointer in the sigcontext. + * This will be saved when ever the FP and extended state context is + * saved on the user stack during the signal handler delivery to the user. + */ +void fpu__init_prepare_fx_sw_frame(void) +{ + int fsave_header_size = sizeof(struct fregs_state); + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; + + if (config_enabled(CONFIG_X86_32)) + size += fsave_header_size; + + fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; + fx_sw_reserved.extended_size = size; + fx_sw_reserved.xfeatures = xfeatures_mask; + fx_sw_reserved.xstate_size = xstate_size; + + if (config_enabled(CONFIG_IA32_EMULATION)) { + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size += fsave_header_size; + } +} + diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c new file mode 100644 index 000000000..62fc001c7 --- /dev/null +++ b/arch/x86/kernel/fpu/xstate.c @@ -0,0 +1,461 @@ +/* + * xsave/xrstor support. + * + * Author: Suresh Siddha <suresh.b.siddha@intel.com> + */ +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/api.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/tlbflush.h> + +static const char *xfeature_names[] = +{ + "x87 floating point registers" , + "SSE registers" , + "AVX registers" , + "MPX bounds registers" , + "MPX CSR" , + "AVX-512 opmask" , + "AVX-512 Hi256" , + "AVX-512 ZMM_Hi256" , + "unknown xstate feature" , +}; + +/* + * Mask of xstate features supported by the CPU and the kernel: + */ +u64 xfeatures_mask __read_mostly; + +static unsigned int xstate_offsets[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1}; +static unsigned int xstate_sizes[XFEATURES_NR_MAX] = { [ 0 ... XFEATURES_NR_MAX - 1] = -1}; +static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8]; + +/* The number of supported xfeatures in xfeatures_mask: */ +static unsigned int xfeatures_nr; + +/* + * Return whether the system supports a given xfeature. + * + * Also return the name of the (most advanced) feature that the caller requested: + */ +int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) +{ + u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask; + + if (unlikely(feature_name)) { + long xfeature_idx, max_idx; + u64 xfeatures_print; + /* + * So we use FLS here to be able to print the most advanced + * feature that was requested but is missing. So if a driver + * asks about "XSTATE_SSE | XSTATE_YMM" we'll print the + * missing AVX feature - this is the most informative message + * to users: + */ + if (xfeatures_missing) + xfeatures_print = xfeatures_missing; + else + xfeatures_print = xfeatures_needed; + + xfeature_idx = fls64(xfeatures_print)-1; + max_idx = ARRAY_SIZE(xfeature_names)-1; + xfeature_idx = min(xfeature_idx, max_idx); + + *feature_name = xfeature_names[xfeature_idx]; + } + + if (xfeatures_missing) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(cpu_has_xfeatures); + +/* + * When executing XSAVEOPT (or other optimized XSAVE instructions), if + * a processor implementation detects that an FPU state component is still + * (or is again) in its initialized state, it may clear the corresponding + * bit in the header.xfeatures field, and can skip the writeout of registers + * to the corresponding memory layout. + * + * This means that when the bit is zero, the state component might still contain + * some previous - non-initialized register state. + * + * Before writing xstate information to user-space we sanitize those components, + * to always ensure that the memory layout of a feature will be in the init state + * if the corresponding header bit is zero. This is to ensure that user-space doesn't + * see some stale state in the memory layout during signal handling, debugging etc. + */ +void fpstate_sanitize_xstate(struct fpu *fpu) +{ + struct fxregs_state *fx = &fpu->state.fxsave; + int feature_bit; + u64 xfeatures; + + if (!use_xsaveopt()) + return; + + xfeatures = fpu->state.xsave.header.xfeatures; + + /* + * None of the feature bits are in init state. So nothing else + * to do for us, as the memory layout is up to date. + */ + if ((xfeatures & xfeatures_mask) == xfeatures_mask) + return; + + /* + * FP is in init state + */ + if (!(xfeatures & XSTATE_FP)) { + fx->cwd = 0x37f; + fx->swd = 0; + fx->twd = 0; + fx->fop = 0; + fx->rip = 0; + fx->rdp = 0; + memset(&fx->st_space[0], 0, 128); + } + + /* + * SSE is in init state + */ + if (!(xfeatures & XSTATE_SSE)) + memset(&fx->xmm_space[0], 0, 256); + + /* + * First two features are FPU and SSE, which above we handled + * in a special way already: + */ + feature_bit = 0x2; + xfeatures = (xfeatures_mask & ~xfeatures) >> 2; + + /* + * Update all the remaining memory layouts according to their + * standard xstate layout, if their header bit is in the init + * state: + */ + while (xfeatures) { + if (xfeatures & 0x1) { + int offset = xstate_offsets[feature_bit]; + int size = xstate_sizes[feature_bit]; + + memcpy((void *)fx + offset, + (void *)&init_fpstate.xsave + offset, + size); + } + + xfeatures >>= 1; + feature_bit++; + } +} + +/* + * Enable the extended processor state save/restore feature. + * Called once per CPU onlining. + */ +void fpu__init_cpu_xstate(void) +{ + if (!cpu_has_xsave || !xfeatures_mask) + return; + + cr4_set_bits(X86_CR4_OSXSAVE); + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Record the offsets and sizes of various xstates contained + * in the XSAVE state memory layout. + * + * ( Note that certain features might be non-present, for them + * we'll have 0 offset and 0 size. ) + */ +static void __init setup_xstate_features(void) +{ + u32 eax, ebx, ecx, edx, leaf; + + xfeatures_nr = fls64(xfeatures_mask); + + for (leaf = 2; leaf < xfeatures_nr; leaf++) { + cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); + + xstate_offsets[leaf] = ebx; + xstate_sizes[leaf] = eax; + + printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %04x, xstate_sizes[%d]: %04x\n", leaf, ebx, leaf, eax); + } +} + +static void __init print_xstate_feature(u64 xstate_mask) +{ + const char *feature_name; + + if (cpu_has_xfeatures(xstate_mask, &feature_name)) + pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name); +} + +/* + * Print out all the supported xstate features: + */ +static void __init print_xstate_features(void) +{ + print_xstate_feature(XSTATE_FP); + print_xstate_feature(XSTATE_SSE); + print_xstate_feature(XSTATE_YMM); + print_xstate_feature(XSTATE_BNDREGS); + print_xstate_feature(XSTATE_BNDCSR); + print_xstate_feature(XSTATE_OPMASK); + print_xstate_feature(XSTATE_ZMM_Hi256); + print_xstate_feature(XSTATE_Hi16_ZMM); +} + +/* + * This function sets up offsets and sizes of all extended states in + * xsave area. This supports both standard format and compacted format + * of the xsave aread. + */ +static void __init setup_xstate_comp(void) +{ + unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8]; + int i; + + /* + * The FP xstates and SSE xstates are legacy states. They are always + * in the fixed offsets in the xsave area in either compacted form + * or standard form. + */ + xstate_comp_offsets[0] = 0; + xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); + + if (!cpu_has_xsaves) { + for (i = 2; i < xfeatures_nr; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) { + xstate_comp_offsets[i] = xstate_offsets[i]; + xstate_comp_sizes[i] = xstate_sizes[i]; + } + } + return; + } + + xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; + + for (i = 2; i < xfeatures_nr; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) + xstate_comp_sizes[i] = xstate_sizes[i]; + else + xstate_comp_sizes[i] = 0; + + if (i > 2) + xstate_comp_offsets[i] = xstate_comp_offsets[i-1] + + xstate_comp_sizes[i-1]; + + } +} + +/* + * setup the xstate image representing the init state + */ +static void __init setup_init_fpu_buf(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); + print_xstate_features(); + + if (cpu_has_xsaves) { + init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; + init_fpstate.xsave.header.xfeatures = xfeatures_mask; + } + + /* + * Init all the features state with header_bv being 0x0 + */ + copy_kernel_to_xregs_booting(&init_fpstate.xsave); + + /* + * Dump the init state again. This is to identify the init state + * of any feature which is not represented by all zero's. + */ + copy_xregs_to_kernel_booting(&init_fpstate.xsave); +} + +/* + * Calculate total size of enabled xstates in XCR0/xfeatures_mask. + */ +static void __init init_xstate_size(void) +{ + unsigned int eax, ebx, ecx, edx; + int i; + + if (!cpu_has_xsaves) { + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xstate_size = ebx; + return; + } + + xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + for (i = 2; i < 64; i++) { + if (test_bit(i, (unsigned long *)&xfeatures_mask)) { + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_size += eax; + } + } +} + +/* + * Enable and initialize the xsave feature. + * Called once per system bootup. + */ +void __init fpu__init_system_xstate(void) +{ + unsigned int eax, ebx, ecx, edx; + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) { + pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + return; + } + + if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { + WARN_ON_FPU(1); + return; + } + + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xfeatures_mask = eax + ((u64)edx << 32); + + if ((xfeatures_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { + pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask); + BUG(); + } + + /* Support only the state known to the OS: */ + xfeatures_mask = xfeatures_mask & XCNTXT_MASK; + + /* Enable xstate instructions to be able to continue with initialization: */ + fpu__init_cpu_xstate(); + + /* Recompute the context size for enabled features: */ + init_xstate_size(); + + update_regset_xstate_info(xstate_size, xfeatures_mask); + fpu__init_prepare_fx_sw_frame(); + setup_init_fpu_buf(); + setup_xstate_comp(); + + pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is 0x%x bytes, using '%s' format.\n", + xfeatures_mask, + xstate_size, + cpu_has_xsaves ? "compacted" : "standard"); +} + +/* + * Restore minimal FPU state after suspend: + */ +void fpu__resume_cpu(void) +{ + /* + * Restore XCR0 on xsave capable CPUs: + */ + if (cpu_has_xsave) + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Given the xsave area and a state inside, this function returns the + * address of the state. + * + * This is the API that is called to get xstate address in either + * standard format or compacted format of xsave area. + * + * Note that if there is no data for the field in the xsave buffer + * this will return NULL. + * + * Inputs: + * xstate: the thread's storage area for all FPU data + * xstate_feature: state which is defined in xsave.h (e.g. + * XSTATE_FP, XSTATE_SSE, etc...) + * Output: + * address of the state in the xsave area, or NULL if the + * field is not present in the xsave buffer. + */ +void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) +{ + int feature_nr = fls64(xstate_feature) - 1; + /* + * Do we even *have* xsave state? + */ + if (!boot_cpu_has(X86_FEATURE_XSAVE)) + return NULL; + + xsave = ¤t->thread.fpu.state.xsave; + /* + * We should not ever be requesting features that we + * have not enabled. Remember that pcntxt_mask is + * what we write to the XCR0 register. + */ + WARN_ONCE(!(xfeatures_mask & xstate_feature), + "get of unsupported state"); + /* + * This assumes the last 'xsave*' instruction to + * have requested that 'xstate_feature' be saved. + * If it did not, we might be seeing and old value + * of the field in the buffer. + * + * This can happen because the last 'xsave' did not + * request that this feature be saved (unlikely) + * or because the "init optimization" caused it + * to not be saved. + */ + if (!(xsave->header.xfeatures & xstate_feature)) + return NULL; + + return (void *)xsave + xstate_comp_offsets[feature_nr]; +} +EXPORT_SYMBOL_GPL(get_xsave_addr); + +/* + * This wraps up the common operations that need to occur when retrieving + * data from xsave state. It first ensures that the current task was + * using the FPU and retrieves the data in to a buffer. It then calculates + * the offset of the requested field in the buffer. + * + * This function is safe to call whether the FPU is in use or not. + * + * Note that this only works on the current task. + * + * Inputs: + * @xsave_state: state which is defined in xsave.h (e.g. XSTATE_FP, + * XSTATE_SSE, etc...) + * Output: + * address of the state in the xsave area or NULL if the state + * is not present or is in its 'init state'. + */ +const void *get_xsave_field_ptr(int xsave_state) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (!fpu->fpstate_active) + return NULL; + /* + * fpu__save() takes the CPU's xstate registers + * and saves them off to the 'fpu memory buffer. + */ + fpu__save(fpu); + + return get_xsave_addr(&fpu->state.xsave, xsave_state); +} diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 7e429c99c..0e2d96ffd 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -557,7 +557,7 @@ early_idt_handler_common: cld cmpl $2,(%esp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,%ss:early_recursion_flag je hlt_loop @@ -610,7 +610,7 @@ ex_entry: pop %ecx pop %eax decl %ss:early_recursion_flag -is_nmi: +.Lis_nmi: addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler_common) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7e5da2cbe..1d40ca8a7 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -346,7 +346,7 @@ early_idt_handler_common: cld cmpl $2,(%rsp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,early_recursion_flag(%rip) jz 1f @@ -411,7 +411,7 @@ early_idt_handler_common: popq %rcx popq %rax decl early_recursion_flag(%rip) -is_nmi: +.Lis_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler_common) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 3acbff471..10757d0a3 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -12,6 +12,7 @@ #include <linux/pm.h> #include <linux/io.h> +#include <asm/irqdomain.h> #include <asm/fixmap.h> #include <asm/hpet.h> #include <asm/time.h> @@ -305,8 +306,6 @@ static void hpet_legacy_clockevent_register(void) printk(KERN_DEBUG "hpet clockevent registered\n"); } -static int hpet_setup_msi_irq(unsigned int irq); - static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { @@ -357,7 +356,7 @@ static void hpet_set_mode(enum clock_event_mode mode, hpet_enable_legacy_int(); } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - hpet_setup_msi_irq(hdev->irq); + irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); @@ -423,6 +422,7 @@ static int hpet_legacy_next_event(unsigned long delta, static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev); static struct hpet_dev *hpet_devs; +static struct irq_domain *hpet_domain; void hpet_msi_unmask(struct irq_data *data) { @@ -473,31 +473,6 @@ static int hpet_msi_next_event(unsigned long delta, return hpet_next_event(delta, evt, hdev->num); } -static int hpet_setup_msi_irq(unsigned int irq) -{ - if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { - irq_free_hwirq(irq); - return -EINVAL; - } - return 0; -} - -static int hpet_assign_irq(struct hpet_dev *dev) -{ - unsigned int irq = irq_alloc_hwirq(-1); - - if (!irq) - return -EINVAL; - - irq_set_handler_data(irq, dev); - - if (hpet_setup_msi_irq(irq)) - return -EINVAL; - - dev->irq = irq; - return 0; -} - static irqreturn_t hpet_interrupt_handler(int irq, void *data) { struct hpet_dev *dev = (struct hpet_dev *)data; @@ -540,9 +515,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) if (!(hdev->flags & HPET_DEV_VALID)) return; - if (hpet_setup_msi_irq(hdev->irq)) - return; - hdev->cpu = cpu; per_cpu(cpu_hpet_dev, cpu) = hdev; evt->name = hdev->name; @@ -574,7 +546,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int id; unsigned int num_timers; unsigned int num_timers_used = 0; - int i; + int i, irq; if (hpet_msi_disable) return; @@ -587,6 +559,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) num_timers++; /* Value read out starts from 0 */ hpet_print_config(); + hpet_domain = hpet_create_irq_domain(hpet_blockid); + if (!hpet_domain) + return; + hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL); if (!hpet_devs) return; @@ -604,12 +580,14 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) hdev->flags = 0; if (cfg & HPET_TN_PERIODIC_CAP) hdev->flags |= HPET_DEV_PERI_CAP; + sprintf(hdev->name, "hpet%d", i); hdev->num = i; - sprintf(hdev->name, "hpet%d", i); - if (hpet_assign_irq(hdev)) + irq = hpet_assign_irq(hpet_domain, hdev, hdev->num); + if (irq <= 0) continue; + hdev->irq = irq; hdev->flags |= HPET_DEV_FSB_CAP; hdev->flags |= HPET_DEV_VALID; num_timers_used++; @@ -709,10 +687,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n, } #else -static int hpet_setup_msi_irq(unsigned int irq) -{ - return 0; -} static void hpet_msi_capability_lookup(unsigned int start_timer) { return; diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index 05fd74f53..64341aa48 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c deleted file mode 100644 index 6185d3141..000000000 --- a/arch/x86/kernel/i387.c +++ /dev/null @@ -1,671 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - */ -#include <linux/module.h> -#include <linux/regset.h> -#include <linux/sched.h> -#include <linux/slab.h> - -#include <asm/sigcontext.h> -#include <asm/processor.h> -#include <asm/math_emu.h> -#include <asm/tlbflush.h> -#include <asm/uaccess.h> -#include <asm/ptrace.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/user.h> - -static DEFINE_PER_CPU(bool, in_kernel_fpu); - -void kernel_fpu_disable(void) -{ - WARN_ON(this_cpu_read(in_kernel_fpu)); - this_cpu_write(in_kernel_fpu, true); -} - -void kernel_fpu_enable(void) -{ - this_cpu_write(in_kernel_fpu, false); -} - -/* - * Were we in an interrupt that interrupted kernel mode? - * - * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that - * pair does nothing at all: the thread must not have fpu (so - * that we don't try to save the FPU state), and TS must - * be set (so that the clts/stts pair does nothing that is - * visible in the interrupted kernel thread). - * - * Except for the eagerfpu case when we return true; in the likely case - * the thread has FPU but we are not going to set/clear TS. - */ -static inline bool interrupted_kernel_fpu_idle(void) -{ - if (this_cpu_read(in_kernel_fpu)) - return false; - - if (use_eager_fpu()) - return true; - - return !__thread_has_fpu(current) && - (read_cr0() & X86_CR0_TS); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static inline bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - -/* - * Can we use the FPU in kernel mode with the - * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. - */ -bool irq_fpu_usable(void) -{ - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); -} -EXPORT_SYMBOL(irq_fpu_usable); - -void __kernel_fpu_begin(void) -{ - struct task_struct *me = current; - - this_cpu_write(in_kernel_fpu, true); - - if (__thread_has_fpu(me)) { - __save_init_fpu(me); - } else { - this_cpu_write(fpu_owner_task, NULL); - if (!use_eager_fpu()) - clts(); - } -} -EXPORT_SYMBOL(__kernel_fpu_begin); - -void __kernel_fpu_end(void) -{ - struct task_struct *me = current; - - if (__thread_has_fpu(me)) { - if (WARN_ON(restore_fpu_checking(me))) - fpu_reset_state(me); - } else if (!use_eager_fpu()) { - stts(); - } - - this_cpu_write(in_kernel_fpu, false); -} -EXPORT_SYMBOL(__kernel_fpu_end); - -void unlazy_fpu(struct task_struct *tsk) -{ - preempt_disable(); - if (__thread_has_fpu(tsk)) { - if (use_eager_fpu()) { - __save_fpu(tsk); - } else { - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - } - } - preempt_enable(); -} -EXPORT_SYMBOL(unlazy_fpu); - -unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; -unsigned int xstate_size; -EXPORT_SYMBOL_GPL(xstate_size); -static struct i387_fxsave_struct fx_scratch; - -static void mxcsr_feature_mask_init(void) -{ - unsigned long mask = 0; - - if (cpu_has_fxsr) { - memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : "+m" (fx_scratch)); - mask = fx_scratch.mxcsr_mask; - if (mask == 0) - mask = 0x0000ffbf; - } - mxcsr_feature_mask &= mask; -} - -static void init_thread_xstate(void) -{ - /* - * Note that xstate_size might be overwriten later during - * xsave_init(). - */ - - if (!cpu_has_fpu) { - /* - * Disable xsave as we do not support it if i387 - * emulation is enabled. - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - xstate_size = sizeof(struct i387_soft_struct); - return; - } - - if (cpu_has_fxsr) - xstate_size = sizeof(struct i387_fxsave_struct); - else - xstate_size = sizeof(struct i387_fsave_struct); - - /* - * Quirk: we don't yet handle the XSAVES* instructions - * correctly, as we don't correctly convert between - * standard and compacted format when interfacing - * with user-space - so disable it for now. - * - * The difference is small: with recent CPUs the - * compacted format is only marginally smaller than - * the standard FPU state format. - * - * ( This is easy to backport while we are fixing - * XSAVES* support. ) - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); -} - -/* - * Called at bootup to set up the initial FPU state that is later cloned - * into all processes. - */ - -void fpu_init(void) -{ - unsigned long cr0; - unsigned long cr4_mask = 0; - -#ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { - pr_emerg("No FPU found and no math emulation present\n"); - pr_emerg("Giving up\n"); - for (;;) - asm volatile("hlt"); - } -#endif - if (cpu_has_fxsr) - cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) - cr4_mask |= X86_CR4_OSXMMEXCPT; - if (cr4_mask) - cr4_set_bits(cr4_mask); - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) - cr0 |= X86_CR0_EM; - write_cr0(cr0); - - /* - * init_thread_xstate is only called once to avoid overriding - * xstate_size during boot time or during CPU hotplug. - */ - if (xstate_size == 0) - init_thread_xstate(); - - mxcsr_feature_mask_init(); - xsave_init(); - eager_fpu_init(); -} - -void fpu_finit(struct fpu *fpu) -{ - if (!cpu_has_fpu) { - finit_soft_fpu(&fpu->state->soft); - return; - } - - memset(fpu->state, 0, xstate_size); - - if (cpu_has_fxsr) { - fx_finit(&fpu->state->fxsave); - } else { - struct i387_fsave_struct *fp = &fpu->state->fsave; - fp->cwd = 0xffff037fu; - fp->swd = 0xffff0000u; - fp->twd = 0xffffffffu; - fp->fos = 0xffff0000u; - } -} -EXPORT_SYMBOL_GPL(fpu_finit); - -/* - * The _current_ task is using the FPU for the first time - * so initialize it and set the mxcsr to its default - * value at reset if we support XMM instructions and then - * remember the current task has used the FPU. - */ -int init_fpu(struct task_struct *tsk) -{ - int ret; - - if (tsk_used_math(tsk)) { - if (cpu_has_fpu && tsk == current) - unlazy_fpu(tsk); - task_disable_lazy_fpu_restore(tsk); - return 0; - } - - /* - * Memory allocation at the first usage of the FPU and other state. - */ - ret = fpu_alloc(&tsk->thread.fpu); - if (ret) - return ret; - - fpu_finit(&tsk->thread.fpu); - - set_stopped_child_used_math(tsk); - return 0; -} -EXPORT_SYMBOL_GPL(init_fpu); - -/* - * The xstateregs_active() routine is the same as the fpregs_active() routine, - * as the "regset->n" for the xstate regset will be updated based on the feature - * capabilites supported by the xsave. - */ -int fpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return tsk_used_math(target) ? regset->n : 0; -} - -int xfpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0; -} - -int xfpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); -} - -int xfpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); - - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - - /* - * update the header bits in the xsave header, indicating the - * presence of FP and SSE state. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - return ret; -} - -int xstateregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - /* - * Copy the 48bytes defined by the software first into the xstate - * memory layout in the thread struct, so that we can copy the entire - * xstateregs to the user using one user_regset_copyout(). - */ - memcpy(&xsave->i387.sw_reserved, - xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); - /* - * Copy the xstate memory layout. - */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - return ret; -} - -int xstateregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->xsave_hdr.xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - memset(&xsave->xsave_hdr.reserved, 0, 48); - return ret; -} - -#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION - -/* - * FPU tag word conversions. - */ - -static inline unsigned short twd_i387_to_fxsr(unsigned short twd) -{ - unsigned int tmp; /* to avoid 16 bit prefixes in the code */ - - /* Transform each pair of bits into 01 (valid) or 00 (empty) */ - tmp = ~twd; - tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ - /* and move the valid bits to the lower byte. */ - tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ - tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ - tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ - - return tmp; -} - -#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) -#define FP_EXP_TAG_VALID 0 -#define FP_EXP_TAG_ZERO 1 -#define FP_EXP_TAG_SPECIAL 2 -#define FP_EXP_TAG_EMPTY 3 - -static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) -{ - struct _fpxreg *st; - u32 tos = (fxsave->swd >> 11) & 7; - u32 twd = (unsigned long) fxsave->twd; - u32 tag; - u32 ret = 0xffff0000u; - int i; - - for (i = 0; i < 8; i++, twd >>= 1) { - if (twd & 0x1) { - st = FPREG_ADDR(fxsave, (i - tos) & 7); - - switch (st->exponent & 0x7fff) { - case 0x7fff: - tag = FP_EXP_TAG_SPECIAL; - break; - case 0x0000: - if (!st->significand[0] && - !st->significand[1] && - !st->significand[2] && - !st->significand[3]) - tag = FP_EXP_TAG_ZERO; - else - tag = FP_EXP_TAG_SPECIAL; - break; - default: - if (st->significand[3] & 0x8000) - tag = FP_EXP_TAG_VALID; - else - tag = FP_EXP_TAG_SPECIAL; - break; - } - } else { - tag = FP_EXP_TAG_EMPTY; - } - ret |= tag << (2 * i); - } - return ret; -} - -/* - * FXSR floating point environment conversions. - */ - -void -convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - env->cwd = fxsave->cwd | 0xffff0000u; - env->swd = fxsave->swd | 0xffff0000u; - env->twd = twd_fxsr_to_i387(fxsave); - -#ifdef CONFIG_X86_64 - env->fip = fxsave->rip; - env->foo = fxsave->rdp; - /* - * should be actually ds/cs at fpu exception time, but - * that information is not available in 64bit mode. - */ - env->fcs = task_pt_regs(tsk)->cs; - if (tsk == current) { - savesegment(ds, env->fos); - } else { - env->fos = tsk->thread.ds; - } - env->fos |= 0xffff0000; -#else - env->fip = fxsave->fip; - env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); - env->foo = fxsave->foo; - env->fos = fxsave->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(to[0])); -} - -void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) - -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - fxsave->cwd = env->cwd; - fxsave->swd = env->swd; - fxsave->twd = twd_i387_to_fxsr(env->twd); - fxsave->fop = (u16) ((u32) env->fcs >> 16); -#ifdef CONFIG_X86_64 - fxsave->rip = env->fip; - fxsave->rdp = env->foo; - /* cs and ds ignored */ -#else - fxsave->fip = env->fip; - fxsave->fcs = (env->fcs & 0xffff); - fxsave->foo = env->foo; - fxsave->fos = env->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(from[0])); -} - -int fpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - sanitize_i387_state(target); - - if (kbuf && pos == 0 && count == sizeof(env)) { - convert_from_fxsr(kbuf, target); - return 0; - } - - convert_from_fxsr(&env, target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); -} - -int fpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - if (pos > 0 || count < sizeof(env)) - convert_from_fxsr(&env, target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); - if (!ret) - convert_to_fxsr(target, &env); - - /* - * update the header bit in the xsave header, indicating the - * presence of FP. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP; - return ret; -} - -/* - * FPU state for core dumps. - * This is only used for a.out dumps now. - * It is declared generically using elf_fpregset_t (which is - * struct user_i387_struct) but is in fact only used for 32-bit - * dumps, so on 64-bit it is really struct user_i387_ia32_struct. - */ -int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu) -{ - struct task_struct *tsk = current; - int fpvalid; - - fpvalid = !!used_math(); - if (fpvalid) - fpvalid = !fpregs_get(tsk, NULL, - 0, sizeof(struct user_i387_ia32_struct), - fpu, NULL); - - return fpvalid; -} -EXPORT_SYMBOL(dump_fpu); - -#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ - -static int __init no_387(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FPU); - return 1; -} - -__setup("no387", no_387); - -void fpu_detect(struct cpuinfo_x86 *c) -{ - unsigned long cr0; - u16 fsw, fcw; - - fsw = fcw = 0xffff; - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS | X86_CR0_EM); - write_cr0(cr0); - - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); - - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); - - /* The final cr0 value is set in fpu_init() */ -} diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index e7cc5370c..16cb827a5 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -329,8 +329,8 @@ static void init_8259A(int auto_eoi) */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */ - outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); + /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */ + outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); @@ -342,8 +342,8 @@ static void init_8259A(int auto_eoi) outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ - /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */ - outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR); + /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */ + outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR); /* 8259A-2 is a slave on master's IR2 */ outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */ diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 816f81544..37dae792d 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -28,18 +28,8 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) return -EINVAL; -#ifdef CONFIG_SCHED_BFS_AUTOISO - if (turn_on) { - struct sched_param param = { .sched_priority = 0 }; - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - /* Start X as SCHED_ISO */ - sched_setscheduler_nocheck(current, SCHED_ISO, ¶m); - } -#else if (turn_on && !capable(CAP_SYS_RAWIO)) return -EPERM; -#endif /* * If it's the first ioperm() call in this thread's lifetime, set the @@ -113,15 +103,8 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) return -EINVAL; /* Trying to gain more privileges? */ if (level > old) { -#ifdef CONFIG_SCHED_BFS_AUTOISO - struct sched_param param = { .sched_priority = 0 }; -#endif if (!capable(CAP_SYS_RAWIO)) return -EPERM; -#ifdef CONFIG_SCHED_BFS_AUTOISO - /* Start X as SCHED_ISO */ - sched_setscheduler_nocheck(current, SCHED_ISO, ¶m); -#endif } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); t->iopl = level << 12; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index e5952c225..c7dfe1be7 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -22,6 +22,12 @@ #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +EXPORT_PER_CPU_SYMBOL(irq_stat); + +DEFINE_PER_CPU(struct pt_regs *, irq_regs); +EXPORT_PER_CPU_SYMBOL(irq_regs); + atomic_t irq_err_count; /* Function pointer for generic interrupt vector handling */ @@ -116,6 +122,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); seq_puts(p, " Threshold APIC interrupts\n"); #endif +#ifdef CONFIG_X86_MCE_AMD + seq_printf(p, "%*s: ", prec, "DFR"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count); + seq_puts(p, " Deferred Error APIC interrupts\n"); +#endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); for_each_online_cpu(j) @@ -136,6 +148,18 @@ int arch_show_interrupts(struct seq_file *p, int prec) #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); #endif +#ifdef CONFIG_HAVE_KVM + seq_printf(p, "%*s: ", prec, "PIN"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); + seq_puts(p, " Posted-interrupt notification event\n"); + + seq_printf(p, "%*s: ", prec, "PIW"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->kvm_posted_intr_wakeup_ipis); + seq_puts(p, " Posted-interrupt wakeup event\n"); +#endif return 0; } @@ -192,8 +216,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) unsigned vector = ~regs->orig_ax; unsigned irq; - irq_enter(); - exit_idle(); + entering_irq(); irq = __this_cpu_read(vector_irq[vector]); @@ -209,7 +232,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) } } - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); return 1; @@ -237,6 +260,18 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs) } #ifdef CONFIG_HAVE_KVM +static void dummy_handler(void) {} +static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler; + +void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)) +{ + if (handler) + kvm_posted_intr_wakeup_handler = handler; + else + kvm_posted_intr_wakeup_handler = dummy_handler; +} +EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); + /* * Handler for POSTED_INTERRUPT_VECTOR. */ @@ -244,16 +279,23 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - ack_APIC_irq(); - - irq_enter(); - - exit_idle(); - + entering_ack_irq(); inc_irq_stat(kvm_posted_intr_ipis); + exiting_irq(); + set_irq_regs(old_regs); +} - irq_exit(); +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + entering_ack_irq(); + inc_irq_stat(kvm_posted_intr_wakeup_ipis); + kvm_posted_intr_wakeup_handler(); + exiting_irq(); set_irq_regs(old_regs); } #endif @@ -305,14 +347,22 @@ int check_irq_vectors_for_cpu_disable(void) if (!desc) continue; + /* + * Protect against concurrent action removal, + * affinity changes etc. + */ + raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); cpumask_copy(&affinity_new, data->affinity); cpumask_clear_cpu(this_cpu, &affinity_new); /* Do not count inactive or per-cpu irqs. */ - if (!irq_has_action(irq) || irqd_is_per_cpu(data)) + if (!irq_has_action(irq) || irqd_is_per_cpu(data)) { + raw_spin_unlock(&desc->lock); continue; + } + raw_spin_unlock(&desc->lock); /* * A single irq may be mapped to multiple * cpu's vector_irq[] (for example IOAPIC cluster @@ -343,6 +393,9 @@ int check_irq_vectors_for_cpu_disable(void) * vector. If the vector is marked in the used vectors * bitmap or an irq is assigned to it, we don't count * it as available. + * + * As this is an inaccurate snapshot anyway, we can do + * this w/o holding vector_lock. */ for (vector = FIRST_EXTERNAL_VECTOR; vector < first_system_vector; vector++) { @@ -444,6 +497,11 @@ void fixup_irqs(void) */ mdelay(1); + /* + * We can walk the vector array of this cpu without holding + * vector_lock because the cpu is already marked !online, so + * nothing else will touch it. + */ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irr; @@ -455,9 +513,9 @@ void fixup_irqs(void) irq = __this_cpu_read(vector_irq[vector]); desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); - raw_spin_lock(&desc->lock); if (chip->irq_retrigger) { chip->irq_retrigger(data); __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index f9fd86a7f..cd74f5978 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -21,12 +21,6 @@ #include <asm/apic.h> -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); - -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - #ifdef CONFIG_DEBUG_STACKOVERFLOW int sysctl_panic_on_stackoverflow __read_mostly; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 394e643d7..bc4604e50 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -20,12 +20,6 @@ #include <asm/idle.h> #include <asm/apic.h> -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); - -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - int sysctl_panic_on_stackoverflow; /* diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 15d741ddf..dc5fa6a1e 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -10,12 +10,6 @@ #include <asm/apic.h> #include <asm/trace/irq_vectors.h> -static inline void irq_work_entering_irq(void) -{ - irq_enter(); - ack_APIC_irq(); -} - static inline void __smp_irq_work_interrupt(void) { inc_irq_stat(apic_irq_work_irqs); @@ -24,14 +18,14 @@ static inline void __smp_irq_work_interrupt(void) __visible void smp_irq_work_interrupt(struct pt_regs *regs) { - irq_work_entering_irq(); + ipi_entering_ack_irq(); __smp_irq_work_interrupt(); exiting_irq(); } __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) { - irq_work_entering_irq(); + ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); __smp_irq_work_interrupt(); trace_irq_work_exit(IRQ_WORK_VECTOR); diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index cd10a6437..a3a5e158e 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -86,7 +86,7 @@ void __init init_IRQ(void) int i; /* - * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15. + * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If * these IRQ's are handled by more mordern controllers like IO-APIC, @@ -94,7 +94,7 @@ void __init init_IRQ(void) * irq's migrate etc. */ for (i = 0; i < nr_legacy_irqs(); i++) - per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i; + per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = i; x86_init.irqs.intr_init(); } @@ -135,6 +135,10 @@ static void __init apic_intr_init(void) alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); #endif +#ifdef CONFIG_X86_MCE_AMD + alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt); +#endif + #ifdef CONFIG_X86_LOCAL_APIC /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); @@ -144,6 +148,8 @@ static void __init apic_intr_init(void) #ifdef CONFIG_HAVE_KVM /* IPI for KVM to deliver posted interrupt */ alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); + /* IPI for KVM to deliver interrupt to wake up tasks */ + alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); #endif /* IPI vectors for APIC spurious and error interrupts */ diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index ca05f8648..ca83f7ac3 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -72,15 +72,16 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, unsigned long cmdline_len) { char *cmdline_ptr = ((char *)params) + cmdline_offset; - unsigned long cmdline_ptr_phys, len; + unsigned long cmdline_ptr_phys, len = 0; uint32_t cmdline_low_32, cmdline_ext_32; - memcpy(cmdline_ptr, cmdline, cmdline_len); if (image->type == KEXEC_TYPE_CRASH) { - len = sprintf(cmdline_ptr + cmdline_len - 1, - " elfcorehdr=0x%lx", image->arch.elf_load_addr); - cmdline_len += len; + len = sprintf(cmdline_ptr, + "elfcorehdr=0x%lx ", image->arch.elf_load_addr); } + memcpy(cmdline_ptr + len, cmdline, cmdline_len); + cmdline_len += len; + cmdline_ptr[cmdline_len - 1] = '\0'; pr_debug("Final command line is: %s\n", cmdline_ptr); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 943562006..47190bd39 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -331,7 +331,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) apic_write(APIC_EOI, APIC_EOI_ACK); } -void kvm_guest_cpu_init(void) +static void kvm_guest_cpu_init(void) { if (!kvm_para_available()) return; @@ -584,6 +584,39 @@ static void kvm_kick_cpu(int cpu) kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); } + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void kvm_wait(u8 *ptr, u8 val) +{ + unsigned long flags; + + if (in_nmi()) + return; + + local_irq_save(flags); + + if (READ_ONCE(*ptr) != val) + goto out; + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + local_irq_restore(flags); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + enum kvm_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -655,7 +688,7 @@ static inline void spin_time_accum_blocked(u64 start) static struct dentry *d_spin_debug; static struct dentry *d_kvm_debug; -struct dentry *kvm_init_debugfs(void) +static struct dentry *kvm_init_debugfs(void) { d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) @@ -817,6 +850,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) } } +#endif /* !CONFIG_QUEUED_SPINLOCKS */ + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -828,8 +863,16 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = kvm_wait; + pv_lock_ops.kick = kvm_kick_cpu; +#else /* !CONFIG_QUEUED_SPINLOCKS */ pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); pv_lock_ops.unlock_kick = kvm_unlock_kick; +#endif } static __init int kvm_spinlock_init_jump(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 42caaef89..49487b488 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,6 +24,7 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/memblock.h> +#include <linux/sched.h> #include <asm/x86_init.h> #include <asm/reboot.h> @@ -217,8 +218,10 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + struct pvclock_vcpu_time_info *vcpu_time; unsigned long mem; - int size; + int size, cpu; + u8 flags; size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); @@ -264,7 +267,14 @@ void __init kvmclock_init(void) pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) - pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + pvclock_set_flags(~0); + + cpu = get_cpu(); + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + if (flags & PVCLOCK_COUNTS_FROM_ZERO) + set_sched_clock_stable(); + put_cpu(); } int __init kvm_setup_vsyscall_timeinfo(void) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index c37886d75..2bcc0525f 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -12,6 +12,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> @@ -20,82 +21,82 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> -#ifdef CONFIG_SMP +/* context.lock is held for us, so we don't need any locking. */ static void flush_ldt(void *current_mm) { - if (current->active_mm == current_mm) - load_LDT(¤t->active_mm->context); + mm_context_t *pc; + + if (current->active_mm != current_mm) + return; + + pc = ¤t->active_mm->context; + set_ldt(pc->ldt->entries, pc->ldt->size); } -#endif -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ +static struct ldt_struct *alloc_ldt_struct(int size) { - void *oldldt, *newldt; - int oldsize; - - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) & - (~(PAGE_SIZE / LDT_ENTRY_SIZE - 1)); - if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount * LDT_ENTRY_SIZE); + struct ldt_struct *new_ldt; + int alloc_size; + + if (size > LDT_ENTRIES) + return NULL; + + new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); + if (!new_ldt) + return NULL; + + BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); + alloc_size = size * LDT_ENTRY_SIZE; + + /* + * Xen is very picky: it requires a page-aligned LDT that has no + * trailing nonzero bytes in any page that contains LDT descriptors. + * Keep it simple: zero the whole allocation and never allocate less + * than PAGE_SIZE. + */ + if (alloc_size > PAGE_SIZE) + new_ldt->entries = vzalloc(alloc_size); else - newldt = (void *)__get_free_page(GFP_KERNEL); - - if (!newldt) - return -ENOMEM; + new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (oldsize) - memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt + oldsize * LDT_ENTRY_SIZE, 0, - (mincount - oldsize) * LDT_ENTRY_SIZE); + if (!new_ldt->entries) { + kfree(new_ldt); + return NULL; + } - paravirt_alloc_ldt(newldt, mincount); + new_ldt->size = size; + return new_ldt; +} -#ifdef CONFIG_X86_64 - /* CHECKME: Do we really need this ? */ - wmb(); -#endif - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - preempt_disable(); - load_LDT(pc); - if (!cpumask_equal(mm_cpumask(current->mm), - cpumask_of(smp_processor_id()))) - smp_call_function(flush_ldt, current->mm, 1); - preempt_enable(); -#else - load_LDT(pc); -#endif - } - if (oldsize) { - paravirt_free_ldt(oldldt, oldsize); - if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - put_page(virt_to_page(oldldt)); - } - return 0; +/* After calling this, the LDT is immutable. */ +static void finalize_ldt_struct(struct ldt_struct *ldt) +{ + paravirt_alloc_ldt(ldt->entries, ldt->size); } -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +/* context.lock is held */ +static void install_ldt(struct mm_struct *current_mm, + struct ldt_struct *ldt) { - int err = alloc_ldt(new, old->size, 0); - int i; + /* Synchronizes with lockless_dereference in load_mm_ldt. */ + smp_store_release(¤t_mm->context.ldt, ldt); + + /* Activate the LDT for all CPUs using current_mm. */ + on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); +} - if (err < 0) - return err; +static void free_ldt_struct(struct ldt_struct *ldt) +{ + if (likely(!ldt)) + return; - for (i = 0; i < old->size; i++) - write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE); - return 0; + paravirt_free_ldt(ldt->entries, ldt->size); + if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(ldt->entries); + else + kfree(ldt->entries); + kfree(ldt); } /* @@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old) */ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + struct ldt_struct *new_ldt; struct mm_struct *old_mm; int retval = 0; mutex_init(&mm->context.lock); - mm->context.size = 0; old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - mutex_lock(&old_mm->context.lock); - retval = copy_ldt(&mm->context, &old_mm->context); - mutex_unlock(&old_mm->context.lock); + if (!old_mm) { + mm->context.ldt = NULL; + return 0; } + + mutex_lock(&old_mm->context.lock); + if (!old_mm->context.ldt) { + mm->context.ldt = NULL; + goto out_unlock; + } + + new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + if (!new_ldt) { + retval = -ENOMEM; + goto out_unlock; + } + + memcpy(new_ldt->entries, old_mm->context.ldt->entries, + new_ldt->size * LDT_ENTRY_SIZE); + finalize_ldt_struct(new_ldt); + + mm->context.ldt = new_ldt; + +out_unlock: + mutex_unlock(&old_mm->context.lock); return retval; } @@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ void destroy_context(struct mm_struct *mm) { - if (mm->context.size) { -#ifdef CONFIG_X86_32 - /* CHECKME: Can this ever happen ? */ - if (mm == current->active_mm) - clear_LDT(); -#endif - paravirt_free_ldt(mm->context.ldt, mm->context.size); - if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - put_page(virt_to_page(mm->context.ldt)); - mm->context.size = 0; - } + free_ldt_struct(mm->context.ldt); + mm->context.ldt = NULL; } static int read_ldt(void __user *ptr, unsigned long bytecount) { - int err; + int retval; unsigned long size; struct mm_struct *mm = current->mm; - if (!mm->context.size) - return 0; + mutex_lock(&mm->context.lock); + + if (!mm->context.ldt) { + retval = 0; + goto out_unlock; + } + if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - mutex_lock(&mm->context.lock); - size = mm->context.size * LDT_ENTRY_SIZE; + size = mm->context.ldt->size * LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - mutex_unlock(&mm->context.lock); - if (err < 0) - goto error_return; + if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + retval = -EFAULT; + goto out_unlock; + } + if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr + size, bytecount - size) != 0) { - err = -EFAULT; - goto error_return; + /* Zero-fill the rest and pretend we read bytecount bytes. */ + if (clear_user(ptr + size, bytecount - size)) { + retval = -EFAULT; + goto out_unlock; } } - return bytecount; -error_return: - return err; + retval = bytecount; + +out_unlock: + mutex_unlock(&mm->context.lock); + return retval; } static int read_default_ldt(void __user *ptr, unsigned long bytecount) @@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) struct desc_struct ldt; int error; struct user_desc ldt_info; + int oldsize, newsize; + struct ldt_struct *new_ldt, *old_ldt; error = -EINVAL; if (bytecount != sizeof(ldt_info)) @@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) goto out; } - mutex_lock(&mm->context.lock); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(¤t->mm->context, - ldt_info.entry_number + 1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - memset(&ldt, 0, sizeof(ldt)); - goto install; + if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) || + LDT_empty(&ldt_info)) { + /* The user wants to clear the entry. */ + memset(&ldt, 0, sizeof(ldt)); + } else { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out; } + + fill_ldt(&ldt, &ldt_info); + if (oldmode) + ldt.avl = 0; } - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { - error = -EINVAL; + mutex_lock(&mm->context.lock); + + old_ldt = mm->context.ldt; + oldsize = old_ldt ? old_ldt->size : 0; + newsize = max((int)(ldt_info.entry_number + 1), oldsize); + + error = -ENOMEM; + new_ldt = alloc_ldt_struct(newsize); + if (!new_ldt) goto out_unlock; - } - fill_ldt(&ldt, &ldt_info); - if (oldmode) - ldt.avl = 0; + if (old_ldt) + memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; + finalize_ldt_struct(new_ldt); - /* Install the new entry ... */ -install: - write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt); + install_ldt(mm, new_ldt); + free_ldt_struct(old_ldt); error = 0; out_unlock: diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 415480d3e..819ab3f9c 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -17,6 +17,7 @@ #include <linux/ftrace.h> #include <linux/io.h> #include <linux/suspend.h> +#include <linux/vmalloc.h> #include <asm/init.h> #include <asm/pgtable.h> @@ -25,6 +26,7 @@ #include <asm/io_apic.h> #include <asm/debugreg.h> #include <asm/kexec-bzimage64.h> +#include <asm/setup.h> #ifdef CONFIG_KEXEC_FILE static struct kexec_file_ops *kexec_file_loaders[] = { @@ -334,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", - (unsigned long)&_text - __START_KERNEL); + kaslr_offset()); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 2d2a237f2..30ca7607c 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -19,8 +19,8 @@ #include <linux/module.h> #include <linux/smp.h> #include <linux/pci.h> -#include <linux/irqdomain.h> +#include <asm/irqdomain.h> #include <asm/mtrr.h> #include <asm/mpspec.h> #include <asm/pgalloc.h> @@ -113,11 +113,6 @@ static void __init MP_bus_info(struct mpc_bus *m) pr_warn("Unknown bustype %s - ignoring\n", str); } -static struct irq_domain_ops mp_ioapic_irqdomain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, -}; - static void __init MP_ioapic_info(struct mpc_ioapic *m) { struct ioapic_domain_cfg cfg = { diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index bbb6c7316..33ee3e0ef 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -8,11 +8,33 @@ #include <asm/paravirt.h> +#ifdef CONFIG_QUEUED_SPINLOCKS +__visible void __native_queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} + +PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock); + +bool pv_is_native_spin_unlock(void) +{ + return pv_lock_ops.queued_spin_unlock.func == + __raw_callee_save___native_queued_spin_unlock; +} +#endif + struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP +#ifdef CONFIG_QUEUED_SPINLOCKS + .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, + .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), + .wait = paravirt_nop, + .kick = paravirt_nop, +#else /* !CONFIG_QUEUED_SPINLOCKS */ .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), .unlock_kick = paravirt_nop, -#endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ +#endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c614dd492..58bcfb67c 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -154,7 +154,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || +#ifdef CONFIG_X86_32 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || +#endif type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ @@ -371,7 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +#if defined(CONFIG_X86_32) .irq_enable_sysexit = native_irq_enable_sysexit, #endif #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index d9f32e6d6..e1b013696 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -12,6 +12,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { /* arg in %eax, return in %eax */ @@ -24,6 +28,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) return 0; } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -47,14 +53,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_cpu_ops, read_tsc); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index a1da6737b..8aa05583b 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); DEF_NATIVE(, mov64, "mov %rdi, %rax"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { return paravirt_patch_insns(insnbuf, len, @@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) start__mov64, end__mov64); } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -49,7 +55,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); @@ -59,14 +64,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index a25e202bb..353972c19 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -140,6 +140,51 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } +void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + void *memory; + + gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + + if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) + return memory; + + if (!dev) + dev = &x86_dma_fallback_dev; + + if (!is_device_dma_capable(dev)) + return NULL; + + if (!ops->alloc) + return NULL; + + memory = ops->alloc(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp), attrs); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; +} +EXPORT_SYMBOL(dma_alloc_attrs); + +void dma_free_attrs(struct device *dev, size_t size, + void *vaddr, dma_addr_t bus, + struct dma_attrs *attrs) +{ + struct dma_map_ops *ops = get_dma_ops(dev); + + WARN_ON(irqs_disabled()); /* for portability */ + + if (dma_release_from_coherent(dev, get_order(size), vaddr)) + return; + + debug_dma_free_coherent(dev, size, vaddr, bus); + if (ops->free) + ops->free(dev, size, vaddr, bus, attrs); +} +EXPORT_SYMBOL(dma_free_attrs); + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 77dd0ad58..adf0392d5 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, { void *vaddr; + /* + * Don't print a warning when the first allocation attempt fails. + * swiotlb_alloc_coherent() will print a warning when the DMA + * memory allocation ultimately failed. + */ + flags |= __GFP_NOWARN; + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags, attrs); if (vaddr) diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 3420c874d..64f90f53b 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -1,53 +1,82 @@ /* * Copyright (c) 2015, Christoph Hellwig. + * Copyright (c) 2015, Intel Corporation. */ -#include <linux/memblock.h> #include <linux/platform_device.h> -#include <linux/slab.h> +#include <linux/libnvdimm.h> +#include <linux/module.h> #include <asm/e820.h> -#include <asm/page_types.h> -#include <asm/setup.h> -static __init void register_pmem_device(struct resource *res) +static void e820_pmem_release(struct device *dev) { - struct platform_device *pdev; - int error; + struct nvdimm_bus *nvdimm_bus = dev->platform_data; - pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); - if (!pdev) - return; + if (nvdimm_bus) + nvdimm_bus_unregister(nvdimm_bus); +} - error = platform_device_add_resources(pdev, res, 1); - if (error) - goto out_put_pdev; +static struct platform_device e820_pmem = { + .name = "e820_pmem", + .id = -1, + .dev = { + .release = e820_pmem_release, + }, +}; - error = platform_device_add(pdev); - if (error) - goto out_put_pdev; - return; +static const struct attribute_group *e820_pmem_attribute_groups[] = { + &nvdimm_bus_attribute_group, + NULL, +}; -out_put_pdev: - dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); - platform_device_put(pdev); -} +static const struct attribute_group *e820_pmem_region_attribute_groups[] = { + &nd_region_attribute_group, + &nd_device_attribute_group, + NULL, +}; -static __init int register_pmem_devices(void) +static __init int register_e820_pmem(void) { - int i; + static struct nvdimm_bus_descriptor nd_desc; + struct device *dev = &e820_pmem.dev; + struct nvdimm_bus *nvdimm_bus; + int rc, i; + + rc = platform_device_register(&e820_pmem); + if (rc) + return rc; + + nd_desc.attr_groups = e820_pmem_attribute_groups; + nd_desc.provider_name = "e820"; + nvdimm_bus = nvdimm_bus_register(dev, &nd_desc); + if (!nvdimm_bus) + goto err; + dev->platform_data = nvdimm_bus; for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; + struct resource res = { + .flags = IORESOURCE_MEM, + .start = ei->addr, + .end = ei->addr + ei->size - 1, + }; + struct nd_region_desc ndr_desc; + + if (ei->type != E820_PRAM) + continue; - if (ei->type == E820_PRAM) { - struct resource res = { - .flags = IORESOURCE_MEM, - .start = ei->addr, - .end = ei->addr + ei->size - 1, - }; - register_pmem_device(&res); - } + memset(&ndr_desc, 0, sizeof(ndr_desc)); + ndr_desc.res = &res; + ndr_desc.attr_groups = e820_pmem_region_attribute_groups; + ndr_desc.numa_node = NUMA_NO_NODE; + if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc)) + goto err; } return 0; + + err: + dev_err(dev, "failed to register legacy persistent memory ranges\n"); + platform_device_unregister(&e820_pmem); + return -ENXIO; } -device_initcall(register_pmem_devices); +device_initcall(register_e820_pmem); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6e338e3b1..c27cad726 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -25,8 +25,7 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/mwait.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> @@ -76,47 +75,15 @@ void idle_notifier_unregister(struct notifier_block *n) EXPORT_SYMBOL_GPL(idle_notifier_unregister); #endif -struct kmem_cache *task_xstate_cachep; -EXPORT_SYMBOL_GPL(task_xstate_cachep); - /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - *dst = *src; - - dst->thread.fpu_counter = 0; - dst->thread.fpu.has_fpu = 0; - dst->thread.fpu.state = NULL; - task_disable_lazy_fpu_restore(dst); - if (tsk_used_math(src)) { - int err = fpu_alloc(&dst->thread.fpu); - if (err) - return err; - fpu_copy(dst, src); - } - return 0; -} - -void free_thread_xstate(struct task_struct *tsk) -{ - fpu_free(&tsk->thread.fpu); -} + memcpy(dst, src, arch_task_struct_size); -void arch_release_task_struct(struct task_struct *tsk) -{ - free_thread_xstate(tsk); -} - -void arch_task_cache_init(void) -{ - task_xstate_cachep = - kmem_cache_create("task_xstate", xstate_size, - __alignof__(union thread_xstate), - SLAB_PANIC | SLAB_NOTRACK, NULL); - setup_xstate_comp(); + return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } /* @@ -127,6 +94,7 @@ void exit_thread(void) struct task_struct *me = current; struct thread_struct *t = &me->thread; unsigned long *bp = t->io_bitmap_ptr; + struct fpu *fpu = &t->fpu; if (bp) { struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); @@ -142,7 +110,7 @@ void exit_thread(void) kfree(bp); } - drop_fpu(me); + fpu__drop(fpu); } void flush_thread(void) @@ -152,19 +120,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - if (!use_eager_fpu()) { - /* FPU state will be reallocated lazily at the first use. */ - drop_fpu(tsk); - free_thread_xstate(tsk); - } else { - if (!tsk_used_math(tsk)) { - /* kthread execs. TODO: cleanup this horror. */ - if (WARN_ON(init_fpu(tsk))) - force_sig(SIGKILL, tsk); - user_fpu_begin(); - } - restore_init_xstate(); - } + fpu__clear(&tsk->thread.fpu); } static void hard_disable_TSC(void) @@ -445,14 +401,14 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) } /* - * MONITOR/MWAIT with no hints, used for default default C1 state. - * This invokes MWAIT with interrutps enabled and no flags, - * which is backwards compatible with the original MWAIT implementation. + * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT + * with interrupts enabled and no flags, which is backwards compatible with the + * original MWAIT implementation. */ - static void mwait_idle(void) { if (!current_set_polling_and_test()) { + trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { smp_mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -464,6 +420,7 @@ static void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 8ed2106b0..f73c962fe 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -39,8 +39,7 @@ #include <asm/pgtable.h> #include <asm/ldt.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/desc.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> @@ -129,8 +128,8 @@ void release_thread(struct task_struct *dead_task) release_vm86_irqs(dead_task); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; @@ -185,7 +184,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); if (err && p->thread.io_bitmap_ptr) { kfree(p->thread.io_bitmap_ptr); @@ -242,14 +241,16 @@ __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, - *next = &next_p->thread; + *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - fpu_switch_t fpu; + fpu_switch_t fpu_switch; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -296,19 +297,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up + * done before fpu__restore(), so the TS bit is up * to date. */ arch_end_context_switch(next_p); /* - * Reload esp0, kernel_stack, and current_top_of_stack. This changes + * Reload esp0 and cpu_current_top_of_stack. This changes * current_thread_info(). */ load_sp0(tss, next); - this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + - THREAD_SIZE); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); @@ -319,7 +317,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) lazy_load_gs(next->gs); - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); this_cpu_write(current_task, next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ddfdbf74f..f6b916387 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -38,8 +38,7 @@ #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -122,11 +121,11 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { - if (dead_task->mm->context.size) { + if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt, - dead_task->mm->context.size); + dead_task->mm->context.ldt->size); BUG(); } } @@ -151,8 +150,8 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) return get_desc_base(&t->thread.tls_array[tls]); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { int err; struct pt_regs *childregs; @@ -208,10 +207,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, #ifdef CONFIG_IA32_EMULATION if (is_ia32_task()) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); + err = do_arch_prctl(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -274,12 +273,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); unsigned fsindex, gsindex; - fpu_switch_t fpu; + fpu_switch_t fpu_switch; - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -299,7 +300,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. This * must be done after loading TLS entries in the GDT but before * loading segments that might reference them, and and it must - * be done before math_state_restore, so the TS bit is up to + * be done before fpu__restore(), so the TS bit is up to * date. */ arch_end_context_switch(next_p); @@ -391,7 +392,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); /* * Switch the PDA and FPU contexts. @@ -409,9 +410,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* Reload esp0 and ss1. This changes current_thread_info(). */ load_sp0(tss, next); - this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + THREAD_SIZE); - /* * Now maybe reload the debug registers and handle I/O bitmaps */ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index a7bc79480..9be72bc36 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -11,7 +11,6 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/ptrace.h> -#include <linux/regset.h> #include <linux/tracehook.h> #include <linux/user.h> #include <linux/elf.h> @@ -28,8 +27,9 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> @@ -1297,7 +1297,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, @@ -1338,13 +1338,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = fpregs_active, .get = fpregs_get, .set = fpregs_set + .active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d74ac3329..80f874bf9 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -461,19 +461,18 @@ static void __init e820_reserve_setup_data(void) { struct setup_data *data; u64 pa_data; - int found = 0; pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return; + while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); e820_update_range(pa_data, sizeof(*data)+data->len, E820_RAM, E820_RESERVED_KERN); - found = 1; pa_data = data->next; early_memunmap(data, sizeof(*data)); } - if (!found) - return; sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); memcpy(&e820_saved, &e820, sizeof(struct e820map)); @@ -531,12 +530,14 @@ static void __init reserve_crashkernel_low(void) if (ret != 0) { /* * two parts from lib/swiotlb.c: - * swiotlb size: user specified with swiotlb= or default. - * swiotlb overflow buffer: now is hardcoded to 32k. - * We round it to 8M for other buffers that - * may need to stay low too. + * -swiotlb size: user-specified with swiotlb= or default. + * + * -swiotlb overflow buffer: now hardcoded to 32k. We round it + * to 8M for other buffers that may need to stay low too. Also + * make sure we allocate enough extra low memory so that we + * don't run out of DMA buffers for 32-bit devices. */ - low_size = swiotlb_size_or_default() + (8UL<<20); + low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20); auto_set = true; } else { /* passed with crashkernel=0,low ? */ @@ -834,7 +835,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { if (kaslr_enabled()) { pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n", - (unsigned long)&_text - __START_KERNEL, + kaslr_offset(), __START_KERNEL, __START_KERNEL_map, MODULES_VADDR-1); @@ -1103,6 +1104,9 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); + if (efi_enabled(EFI_BOOT)) + efi_find_mirror(); + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1222,8 +1226,7 @@ void __init setup_arch(char **cmdline_p) init_cpu_to_node(); init_apic_mappings(); - if (x86_io_apic_ops.init) - x86_io_apic_ops.init(); + io_apic_init_mappings(); kvm_guest_init(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 1ea14fd53..71820c42b 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -26,8 +26,8 @@ #include <asm/processor.h> #include <asm/ucontext.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> @@ -93,8 +93,15 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) COPY(r15); #endif /* CONFIG_X86_64 */ +#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); +#else /* !CONFIG_X86_32 */ + /* Kernel saves and restores only the CS segment register on signals, + * which is the bare minimum needed to allow mixed 32/64-bit code. + * App's signal handler can save/restore other segments if needed. */ + COPY_SEG_CPL3(cs); +#endif /* CONFIG_X86_32 */ get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); @@ -103,7 +110,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) get_user_ex(buf, &sc->fpstate); } get_user_catch(err); - err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32)); force_iret(); @@ -154,9 +161,8 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, #else /* !CONFIG_X86_32 */ put_user_ex(regs->flags, &sc->flags); put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->__pad2); - put_user_ex(0, &sc->__pad1); - put_user_ex(regs->ss, &sc->ss); + put_user_ex(0, &sc->gs); + put_user_ex(0, &sc->fs); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -199,6 +205,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long sp = regs->sp; unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); + struct fpu *fpu = ¤t->thread.fpu; /* redzone */ if (config_enabled(CONFIG_X86_64)) @@ -218,9 +225,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, } } - if (used_math()) { - sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), - &buf_fx, &math_size); + if (fpu->fpstate_active) { + sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -234,8 +241,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (used_math() && - save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) + if (fpu->fpstate_active && + copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -450,19 +457,9 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. - */ + /* Set up the CS register to run signal handlers in 64-bit mode, + even if the handler happens to be interrupting 32-bit code. */ regs->cs = __USER_CS; - regs->ss = __USER_DS; return 0; } @@ -593,6 +590,22 @@ badframe: return 0; } +static inline int is_ia32_compat_frame(void) +{ + return config_enabled(CONFIG_IA32_EMULATION) && + test_thread_flag(TIF_IA32); +} + +static inline int is_ia32_frame(void) +{ + return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); +} + +static inline int is_x32_frame(void) +{ + return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); +} + static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { @@ -617,6 +630,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; + struct fpu *fpu = ¤t->thread.fpu; /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { @@ -665,8 +679,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (used_math()) - fpu_reset_state(current); + if (fpu->fpstate_active) + fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index be8e1bde0..15aaa69bb 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -170,8 +170,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) asmlinkage __visible void smp_reboot_interrupt(void) { - ack_APIC_irq(); - irq_enter(); + ipi_entering_ack_irq(); stop_this_cpu(NULL); irq_exit(); } @@ -265,12 +264,6 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs) */ } -static inline void smp_entering_irq(void) -{ - ack_APIC_irq(); - irq_enter(); -} - __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) { /* @@ -279,7 +272,7 @@ __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) * scheduler_ipi(). This is OK, since those functions are allowed * to nest. */ - smp_entering_irq(); + ipi_entering_ack_irq(); trace_reschedule_entry(RESCHEDULE_VECTOR); __smp_reschedule_interrupt(); trace_reschedule_exit(RESCHEDULE_VECTOR); @@ -297,14 +290,14 @@ static inline void __smp_call_function_interrupt(void) __visible void smp_call_function_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); __smp_call_function_interrupt(); exiting_irq(); } __visible void smp_trace_call_function_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); __smp_call_function_interrupt(); trace_call_function_exit(CALL_FUNCTION_VECTOR); @@ -319,14 +312,14 @@ static inline void __smp_call_function_single_interrupt(void) __visible void smp_call_function_single_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); __smp_call_function_single_interrupt(); exiting_irq(); } __visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); __smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 50e547eac..b1f3ed9c7 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -68,8 +68,7 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -172,11 +171,6 @@ static void smp_callin(void) apic_ap_setup(); /* - * Need to setup vector mappings before we enable interrupts. - */ - setup_vector_irq(smp_processor_id()); - - /* * Save our processor parameters. Note: this information * is needed for clock calibration. */ @@ -240,18 +234,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* - * Enable the espfix hack for this CPU - */ -#ifdef CONFIG_X86_ESPFIX64 - init_espfix_ap(); -#endif - - /* - * We need to hold vector_lock so there the set of online cpus - * does not change while we are assigning vectors to cpus. Holding - * this lock ensures we don't half assign or remove an irq from a cpu. + * Lock vector_lock and initialize the vectors on this cpu + * before setting the cpu online. We must set it online with + * vector_lock held to prevent a concurrent setup/teardown + * from seeing a half valid vector space. */ lock_vector_lock(); + setup_vector_irq(smp_processor_id()); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); cpu_set_state_online(smp_processor_id()); @@ -314,10 +303,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } -#define link_mask(_m, c1, c2) \ +#define link_mask(mfunc, c1, c2) \ do { \ - cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ - cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ + cpumask_set_cpu((c1), mfunc(c2)); \ + cpumask_set_cpu((c2), mfunc(c1)); \ } while (0) static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -398,9 +387,9 @@ void set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_setup_mask); if (!has_mp) { - cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); c->booted_cores = 1; return; } @@ -409,32 +398,34 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if ((i == cpu) || (has_smt && match_smt(c, o))) - link_mask(sibling, cpu, i); + link_mask(topology_sibling_cpumask, cpu, i); if ((i == cpu) || (has_mp && match_llc(c, o))) - link_mask(llc_shared, cpu, i); + link_mask(cpu_llc_shared_mask, cpu, i); } /* * This needs a separate iteration over the cpus because we rely on all - * cpu_sibling_mask links to be set-up. + * topology_sibling_cpumask links to be set-up. */ for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); if ((i == cpu) || (has_mp && match_die(c, o))) { - link_mask(core, cpu, i); + link_mask(topology_core_cpumask, cpu, i); /* * Does this new cpu bringup a new core? */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) { + if (cpumask_weight( + topology_sibling_cpumask(cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (cpumask_first(cpu_sibling_mask(i)) == i) + if (cpumask_first( + topology_sibling_cpumask(i)) == i) c->booted_cores++; /* * increment the core count for all @@ -514,6 +505,40 @@ void __inquire_remote_apic(int apicid) } /* + * The Multiprocessor Specification 1.4 (1997) example code suggests + * that there should be a 10ms delay between the BSP asserting INIT + * and de-asserting INIT, when starting a remote processor. + * 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. + */ +#define UDELAY_10MS_DEFAULT 10000 + +static unsigned int init_udelay = UDELAY_10MS_DEFAULT; + +static int __init cpu_init_udelay(char *str) +{ + get_option(&str, &init_udelay); + + return 0; +} +early_param("cpu_init_udelay", cpu_init_udelay); + +static void __init smp_quirk_init_udelay(void) +{ + /* if cmdline changed it from default, leave it alone */ + if (init_udelay != UDELAY_10MS_DEFAULT) + 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_AMD) && (boot_cpu_data.x86 >= 0xF))) + init_udelay = 0; +} + +/* * 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. @@ -555,7 +580,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) { - unsigned long send_status, accept_status = 0; + unsigned long send_status = 0, accept_status = 0; int maxlvt, num_starts, j; maxlvt = lapic_get_maxlvt(); @@ -583,7 +608,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); - mdelay(10); + udelay(init_udelay); pr_debug("Deasserting INIT\n"); @@ -651,6 +676,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) * Give the other CPU some time to accept the IPI. */ udelay(200); + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); accept_status = (apic_read(APIC_ESR) & 0xEF); @@ -792,8 +818,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); #endif - per_cpu(kernel_stack, cpu) = - (unsigned long)task_stack_page(idle) + THREAD_SIZE; } /* @@ -820,6 +844,13 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) initial_code = (unsigned long)start_secondary; stack_start = idle->thread.sp; + /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(cpu); +#endif + /* So we see what's up */ announce_cpu(cpu, apicid); @@ -961,8 +992,17 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); + /* + * We have to walk the irq descriptors to setup the vector + * space for the cpu which comes online. Prevent irq + * alloc/free across the bringup. + */ + irq_lock_sparse(); + err = do_boot_cpu(apicid, cpu, tidle); + if (err) { + irq_unlock_sparse(); pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } @@ -980,6 +1020,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } + irq_unlock_sparse(); + return 0; } @@ -1009,8 +1051,8 @@ static __init void disable_smp(void) 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, cpu_sibling_mask(0)); - cpumask_set_cpu(0, cpu_core_mask(0)); + cpumask_set_cpu(0, topology_sibling_cpumask(0)); + cpumask_set_cpu(0, topology_core_cpumask(0)); } enum { @@ -1176,6 +1218,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) uv_system_init(); set_mtrr_aps_delayed_init(); + + smp_quirk_init_udelay(); } void arch_enable_nonboot_cpus_begin(void) @@ -1293,22 +1337,22 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu(sibling, cpu_core_mask(cpu)) { - cpumask_clear_cpu(cpu, cpu_core_mask(sibling)); + for_each_cpu(sibling, topology_core_cpumask(cpu)) { + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); /*/ * last thread sibling in this cpu core going down */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) + if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1) cpu_data(sibling).booted_cores--; } - for_each_cpu(sibling, cpu_sibling_mask(cpu)) - cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); - cpumask_clear(cpu_sibling_mask(cpu)); - cpumask_clear(cpu_core_mask(cpu)); + cpumask_clear(topology_sibling_cpumask(cpu)); + cpumask_clear(topology_core_cpumask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 9b4d51d0c..0ccb53a9f 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <linux/ptrace.h> #include <asm/desc.h> +#include <asm/mmu_context.h> unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) { @@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re struct desc_struct *desc; unsigned long base; - seg &= ~7UL; + seg >>= 3; mutex_lock(&child->mm->context.lock); - if (unlikely((seg >> 3) >= child->mm->context.size)) + if (unlikely(!child->mm->context.ldt || + seg >= child->mm->context.ldt->size)) addr = -1L; /* bogus selector, access would fault */ else { - desc = child->mm->context.ldt + seg; + desc = &child->mm->context.ldt->entries[seg]; base = get_desc_base(desc); /* 16-bit code segment? */ diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c deleted file mode 100644 index 3777189c4..000000000 --- a/arch/x86/kernel/syscall_32.c +++ /dev/null @@ -1,33 +0,0 @@ -/* System call table for i386. */ - -#include <linux/linkage.h> -#include <linux/sys.h> -#include <linux/cache.h> -#include <asm/asm-offsets.h> - -#ifdef CONFIG_IA32_EMULATION -#define SYM(sym, compat) compat -#else -#define SYM(sym, compat) sym -#define ia32_sys_call_table sys_call_table -#define __NR_ia32_syscall_max __NR_syscall_max -#endif - -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ; -#include <asm/syscalls_32.h> -#undef __SYSCALL_I386 - -#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat), - -typedef asmlinkage void (*sys_call_ptr_t)(void); - -extern asmlinkage void sys_ni_syscall(void); - -__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall, -#include <asm/syscalls_32.h> -}; diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c deleted file mode 100644 index 4ac730b37..000000000 --- a/arch/x86/kernel/syscall_64.c +++ /dev/null @@ -1,32 +0,0 @@ -/* System call table for x86-64. */ - -#include <linux/linkage.h> -#include <linux/sys.h> -#include <linux/cache.h> -#include <asm/asm-offsets.h> -#include <asm/syscall.h> - -#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) - -#ifdef CONFIG_X86_X32_ABI -# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat) -#else -# define __SYSCALL_X32(nr, sym, compat) /* nothing */ -#endif - -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; -#include <asm/syscalls_64.h> -#undef __SYSCALL_64 - -#define __SYSCALL_64(nr, sym, compat) [nr] = sym, - -extern void sys_ni_syscall(void); - -asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, -#include <asm/syscalls_64.h> -}; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 324ab5247..f5791927a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -54,12 +54,13 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> #include <asm/alternative.h> +#include <asm/fpu/xstate.h> +#include <asm/trace/mpx.h> #include <asm/mpx.h> #ifdef CONFIG_X86_64 @@ -72,8 +73,7 @@ gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> - -asmlinkage int system_call(void); +#include <asm/proto.h> #endif /* Must be page-aligned because the real IDT is used in a fixmap. */ @@ -371,10 +371,8 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - struct xsave_struct *xsave_buf; enum ctx_state prev_state; - struct bndcsr *bndcsr; + const struct bndcsr *bndcsr; siginfo_t *info; prev_state = exception_enter(); @@ -393,15 +391,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) /* * We need to look at BNDSTATUS to resolve this exception. - * It is not directly accessible, though, so we need to - * do an xsave and then pull it out of the xsave buffer. + * A NULL here might mean that it is in its 'init state', + * which is all zeros which indicates MPX was not + * responsible for the exception. */ - fpu_save_init(&tsk->thread.fpu); - xsave_buf = &(tsk->thread.fpu.state->xsave); - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XSTATE_BNDCSR); if (!bndcsr) goto exit_trap; + trace_bounds_exception_mpx(bndcsr); /* * The error code field of the BNDSTATUS register communicates status * information of a bound range exception #BR or operation involving @@ -409,11 +407,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) */ switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) { case 2: /* Bound directory has invalid entry. */ - if (mpx_handle_bd_fault(xsave_buf)) + if (mpx_handle_bd_fault()) goto exit_trap; break; /* Success, it was handled */ case 1: /* Bound violation. */ - info = mpx_generate_siginfo(regs, xsave_buf); + info = mpx_generate_siginfo(regs); if (IS_ERR(info)) { /* * We failed to decode the MPX instruction. Act as if @@ -709,8 +707,8 @@ NOKPROBE_SYMBOL(do_debug); static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; + struct fpu *fpu = &task->thread.fpu; siginfo_t info; - unsigned short err; char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; @@ -718,8 +716,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) return; conditional_sti(regs); - if (!user_mode(regs)) - { + if (!user_mode(regs)) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; task->thread.trap_nr = trapnr; @@ -731,62 +728,20 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) /* * Save the info for the exception handler and clear the error. */ - unlazy_fpu(task); - task->thread.trap_nr = trapnr; + fpu__save(fpu); + + task->thread.trap_nr = trapnr; task->thread.error_code = error_code; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - if (trapnr == X86_TRAP_MF) { - unsigned short cwd, swd; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - err = swd & ~cwd; - } else { - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - unsigned short mxcsr = get_fpu_mxcsr(task); - err = ~(mxcsr >> 7) & mxcsr; - } + info.si_code = fpu__exception_code(fpu, trapnr); - if (err & 0x001) { /* Invalid op */ - /* - * swd & 0x240 == 0x040: Stack Underflow - * swd & 0x240 == 0x240: Stack Overflow - * User must clear the SF bit (0x40) if set - */ - info.si_code = FPE_FLTINV; - } else if (err & 0x004) { /* Divide by Zero */ - info.si_code = FPE_FLTDIV; - } else if (err & 0x008) { /* Overflow */ - info.si_code = FPE_FLTOVF; - } else if (err & 0x012) { /* Denormal, Underflow */ - info.si_code = FPE_FLTUND; - } else if (err & 0x020) { /* Precision */ - info.si_code = FPE_FLTRES; - } else { - /* - * If we're using IRQ 13, or supposedly even some trap - * X86_TRAP_MF implementations, it's possible - * we get a spurious trap, which is not an error. - */ + /* Retry when we get spurious exceptions: */ + if (!info.si_code) return; - } + force_sig_info(SIGFPE, &info, task); } @@ -813,62 +768,8 @@ dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { conditional_sti(regs); -#if 0 - /* No need to warn about this any longer. */ - pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); -#endif -} - -asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void) -{ } -asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void) -{ -} - -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - * - * Must be called with kernel preemption disabled (eg with local - * local interrupts as in the case of do_device_not_available). - */ -void math_state_restore(void) -{ - struct task_struct *tsk = current; - - if (!tsk_used_math(tsk)) { - local_irq_enable(); - /* - * does a slab alloc which can sleep - */ - if (init_fpu(tsk)) { - /* - * ran out of memory! - */ - do_group_exit(SIGKILL); - return; - } - local_irq_disable(); - } - - /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */ - kernel_fpu_disable(); - __thread_fpu_begin(tsk); - if (unlikely(restore_fpu_checking(tsk))) { - fpu_reset_state(tsk); - force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); - } else { - tsk->thread.fpu_counter++; - } - kernel_fpu_enable(); -} -EXPORT_SYMBOL_GPL(math_state_restore); - dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { @@ -889,7 +790,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) return; } #endif - math_state_restore(); /* interrupts still off */ + fpu__restore(¤t->thread.fpu); /* interrupts still off */ #ifdef CONFIG_X86_32 conditional_sti(regs); #endif @@ -992,13 +893,13 @@ void __init trap_init(void) set_bit(i, used_vectors); #ifdef CONFIG_IA32_EMULATION - set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall); + set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat); set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif #ifdef CONFIG_X86_32 - set_system_trap_gate(SYSCALL_VECTOR, &system_call); - set_bit(SYSCALL_VECTOR, used_vectors); + set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); + set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index f95603842..7437b41f6 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -12,7 +12,6 @@ #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> -#include <linux/mm.h> #include <asm/hpet.h> #include <asm/timer.h> @@ -196,10 +195,6 @@ static void cyc2ns_init(int cpu) c2n->head = c2n->data; c2n->tail = c2n->data; - - // Don't let TuxOnIce make data RO - a secondary CPU will cause a triple fault - // if it loads microcode, which then does a printk, which may end up invoking cycles_2_ns - SetPageTOI_Untracked(virt_to_page(c2n)); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) @@ -603,10 +598,19 @@ static unsigned long quick_pit_calibrate(void) if (!pit_expect_msb(0xff-i, &delta, &d2)) break; + delta -= tsc; + + /* + * Extrapolate the error and fail fast if the error will + * never be below 500 ppm. + */ + if (i == 1 && + d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) + return 0; + /* * Iterate until the error is less than 500 ppm */ - delta -= tsc; if (d1+d2 >= delta >> 11) continue; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 26488487b..dd8d0791d 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -113,7 +113,7 @@ static void check_tsc_warp(unsigned int timeout) */ static inline unsigned int loop_timeout(int cpu) { - return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; + return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20; } /* diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 0b81ad67d..664762447 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -29,6 +29,7 @@ #include <linux/kdebug.h> #include <asm/processor.h> #include <asm/insn.h> +#include <asm/mmu_context.h> /* Post-execution fixups. */ @@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool } #ifdef CONFIG_X86_64 -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return !config_enabled(CONFIG_IA32_EMULATION) || - !(mm->context.ia32_compat == TIF_IA32); -} /* * If arch_uprobe->insn doesn't use rip-relative addressing, return * immediately. Otherwise, rewrite the instruction so that it accesses @@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) } } #else /* 32-bit: */ -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return false; -} /* * No RIP-relative addressing on 32-bit */ diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index ee22c1d93..b034b1b14 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -72,7 +72,7 @@ asmlinkage __visible void vsmp_irq_enable(void) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); -static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf, +static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { switch (type) { diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c deleted file mode 100644 index 2dcc6ff6f..000000000 --- a/arch/x86/kernel/vsyscall_64.c +++ /dev/null @@ -1,335 +0,0 @@ -/* - * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> - * - * Based on the original implementation which is: - * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE - * Copyright 2003 Andi Kleen, SuSE Labs. - * - * Parts of the original code have been moved to arch/x86/vdso/vma.c - * - * This file implements vsyscall emulation. vsyscalls are a legacy ABI: - * Userspace can request certain kernel services by calling fixed - * addresses. This concept is problematic: - * - * - It interferes with ASLR. - * - It's awkward to write code that lives in kernel addresses but is - * callable by userspace at fixed addresses. - * - The whole concept is impossible for 32-bit compat userspace. - * - UML cannot easily virtualize a vsyscall. - * - * As of mid-2014, I believe that there is no new userspace code that - * will use a vsyscall if the vDSO is present. I hope that there will - * soon be no new userspace code that will ever use a vsyscall. - * - * The code in this file emulates vsyscalls when notified of a page - * fault to a vsyscall address. - */ - -#include <linux/kernel.h> -#include <linux/timer.h> -#include <linux/syscalls.h> -#include <linux/ratelimit.h> - -#include <asm/vsyscall.h> -#include <asm/unistd.h> -#include <asm/fixmap.h> -#include <asm/traps.h> - -#define CREATE_TRACE_POINTS -#include "vsyscall_trace.h" - -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; - -static int __init vsyscall_setup(char *str) -{ - if (str) { - if (!strcmp("emulate", str)) - vsyscall_mode = EMULATE; - else if (!strcmp("native", str)) - vsyscall_mode = NATIVE; - else if (!strcmp("none", str)) - vsyscall_mode = NONE; - else - return -EINVAL; - - return 0; - } - - return -EINVAL; -} -early_param("vsyscall", vsyscall_setup); - -static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, - const char *message) -{ - if (!show_unhandled_signals) - return; - - printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); -} - -static int addr_to_vsyscall_nr(unsigned long addr) -{ - int nr; - - if ((addr & ~0xC00UL) != VSYSCALL_ADDR) - return -EINVAL; - - nr = (addr & 0xC00UL) >> 10; - if (nr >= 3) - return -EINVAL; - - return nr; -} - -static bool write_ok_or_segv(unsigned long ptr, size_t size) -{ - /* - * XXX: if access_ok, get_user, and put_user handled - * sig_on_uaccess_error, this could go away. - */ - - if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) { - siginfo_t info; - struct thread_struct *thread = ¤t->thread; - - thread->error_code = 6; /* user fault, no page, write */ - thread->cr2 = ptr; - thread->trap_nr = X86_TRAP_PF; - - memset(&info, 0, sizeof(info)); - info.si_signo = SIGSEGV; - info.si_errno = 0; - info.si_code = SEGV_MAPERR; - info.si_addr = (void __user *)ptr; - - force_sig_info(SIGSEGV, &info, current); - return false; - } else { - return true; - } -} - -bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) -{ - struct task_struct *tsk; - unsigned long caller; - int vsyscall_nr, syscall_nr, tmp; - int prev_sig_on_uaccess_error; - long ret; - - /* - * No point in checking CS -- the only way to get here is a user mode - * trap to a high address, which means that we're in 64-bit user code. - */ - - WARN_ON_ONCE(address != regs->ip); - - if (vsyscall_mode == NONE) { - warn_bad_vsyscall(KERN_INFO, regs, - "vsyscall attempted with vsyscall=none"); - return false; - } - - vsyscall_nr = addr_to_vsyscall_nr(address); - - trace_emulate_vsyscall(vsyscall_nr); - - if (vsyscall_nr < 0) { - warn_bad_vsyscall(KERN_WARNING, regs, - "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); - goto sigsegv; - } - - if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { - warn_bad_vsyscall(KERN_WARNING, regs, - "vsyscall with bad stack (exploit attempt?)"); - goto sigsegv; - } - - tsk = current; - - /* - * Check for access_ok violations and find the syscall nr. - * - * NULL is a valid user pointer (in the access_ok sense) on 32-bit and - * 64-bit, so we don't need to special-case it here. For all the - * vsyscalls, NULL means "don't write anything" not "write it at - * address 0". - */ - switch (vsyscall_nr) { - case 0: - if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) || - !write_ok_or_segv(regs->si, sizeof(struct timezone))) { - ret = -EFAULT; - goto check_fault; - } - - syscall_nr = __NR_gettimeofday; - break; - - case 1: - if (!write_ok_or_segv(regs->di, sizeof(time_t))) { - ret = -EFAULT; - goto check_fault; - } - - syscall_nr = __NR_time; - break; - - case 2: - if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || - !write_ok_or_segv(regs->si, sizeof(unsigned))) { - ret = -EFAULT; - goto check_fault; - } - - syscall_nr = __NR_getcpu; - break; - } - - /* - * Handle seccomp. regs->ip must be the original value. - * See seccomp_send_sigsys and Documentation/prctl/seccomp_filter.txt. - * - * We could optimize the seccomp disabled case, but performance - * here doesn't matter. - */ - regs->orig_ax = syscall_nr; - regs->ax = -ENOSYS; - tmp = secure_computing(); - if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { - warn_bad_vsyscall(KERN_DEBUG, regs, - "seccomp tried to change syscall nr or ip"); - do_exit(SIGSYS); - } - regs->orig_ax = -1; - if (tmp) - goto do_ret; /* skip requested */ - - /* - * With a real vsyscall, page faults cause SIGSEGV. We want to - * preserve that behavior to make writing exploits harder. - */ - prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error; - current_thread_info()->sig_on_uaccess_error = 1; - - ret = -EFAULT; - switch (vsyscall_nr) { - case 0: - ret = sys_gettimeofday( - (struct timeval __user *)regs->di, - (struct timezone __user *)regs->si); - break; - - case 1: - ret = sys_time((time_t __user *)regs->di); - break; - - case 2: - ret = sys_getcpu((unsigned __user *)regs->di, - (unsigned __user *)regs->si, - NULL); - break; - } - - current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error; - -check_fault: - if (ret == -EFAULT) { - /* Bad news -- userspace fed a bad pointer to a vsyscall. */ - warn_bad_vsyscall(KERN_INFO, regs, - "vsyscall fault (exploit attempt?)"); - - /* - * If we failed to generate a signal for any reason, - * generate one here. (This should be impossible.) - */ - if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) && - !sigismember(&tsk->pending.signal, SIGSEGV))) - goto sigsegv; - - return true; /* Don't emulate the ret. */ - } - - regs->ax = ret; - -do_ret: - /* Emulate a ret instruction. */ - regs->ip = caller; - regs->sp += 8; - return true; - -sigsegv: - force_sig(SIGSEGV, current); - return true; -} - -/* - * A pseudo VMA to allow ptrace access for the vsyscall page. This only - * covers the 64bit vsyscall page now. 32bit has a real VMA now and does - * not need special handling anymore: - */ -static const char *gate_vma_name(struct vm_area_struct *vma) -{ - return "[vsyscall]"; -} -static struct vm_operations_struct gate_vma_ops = { - .name = gate_vma_name, -}; -static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_ADDR, - .vm_end = VSYSCALL_ADDR + PAGE_SIZE, - .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC, - .vm_ops = &gate_vma_ops, -}; - -struct vm_area_struct *get_gate_vma(struct mm_struct *mm) -{ -#ifdef CONFIG_IA32_EMULATION - if (!mm || mm->context.ia32_compat) - return NULL; -#endif - if (vsyscall_mode == NONE) - return NULL; - return &gate_vma; -} - -int in_gate_area(struct mm_struct *mm, unsigned long addr) -{ - struct vm_area_struct *vma = get_gate_vma(mm); - - if (!vma) - return 0; - - return (addr >= vma->vm_start) && (addr < vma->vm_end); -} - -/* - * Use this when you have no reliable mm, typically from interrupt - * context. It is less reliable than using a task's mm and may give - * false positives. - */ -int in_gate_area_no_mm(unsigned long addr) -{ - return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; -} - -void __init map_vsyscall(void) -{ - extern char __vsyscall_page; - unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - - if (vsyscall_mode != NONE) - __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); - - BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != - (unsigned long)VSYSCALL_ADDR); -} diff --git a/arch/x86/kernel/vsyscall_emu_64.S b/arch/x86/kernel/vsyscall_emu_64.S deleted file mode 100644 index c9596a9af..000000000 --- a/arch/x86/kernel/vsyscall_emu_64.S +++ /dev/null @@ -1,37 +0,0 @@ -/* - * vsyscall_emu_64.S: Vsyscall emulation page - * - * Copyright (c) 2011 Andy Lutomirski - * - * Subject to the GNU General Public License, version 2 - */ - -#include <linux/linkage.h> - -#include <asm/irq_vectors.h> -#include <asm/page_types.h> -#include <asm/unistd_64.h> - -__PAGE_ALIGNED_DATA - .globl __vsyscall_page - .balign PAGE_SIZE, 0xcc - .type __vsyscall_page, @object -__vsyscall_page: - - mov $__NR_gettimeofday, %rax - syscall - ret - - .balign 1024, 0xcc - mov $__NR_time, %rax - syscall - ret - - .balign 1024, 0xcc - mov $__NR_getcpu, %rax - syscall - ret - - .balign 4096, 0xcc - - .size __vsyscall_page, 4096 diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c deleted file mode 100644 index 51e330416..000000000 --- a/arch/x86/kernel/vsyscall_gtod.c +++ /dev/null @@ -1,70 +0,0 @@ -/* - * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE - * Copyright 2003 Andi Kleen, SuSE Labs. - * - * Modified for x86 32 bit architecture by - * Stefani Seibold <stefani@seibold.net> - * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany - * - * Thanks to hpa@transmeta.com for some useful hint. - * Special thanks to Ingo Molnar for his early experience with - * a different vsyscall implementation for Linux/IA32 and for the name. - * - */ - -#include <linux/timekeeper_internal.h> -#include <asm/vgtod.h> -#include <asm/vvar.h> - -DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); - -void update_vsyscall_tz(void) -{ - vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest; - vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime; -} - -void update_vsyscall(struct timekeeper *tk) -{ - struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; - - gtod_write_begin(vdata); - - /* copy vsyscall data */ - vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; - vdata->cycle_last = tk->tkr_mono.cycle_last; - vdata->mask = tk->tkr_mono.mask; - vdata->mult = tk->tkr_mono.mult; - vdata->shift = tk->tkr_mono.shift; - - vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec; - - vdata->monotonic_time_sec = tk->xtime_sec - + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec - + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->tkr_mono.shift); - while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { - vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; - vdata->monotonic_time_sec++; - } - - vdata->wall_time_coarse_sec = tk->xtime_sec; - vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> - tk->tkr_mono.shift); - - vdata->monotonic_time_coarse_sec = - vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_coarse_nsec = - vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec; - - while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) { - vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC; - vdata->monotonic_time_coarse_sec++; - } - - gtod_write_end(vdata); -} diff --git a/arch/x86/kernel/vsyscall_trace.h b/arch/x86/kernel/vsyscall_trace.h deleted file mode 100644 index a8b2edec5..000000000 --- a/arch/x86/kernel/vsyscall_trace.h +++ /dev/null @@ -1,29 +0,0 @@ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM vsyscall - -#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) -#define __VSYSCALL_TRACE_H - -#include <linux/tracepoint.h> - -TRACE_EVENT(emulate_vsyscall, - - TP_PROTO(int nr), - - TP_ARGS(nr), - - TP_STRUCT__entry(__field(int, nr)), - - TP_fast_assign( - __entry->nr = nr; - ), - - TP_printk("nr = %d", __entry->nr) -); - -#endif - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../arch/x86/kernel -#define TRACE_INCLUDE_FILE vsyscall_trace -#include <trace/define_trace.h> diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index 37d8fa443..a0695be19 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 234b0722d..3839628d9 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -11,7 +11,6 @@ #include <asm/bios_ebda.h> #include <asm/paravirt.h> #include <asm/pci_x86.h> -#include <asm/pci.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> @@ -111,11 +110,9 @@ EXPORT_SYMBOL_GPL(x86_platform); #if defined(CONFIG_PCI_MSI) struct x86_msi_ops x86_msi = { .setup_msi_irqs = native_setup_msi_irqs, - .compose_msi_msg = native_compose_msi_msg, .teardown_msi_irq = native_teardown_msi_irq, .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, - .setup_hpet_msi = default_setup_hpet_msi, }; /* MSI arch specific hooks */ @@ -141,13 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev) #endif struct x86_io_apic_ops x86_io_apic_ops = { - .init = native_io_apic_init_mappings, .read = native_io_apic_read, - .write = native_io_apic_write, - .modify = native_io_apic_modify, .disable = native_disable_io_apic, - .print_entries = native_io_apic_print_entries, - .set_affinity = native_ioapic_set_affinity, - .setup_entry = native_setup_ioapic_entry, - .eoi_ioapic_pin = native_eoi_ioapic_pin, }; diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c deleted file mode 100644 index 87a815b85..000000000 --- a/arch/x86/kernel/xsave.c +++ /dev/null @@ -1,724 +0,0 @@ -/* - * xsave/xrstor support. - * - * Author: Suresh Siddha <suresh.b.siddha@intel.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/bootmem.h> -#include <linux/compat.h> -#include <linux/cpu.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/sigframe.h> -#include <asm/tlbflush.h> -#include <asm/xcr.h> - -/* - * Supported feature mask by the CPU and the kernel. - */ -u64 pcntxt_mask; - -/* - * Represents init state for the supported extended state. - */ -struct xsave_struct *init_xstate_buf; - -static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; -static unsigned int *xstate_offsets, *xstate_sizes; -static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8]; -static unsigned int xstate_features; - -/* - * If a processor implementation discern that a processor state component is - * in its initialized state it may modify the corresponding bit in the - * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory - * layout in the case of xsaveopt. While presenting the xstate information to - * the user, we always ensure that the memory layout of a feature will be in - * the init state if the corresponding header bit is zero. This is to ensure - * that the user doesn't see some stale state in the memory layout during - * signal handling, debugging etc. - */ -void __sanitize_i387_state(struct task_struct *tsk) -{ - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - int feature_bit = 0x2; - u64 xstate_bv; - - if (!fx) - return; - - xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; - - /* - * None of the feature bits are in init state. So nothing else - * to do for us, as the memory layout is up to date. - */ - if ((xstate_bv & pcntxt_mask) == pcntxt_mask) - return; - - /* - * FP is in init state - */ - if (!(xstate_bv & XSTATE_FP)) { - fx->cwd = 0x37f; - fx->swd = 0; - fx->twd = 0; - fx->fop = 0; - fx->rip = 0; - fx->rdp = 0; - memset(&fx->st_space[0], 0, 128); - } - - /* - * SSE is in init state - */ - if (!(xstate_bv & XSTATE_SSE)) - memset(&fx->xmm_space[0], 0, 256); - - xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2; - - /* - * Update all the other memory layouts for which the corresponding - * header bit is in the init state. - */ - while (xstate_bv) { - if (xstate_bv & 0x1) { - int offset = xstate_offsets[feature_bit]; - int size = xstate_sizes[feature_bit]; - - memcpy(((void *) fx) + offset, - ((void *) init_xstate_buf) + offset, - size); - } - - xstate_bv >>= 1; - feature_bit++; - } -} - -/* - * Check for the presence of extended state information in the - * user fpstate pointer in the sigcontext. - */ -static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw) -{ - int min_xstate_size = sizeof(struct i387_fxsave_struct) + - sizeof(struct xsave_hdr_struct); - unsigned int magic2; - - if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) - return -1; - - /* Check for the first magic field and other error scenarios. */ - if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || - fx_sw->xstate_size < min_xstate_size || - fx_sw->xstate_size > xstate_size || - fx_sw->xstate_size > fx_sw->extended_size) - return -1; - - /* - * Check for the presence of second magic word at the end of memory - * layout. This detects the case where the user just copied the legacy - * fpstate layout with out copying the extended state information - * in the memory layout. - */ - if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) - || magic2 != FP_XSTATE_MAGIC2) - return -1; - - return 0; -} - -/* - * Signal frame handlers. - */ -static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) -{ - if (use_fxsr()) { - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct user_i387_ia32_struct env; - struct _fpstate_ia32 __user *fp = buf; - - convert_from_fxsr(&env, tsk); - - if (__copy_to_user(buf, &env, sizeof(env)) || - __put_user(xsave->i387.swd, &fp->status) || - __put_user(X86_FXSR_MAGIC, &fp->magic)) - return -1; - } else { - struct i387_fsave_struct __user *fp = buf; - u32 swd; - if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) - return -1; - } - - return 0; -} - -static inline int save_xstate_epilog(void __user *buf, int ia32_frame) -{ - struct xsave_struct __user *x = buf; - struct _fpx_sw_bytes *sw_bytes; - u32 xstate_bv; - int err; - - /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ - sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; - err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - - if (!use_xsave()) - return err; - - err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; - - err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - return err; -} - -static inline int save_user_xstate(struct xsave_struct __user *buf) -{ - int err; - - if (use_xsave()) - err = xsave_user(buf); - else if (use_fxsr()) - err = fxsave_user((struct i387_fxsave_struct __user *) buf); - else - err = fsave_user((struct i387_fsave_struct __user *) buf); - - if (unlikely(err) && __clear_user(buf, xstate_size)) - err = -EFAULT; - return err; -} - -/* - * Save the fpu, extended register state to the user signal frame. - * - * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save - * state is copied. - * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. - * - * buf == buf_fx for 64-bit frames and 32-bit fsave frame. - * buf != buf_fx for 32-bit frames with fxstate. - * - * If the fpu, extended register state is live, save the state directly - * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, - * copy the thread's fpu state to the user frame starting at 'buf_fx'. - * - * If this is a 32-bit frame with fxstate, put a fsave header before - * the aligned state at 'buf_fx'. - * - * For [f]xsave state, update the SW reserved fields in the [f]xsave frame - * indicating the absence/presence of the extended state to the user. - */ -int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; - struct task_struct *tsk = current; - int ia32_fxstate = (buf != buf_fx); - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!access_ok(VERIFY_WRITE, buf, size)) - return -EACCES; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(current, NULL, 0, - sizeof(struct user_i387_ia32_struct), NULL, - (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - - if (user_has_fpu()) { - /* Save the live register state to the user directly. */ - if (save_user_xstate(buf_fx)) - return -1; - /* Update the thread's fxstate to save the fsave header. */ - if (ia32_fxstate) - fpu_fxsave(&tsk->thread.fpu); - } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf_fx, xsave, xstate_size)) - return -1; - } - - /* Save the fsave header for the 32-bit frames. */ - if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) - return -1; - - if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) - return -1; - - return 0; -} - -static inline void -sanitize_restored_xstate(struct task_struct *tsk, - struct user_i387_ia32_struct *ia32_env, - u64 xstate_bv, int fx_only) -{ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; - - if (use_xsave()) { - /* These bits must be zero. */ - memset(xsave_hdr->reserved, 0, 48); - - /* - * Init the state that is not present in the memory - * layout and not enabled by the OS. - */ - if (fx_only) - xsave_hdr->xstate_bv = XSTATE_FPSSE; - else - xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); - } - - if (use_fxsr()) { - /* - * mscsr reserved bits must be masked to zero for security - * reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - - convert_to_fxsr(tsk, ia32_env); - } -} - -/* - * Restore the extended state if present. Otherwise, restore the FP/SSE state. - */ -static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) -{ - if (use_xsave()) { - if ((unsigned long)buf % 64 || fx_only) { - u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; - xrstor_state(init_xstate_buf, init_bv); - return fxrstor_user(buf); - } else { - u64 init_bv = pcntxt_mask & ~xbv; - if (unlikely(init_bv)) - xrstor_state(init_xstate_buf, init_bv); - return xrestore_user(buf, xbv); - } - } else if (use_fxsr()) { - return fxrstor_user(buf); - } else - return frstor_user(buf); -} - -int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - int ia32_fxstate = (buf != buf_fx); - struct task_struct *tsk = current; - int state_size = xstate_size; - u64 xstate_bv = 0; - int fx_only = 0; - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!buf) { - fpu_reset_state(tsk); - return 0; - } - - if (!access_ok(VERIFY_READ, buf, size)) - return -EACCES; - - if (!used_math() && init_fpu(tsk)) - return -1; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; - - if (use_xsave()) { - struct _fpx_sw_bytes fx_sw_user; - if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { - /* - * Couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - state_size = sizeof(struct i387_fxsave_struct); - fx_only = 1; - } else { - state_size = fx_sw_user.xstate_size; - xstate_bv = fx_sw_user.xstate_bv; - } - } - - if (ia32_fxstate) { - /* - * For 32-bit frames with fxstate, copy the user state to the - * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. - */ - struct fpu *fpu = &tsk->thread.fpu; - struct user_i387_ia32_struct env; - int err = 0; - - /* - * Drop the current fpu which clears used_math(). This ensures - * that any context-switch during the copy of the new state, - * avoids the intermediate state from getting restored/saved. - * Thus avoiding the new restored state from getting corrupted. - * We will be ready to restore/save the state only after - * set_used_math() is again set. - */ - drop_fpu(tsk); - - if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || - __copy_from_user(&env, buf, sizeof(env))) { - fpu_finit(fpu); - err = -1; - } else { - sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - } - - set_used_math(); - if (use_eager_fpu()) { - preempt_disable(); - math_state_restore(); - preempt_enable(); - } - - return err; - } else { - /* - * For 64-bit frames and 32-bit fsave frames, restore the user - * state to the registers directly (with exceptions handled). - */ - user_fpu_begin(); - if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { - fpu_reset_state(tsk); - return -1; - } - } - - return 0; -} - -/* - * Prepare the SW reserved portion of the fxsave memory layout, indicating - * the presence of the extended state information in the memory layout - * pointed by the fpstate pointer in the sigcontext. - * This will be saved when ever the FP and extended state context is - * saved on the user stack during the signal handler delivery to the user. - */ -static void prepare_fx_sw_frame(void) -{ - int fsave_header_size = sizeof(struct i387_fsave_struct); - int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = size; - fx_sw_reserved.xstate_bv = pcntxt_mask; - fx_sw_reserved.xstate_size = xstate_size; - - if (config_enabled(CONFIG_IA32_EMULATION)) { - fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; - } -} - -/* - * Enable the extended processor state save/restore feature - */ -static inline void xstate_enable(void) -{ - cr4_set_bits(X86_CR4_OSXSAVE); - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); -} - -/* - * Record the offsets and sizes of different state managed by the xsave - * memory layout. - */ -static void __init setup_xstate_features(void) -{ - int eax, ebx, ecx, edx, leaf = 0x2; - - xstate_features = fls64(pcntxt_mask); - xstate_offsets = alloc_bootmem(xstate_features * sizeof(int)); - xstate_sizes = alloc_bootmem(xstate_features * sizeof(int)); - - do { - cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); - - if (eax == 0) - break; - - xstate_offsets[leaf] = ebx; - xstate_sizes[leaf] = eax; - - leaf++; - } while (1); -} - -/* - * This function sets up offsets and sizes of all extended states in - * xsave area. This supports both standard format and compacted format - * of the xsave aread. - * - * Input: void - * Output: void - */ -void setup_xstate_comp(void) -{ - unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8]; - int i; - - /* - * The FP xstates and SSE xstates are legacy states. They are always - * in the fixed offsets in the xsave area in either compacted form - * or standard form. - */ - xstate_comp_offsets[0] = 0; - xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space); - - if (!cpu_has_xsaves) { - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - xstate_comp_offsets[i] = xstate_offsets[i]; - xstate_comp_sizes[i] = xstate_sizes[i]; - } - } - return; - } - - xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; - - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) - xstate_comp_sizes[i] = xstate_sizes[i]; - else - xstate_comp_sizes[i] = 0; - - if (i > 2) - xstate_comp_offsets[i] = xstate_comp_offsets[i-1] - + xstate_comp_sizes[i-1]; - - } -} - -/* - * setup the xstate image representing the init state - */ -static void __init setup_init_fpu_buf(void) -{ - /* - * Setup init_xstate_buf to represent the init state of - * all the features managed by the xsave - */ - init_xstate_buf = alloc_bootmem_align(xstate_size, - __alignof__(struct xsave_struct)); - fx_finit(&init_xstate_buf->i387); - - if (!cpu_has_xsave) - return; - - setup_xstate_features(); - - if (cpu_has_xsaves) { - init_xstate_buf->xsave_hdr.xcomp_bv = - (u64)1 << 63 | pcntxt_mask; - init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask; - } - - /* - * Init all the features state with header_bv being 0x0 - */ - xrstor_state_booting(init_xstate_buf, -1); - /* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. - */ - xsave_state_booting(init_xstate_buf, -1); -} - -static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) -{ - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; -} -__setup("eagerfpu=", eager_fpu_setup); - - -/* - * Calculate total size of enabled xstates in XCR0/pcntxt_mask. - */ -static void __init init_xstate_size(void) -{ - unsigned int eax, ebx, ecx, edx; - int i; - - if (!cpu_has_xsaves) { - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xstate_size = ebx; - return; - } - - xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = 2; i < 64; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); - xstate_size += eax; - } - } -} - -/* - * Enable and initialize the xsave feature. - */ -static void __init xstate_enable_boot_cpu(void) -{ - unsigned int eax, ebx, ecx, edx; - - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN(1, KERN_ERR "XSTATE_CPUID missing\n"); - return; - } - - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - pcntxt_mask = eax + ((u64)edx << 32); - - if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { - pr_err("FP/SSE not shown under xsave features 0x%llx\n", - pcntxt_mask); - BUG(); - } - - /* - * Support only the state known to OS. - */ - pcntxt_mask = pcntxt_mask & XCNTXT_MASK; - - xstate_enable(); - - /* - * Recompute the context size for enabled features - */ - init_xstate_size(); - - update_regset_xstate_info(xstate_size, pcntxt_mask); - prepare_fx_sw_frame(); - setup_init_fpu_buf(); - - /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) - eagerfpu = ENABLE; - - if (pcntxt_mask & XSTATE_EAGER) { - if (eagerfpu == DISABLE) { - pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n", - pcntxt_mask & XSTATE_EAGER); - pcntxt_mask &= ~XSTATE_EAGER; - } else { - eagerfpu = ENABLE; - } - } - - pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n", - pcntxt_mask, xstate_size, - cpu_has_xsaves ? "compacted form" : "standard form"); -} - -/* - * For the very first instance, this calls xstate_enable_boot_cpu(); - * for all subsequent instances, this calls xstate_enable(). - * - * This is somewhat obfuscated due to the lack of powerful enough - * overrides for the section checks. - */ -void xsave_init(void) -{ - static __refdata void (*next_func)(void) = xstate_enable_boot_cpu; - void (*this_func)(void); - - if (!cpu_has_xsave) - return; - - this_func = next_func; - next_func = xstate_enable; - this_func(); -} - -/* - * setup_init_fpu_buf() is __init and it is OK to call it here because - * init_xstate_buf will be unset only once during boot. - */ -void __init_refok eager_fpu_init(void) -{ - WARN_ON(used_math()); - current_thread_info()->status = 0; - - if (eagerfpu == ENABLE) - setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); - - if (!cpu_has_eager_fpu) { - stts(); - return; - } - - if (!init_xstate_buf) - setup_init_fpu_buf(); -} - -/* - * Given the xsave area and a state inside, this function returns the - * address of the state. - * - * This is the API that is called to get xstate address in either - * standard format or compacted format of xsave area. - * - * Inputs: - * xsave: base address of the xsave area; - * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE, - * etc.) - * Output: - * address of the state in the xsave area. - */ -void *get_xsave_addr(struct xsave_struct *xsave, int xstate) -{ - int feature = fls64(xstate) - 1; - if (!test_bit(feature, (unsigned long *)&pcntxt_mask)) - return NULL; - - return (void *)xsave + xstate_comp_offsets[feature]; -} -EXPORT_SYMBOL_GPL(get_xsave_addr); |