diff options
Diffstat (limited to 'arch/x86/kernel')
57 files changed, 1399 insertions, 774 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4b994232cb57..a01892bdd61a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -18,6 +18,7 @@ CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg +CFLAGS_REMOVE_head64.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -29,6 +30,7 @@ OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y +OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 26b78d86f25a..85a9e17e0dbc 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,3 +1,5 @@ +OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y + obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c5b8f760473c..32e14d137416 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -409,8 +409,13 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; - /* 0xe8 is a relative jump; fix the offset. */ - if (*insnbuf == 0xe8 && a->replacementlen == 5) { + /* + * 0xe8 is a relative jump; fix the offset. + * + * Instruction length is checked before the opcode to avoid + * accessing uninitialized bytes for zero-length replacements. + */ + if (a->replacementlen == 5 && *insnbuf == 0xe8) { *(s32 *)(insnbuf + 1) += replacement - instr; DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx", *(s32 *)(insnbuf + 1), diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2d75faf743f2..98b3dd8cf2bf 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -54,6 +54,8 @@ #include <asm/mce.h> #include <asm/tsc.h> #include <asm/hypervisor.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> unsigned int num_processors; @@ -545,6 +547,81 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); +#define DEADLINE_MODEL_MATCH_FUNC(model, func) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&func } + +#define DEADLINE_MODEL_MATCH_REV(model, rev) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } + +static u32 hsx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x02: return 0x3a; /* EP */ + case 0x04: return 0x0f; /* EX */ + } + + return ~0U; +} + +static u32 bdx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x02: return 0x00000011; + case 0x03: return 0x0700000e; + case 0x04: return 0x0f00000c; + case 0x05: return 0x0e000003; + } + + return ~0U; +} + +static const struct x86_cpu_id deadline_match[] = { + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_GT3E, 0x17), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_CORE, 0x25), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_GT3E, 0x17), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_MOBILE, 0xb2), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_DESKTOP, 0xb2), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_MOBILE, 0x52), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_DESKTOP, 0x52), + + {}, +}; + +static void apic_check_deadline_errata(void) +{ + const struct x86_cpu_id *m = x86_match_cpu(deadline_match); + u32 rev; + + if (!m) + return; + + /* + * Function pointers will have the MSB set due to address layout, + * immediate revisions will not. + */ + if ((long)m->driver_data < 0) + rev = ((u32 (*)(void))(m->driver_data))(); + else + rev = (u32)m->driver_data; + + if (boot_cpu_data.microcode >= rev) + return; + + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " + "please update microcode to version: 0x%x (or later)\n", rev); +} + /* * Setup the local APIC timer for this CPU. Copy the initialized values * of the boot CPU and register the clock event in the framework. @@ -563,6 +640,7 @@ static void setup_APIC_timer(void) levt->cpumask = cpumask_of(smp_processor_id()); if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + levt->name = "lapic-deadline"; levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; @@ -1779,6 +1857,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; + apic_check_deadline_errata(); + if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); return; @@ -2201,23 +2281,32 @@ void default_init_apic_ldr(void) apic_write(APIC_LDR, val); } -int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) +int default_cpu_mask_to_apicid(const struct cpumask *mask, + struct irq_data *irqdata, + unsigned int *apicid) { - unsigned int cpu; + unsigned int cpu = cpumask_first(mask); - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } + if (cpu >= nr_cpu_ids) + return -EINVAL; + *apicid = per_cpu(x86_cpu_to_apicid, cpu); + irq_data_update_effective_affinity(irqdata, cpumask_of(cpu)); + return 0; +} - if (likely(cpu < nr_cpu_ids)) { - *apicid = per_cpu(x86_cpu_to_apicid, cpu); - return 0; - } +int flat_cpu_mask_to_apicid(const struct cpumask *mask, + struct irq_data *irqdata, + unsigned int *apicid) - return -EINVAL; +{ + struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); + unsigned long cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; + + if (!cpu_mask) + return -EINVAL; + *apicid = (unsigned int)cpu_mask; + cpumask_bits(effmsk)[0] = cpu_mask; + return 0; } /* diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index a4d7ff20ed22..dedd5a41ba48 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -172,7 +172,7 @@ static struct apic apic_flat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, @@ -268,7 +268,7 @@ static struct apic apic_physflat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 2262eb6df796..6599f437b4ab 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -141,7 +141,7 @@ struct apic apic_noop __ro_after_init = { .get_apic_id = noop_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index e08fe2c8dd8c..2fda912219a6 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -267,7 +267,7 @@ static const struct apic apic_numachip1 __refconst = { .get_apic_id = numachip1_get_apic_id, .set_apic_id = numachip1_set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, @@ -318,7 +318,7 @@ static const struct apic apic_numachip2 __refconst = { .get_apic_id = numachip2_get_apic_id, .set_apic_id = numachip2_set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 56012010332c..456e45e8bf84 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -172,7 +172,7 @@ static struct apic apic_bigsmp __ro_after_init = { .get_apic_id = bigsmp_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c index ae50d3454d78..56ccf9346b08 100644 --- a/arch/x86/kernel/apic/htirq.c +++ b/arch/x86/kernel/apic/htirq.c @@ -150,16 +150,27 @@ static const struct irq_domain_ops htirq_domain_ops = { .deactivate = htirq_domain_deactivate, }; -void arch_init_htirq_domain(struct irq_domain *parent) +void __init arch_init_htirq_domain(struct irq_domain *parent) { + struct fwnode_handle *fn; + if (disable_apic) return; - htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL); + fn = irq_domain_alloc_named_fwnode("PCI-HT"); + if (!fn) + goto warn; + + htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL); + irq_domain_free_fwnode(fn); if (!htirq_domain) - pr_warn("failed to initialize irqdomain for HTIRQ.\n"); - else - htirq_domain->parent = parent; + goto warn; + + htirq_domain->parent = parent; + return; + +warn: + pr_warn("Failed to initialize irqdomain for HTIRQ.\n"); } int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 347bb9f65737..b4f5f73febdb 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1200,28 +1200,6 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); static struct irq_chip ioapic_chip, ioapic_ir_chip; -#ifdef CONFIG_X86_32 -static inline int IO_APIC_irq_trigger(int irq) -{ - int apic, idx, pin; - - for_each_ioapic_pin(apic, pin) { - idx = find_irq_entry(apic, pin, mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0))) - return irq_trigger(idx); - } - /* - * nonexistent IRQs are edge default - */ - return 0; -} -#else -static inline int IO_APIC_irq_trigger(int irq) -{ - return 1; -} -#endif - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; @@ -2223,6 +2201,8 @@ static int mp_irqdomain_create(int 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); + struct fwnode_handle *fn; + char *name = "IO-APIC"; if (cfg->type == IOAPIC_DOMAIN_INVALID) return 0; @@ -2233,9 +2213,25 @@ static int mp_irqdomain_create(int ioapic) parent = irq_remapping_get_ir_irq_domain(&info); if (!parent) parent = x86_vector_domain; + else + name = "IO-APIC-IR"; + + /* Handle device tree enumerated APICs proper */ + if (cfg->dev) { + fn = of_node_to_fwnode(cfg->dev); + } else { + fn = irq_domain_alloc_named_id_fwnode(name, ioapic); + if (!fn) + return -ENOMEM; + } + + ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, + (void *)(long)ioapic); + + /* Release fw handle if it was allocated above */ + if (!cfg->dev) + irq_domain_free_fwnode(fn); - ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops, - (void *)(long)ioapic); if (!ip->irqdomain) return -ENOMEM; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index c61aec7e65f4..9b18be764422 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -136,13 +136,20 @@ static struct msi_domain_info pci_msi_domain_info = { .handler_name = "edge", }; -void arch_init_msi_domain(struct irq_domain *parent) +void __init arch_init_msi_domain(struct irq_domain *parent) { + struct fwnode_handle *fn; + if (disable_apic) return; - msi_default_domain = pci_msi_create_irq_domain(NULL, - &pci_msi_domain_info, parent); + fn = irq_domain_alloc_named_fwnode("PCI-MSI"); + if (fn) { + msi_default_domain = + pci_msi_create_irq_domain(fn, &pci_msi_domain_info, + parent); + irq_domain_free_fwnode(fn); + } if (!msi_default_domain) pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); } @@ -167,9 +174,18 @@ static struct msi_domain_info pci_msi_ir_domain_info = { .handler_name = "edge", }; -struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent) +struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, + const char *name, int id) { - return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent); + struct fwnode_handle *fn; + struct irq_domain *d; + + fn = irq_domain_alloc_named_id_fwnode(name, id); + if (!fn) + return NULL; + d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); + irq_domain_free_fwnode(fn); + return d; } #endif @@ -221,13 +237,20 @@ static struct irq_domain *dmar_get_irq_domain(void) { static struct irq_domain *dmar_domain; static DEFINE_MUTEX(dmar_lock); + struct fwnode_handle *fn; mutex_lock(&dmar_lock); - if (dmar_domain == NULL) - dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info, + if (dmar_domain) + goto out; + + fn = irq_domain_alloc_named_fwnode("DMAR-MSI"); + if (fn) { + dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info, x86_vector_domain); + irq_domain_free_fwnode(fn); + } +out: mutex_unlock(&dmar_lock); - return dmar_domain; } @@ -317,9 +340,10 @@ static struct msi_domain_info hpet_msi_domain_info = { struct irq_domain *hpet_create_irq_domain(int hpet_id) { - struct irq_domain *parent; - struct irq_alloc_info info; struct msi_domain_info *domain_info; + struct irq_domain *parent, *d; + struct irq_alloc_info info; + struct fwnode_handle *fn; if (x86_vector_domain == NULL) return NULL; @@ -340,7 +364,16 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id) else hpet_msi_controller.name = "IR-HPET-MSI"; - return msi_create_irq_domain(NULL, domain_info, parent); + fn = irq_domain_alloc_named_id_fwnode(hpet_msi_controller.name, + hpet_id); + if (!fn) { + kfree(domain_info); + return NULL; + } + + d = msi_create_irq_domain(fn, domain_info, parent); + irq_domain_free_fwnode(fn); + return d; } int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 2e8f7f048f4f..63287659adb6 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -102,7 +102,7 @@ static struct apic apic_default __ro_after_init = { .get_apic_id = default_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f3557a1eb562..b3af457ed667 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -103,7 +103,8 @@ static void free_apic_chip_data(struct apic_chip_data *data) } static int __assign_irq_vector(int irq, struct apic_chip_data *d, - const struct cpumask *mask) + const struct cpumask *mask, + struct irq_data *irqdata) { /* * NOTE! The local APIC isn't very good at handling @@ -141,7 +142,7 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, /* * Clear the offline cpus from @vector_cpumask for searching * and verify whether the result overlaps with @mask. If true, - * then the call to apic->cpu_mask_to_apicid_and() will + * then the call to apic->cpu_mask_to_apicid() will * succeed as well. If not, no point in trying to find a * vector in this mask. */ @@ -221,34 +222,40 @@ success: * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail * as we already established, that mask & d->domain & cpu_online_mask * is not empty. + * + * vector_searchmask is a subset of d->domain and has the offline + * cpus masked out. */ - BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid)); + cpumask_and(vector_searchmask, vector_searchmask, mask); + BUG_ON(apic->cpu_mask_to_apicid(vector_searchmask, irqdata, + &d->cfg.dest_apicid)); return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, - const struct cpumask *mask) + const struct cpumask *mask, + struct irq_data *irqdata) { int err; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, data, mask); + err = __assign_irq_vector(irq, data, mask, irqdata); raw_spin_unlock_irqrestore(&vector_lock, flags); return err; } static int assign_irq_vector_policy(int irq, int node, struct apic_chip_data *data, - struct irq_alloc_info *info) + struct irq_alloc_info *info, + struct irq_data *irqdata) { if (info && info->mask) - return assign_irq_vector(irq, data, info->mask); + return assign_irq_vector(irq, data, info->mask, irqdata); if (node != NUMA_NO_NODE && - assign_irq_vector(irq, data, cpumask_of_node(node)) == 0) + assign_irq_vector(irq, data, cpumask_of_node(node), irqdata) == 0) return 0; - return assign_irq_vector(irq, data, apic->target_cpus()); + return assign_irq_vector(irq, data, apic->target_cpus(), irqdata); } static void clear_irq_vector(int irq, struct apic_chip_data *data) @@ -360,9 +367,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irq_data->chip = &lapic_controller; irq_data->chip_data = data; irq_data->hwirq = virq + i; - err = assign_irq_vector_policy(virq + i, node, data, info); + err = assign_irq_vector_policy(virq + i, node, data, info, + irq_data); if (err) goto error; + /* + * If the apic destination mode is physical, then the + * effective affinity is restricted to a single target + * CPU. Mark the interrupt accordingly. + */ + if (!apic->irq_dest_mode) + irqd_set_single_target(irq_data); } return 0; @@ -405,7 +420,7 @@ int __init arch_probe_nr_irqs(void) } #ifdef CONFIG_X86_IO_APIC -static void init_legacy_irqs(void) +static void __init init_legacy_irqs(void) { int i, node = cpu_to_node(0); struct apic_chip_data *data; @@ -424,16 +439,21 @@ static void init_legacy_irqs(void) } } #else -static void init_legacy_irqs(void) { } +static inline void init_legacy_irqs(void) { } #endif int __init arch_early_irq_init(void) { + struct fwnode_handle *fn; + init_legacy_irqs(); - x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops, - NULL); + fn = irq_domain_alloc_named_fwnode("VECTOR"); + BUG_ON(!fn); + x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, + NULL); BUG_ON(x86_vector_domain == NULL); + irq_domain_free_fwnode(fn); irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); @@ -529,11 +549,12 @@ static int apic_set_affinity(struct irq_data *irq_data, if (!cpumask_intersects(dest, cpu_online_mask)) return -EINVAL; - err = assign_irq_vector(irq, data, dest); + err = assign_irq_vector(irq, data, dest, irq_data); return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { + .name = "APIC", .irq_ack = apic_ack_edge, .irq_set_affinity = apic_set_affinity, .irq_retrigger = apic_retrigger_irq, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 5a35f208ed95..481237cb1544 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -4,6 +4,7 @@ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/dmar.h> +#include <linux/irq.h> #include <linux/cpu.h> #include <asm/smp.h> @@ -104,35 +105,30 @@ static void x2apic_send_IPI_all(int vector) } static int -x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) +x2apic_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, + unsigned int *apicid) { + struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); + unsigned int cpu; u32 dest = 0; u16 cluster; - int i; - - for_each_cpu_and(i, cpumask, andmask) { - if (!cpumask_test_cpu(i, cpu_online_mask)) - continue; - dest = per_cpu(x86_cpu_to_logical_apicid, i); - cluster = x2apic_cluster(i); - break; - } - if (!dest) + cpu = cpumask_first(mask); + if (cpu >= nr_cpu_ids) return -EINVAL; - for_each_cpu_and(i, cpumask, andmask) { - if (!cpumask_test_cpu(i, cpu_online_mask)) - continue; - if (cluster != x2apic_cluster(i)) + dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + cluster = x2apic_cluster(cpu); + + cpumask_clear(effmsk); + for_each_cpu(cpu, mask) { + if (cluster != x2apic_cluster(cpu)) continue; - dest |= per_cpu(x86_cpu_to_logical_apicid, i); + dest |= per_cpu(x86_cpu_to_logical_apicid, cpu); + cpumask_set_cpu(cpu, effmsk); } *apicid = dest; - return 0; } @@ -256,7 +252,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index ff111f05a314..3baf0c3dc875 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -127,7 +127,7 @@ static struct apic apic_x2apic_phys __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index b487b3a01615..0d57bb9079c9 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -526,27 +526,15 @@ static void uv_init_apic_ldr(void) } static int -uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) +uv_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, + unsigned int *apicid) { - int unsigned cpu; + int ret = default_cpu_mask_to_apicid(mask, irqdata, apicid); - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - - if (likely(cpu < nr_cpu_ids)) { - *apicid = per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; - return 0; - } + if (!ret) + *apicid |= uv_apicid_hibits; - return -EINVAL; + return ret; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -614,7 +602,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index a70fd61095f8..6f077445647a 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -255,6 +255,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) break; case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */ + case 11: /* GX1 with inverted Device ID */ #ifdef CONFIG_PCI { u32 vendor, device; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index f5af0cc7eb0d..9257bd9dc664 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -856,11 +856,13 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_cdp; + goto out_destroy; static_branch_enable(&rdt_enable_key); goto out; +out_destroy: + kernfs_remove(kn_info); out_cdp: cdp_disable(); out: diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 9c632cb88546..10cec43aac38 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -17,6 +17,8 @@ #include "mce-internal.h" +static BLOCKING_NOTIFIER_HEAD(mce_injector_chain); + static DEFINE_MUTEX(mce_chrdev_read_mutex); static char mce_helper[128]; @@ -345,24 +347,49 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, } } -static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off); +void mce_register_injector_chain(struct notifier_block *nb) +{ + blocking_notifier_chain_register(&mce_injector_chain, nb); +} +EXPORT_SYMBOL_GPL(mce_register_injector_chain); -void register_mce_write_callback(ssize_t (*fn)(struct file *filp, - const char __user *ubuf, - size_t usize, loff_t *off)) +void mce_unregister_injector_chain(struct notifier_block *nb) { - mce_write = fn; + blocking_notifier_chain_unregister(&mce_injector_chain, nb); } -EXPORT_SYMBOL_GPL(register_mce_write_callback); +EXPORT_SYMBOL_GPL(mce_unregister_injector_chain); 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); - else + struct mce m; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* + * There are some cases where real MSR reads could slip + * through. + */ + if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA)) + return -EIO; + + if ((unsigned long)usize > sizeof(struct mce)) + usize = sizeof(struct mce); + if (copy_from_user(&m, ubuf, usize)) + return -EFAULT; + + if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu)) return -EINVAL; + + /* + * Need to give user space some time to set everything up, + * so do it a jiffie or two later everywhere. + */ + schedule_timeout(2); + + blocking_notifier_call_chain(&mce_injector_chain, 0, &m); + + return usize; } static const struct file_operations mce_chrdev_ops = { @@ -388,9 +415,15 @@ static __init int dev_mcelog_init_device(void) /* register character device /dev/mcelog */ err = misc_register(&mce_chrdev_device); if (err) { - pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + if (err == -EBUSY) + /* Xen dom0 might have registered the device already. */ + pr_info("Unable to init device /dev/mcelog, already registered"); + else + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + return err; } + mce_register_decode_chain(&dev_mcelog_nb); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 99165b206df3..231ad23b24a9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -10,23 +10,105 @@ * Authors: * Andi Kleen * Ying Huang + * + * The AMD part (from mce_amd_inj.c): a simple MCE injection facility + * for testing different aspects of the RAS code. This driver should be + * built as module so that it can be loaded on production kernels for + * testing purposes. + * + * This file may be distributed under the terms of the GNU General Public + * License version 2. + * + * Copyright (c) 2010-17: Borislav Petkov <bp@alien8.de> + * Advanced Micro Devices Inc. */ -#include <linux/uaccess.h> -#include <linux/module.h> -#include <linux/timer.h> + +#include <linux/cpu.h> +#include <linux/debugfs.h> #include <linux/kernel.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/preempt.h> -#include <linux/smp.h> +#include <linux/module.h> #include <linux/notifier.h> -#include <linux/kdebug.h> -#include <linux/cpu.h> -#include <linux/sched.h> -#include <linux/gfp.h> -#include <asm/mce.h> +#include <linux/pci.h> +#include <linux/uaccess.h> + +#include <asm/amd_nb.h> #include <asm/apic.h> +#include <asm/irq_vectors.h> +#include <asm/mce.h> #include <asm/nmi.h> +#include <asm/smp.h> + +#include "mce-internal.h" + +/* + * Collect all the MCi_XXX settings + */ +static struct mce i_mce; +static struct dentry *dfs_inj; + +static u8 n_banks; + +#define MAX_FLAG_OPT_SIZE 3 +#define NBCFG 0x44 + +enum injection_type { + SW_INJ = 0, /* SW injection, simply decode the error */ + HW_INJ, /* Trigger a #MC */ + DFR_INT_INJ, /* Trigger Deferred error interrupt */ + THR_INT_INJ, /* Trigger threshold interrupt */ + N_INJ_TYPES, +}; + +static const char * const flags_options[] = { + [SW_INJ] = "sw", + [HW_INJ] = "hw", + [DFR_INT_INJ] = "df", + [THR_INT_INJ] = "th", + NULL +}; + +/* Set default injection to SW_INJ */ +static enum injection_type inj_type = SW_INJ; + +#define MCE_INJECT_SET(reg) \ +static int inj_##reg##_set(void *data, u64 val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + m->reg = val; \ + return 0; \ +} + +MCE_INJECT_SET(status); +MCE_INJECT_SET(misc); +MCE_INJECT_SET(addr); +MCE_INJECT_SET(synd); + +#define MCE_INJECT_GET(reg) \ +static int inj_##reg##_get(void *data, u64 *val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + *val = m->reg; \ + return 0; \ +} + +MCE_INJECT_GET(status); +MCE_INJECT_GET(misc); +MCE_INJECT_GET(addr); +MCE_INJECT_GET(synd); + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); + +static void setup_inj_struct(struct mce *m) +{ + memset(m, 0, sizeof(struct mce)); + + m->cpuvendor = boot_cpu_data.x86_vendor; +} /* Update fake mce registers on current CPU. */ static void inject_mce(struct mce *m) @@ -143,7 +225,7 @@ static int raise_local(void) return ret; } -static void raise_mce(struct mce *m) +static void __maybe_unused raise_mce(struct mce *m) { int context = MCJ_CTX(m->inject_flags); @@ -198,55 +280,454 @@ static void raise_mce(struct mce *m) } } -/* Error injection interface */ -static ssize_t mce_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static int mce_inject_raise(struct notifier_block *nb, unsigned long val, + void *data) { - struct mce m; + struct mce *m = (struct mce *)data; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - /* - * There are some cases where real MSR reads could slip - * through. - */ - if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA)) - return -EIO; + if (!m) + return NOTIFY_DONE; + + mutex_lock(&mce_inject_mutex); + raise_mce(m); + mutex_unlock(&mce_inject_mutex); + + return NOTIFY_DONE; +} + +static struct notifier_block inject_nb = { + .notifier_call = mce_inject_raise, +}; + +/* + * Caller needs to be make sure this cpu doesn't disappear + * from under us, i.e.: get_cpu/put_cpu. + */ +static int toggle_hw_mce_inject(unsigned int cpu, bool enable) +{ + u32 l, h; + int err; + + err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); + if (err) { + pr_err("%s: error reading HWCR\n", __func__); + return err; + } + + enable ? (l |= BIT(18)) : (l &= ~BIT(18)); + + err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); + if (err) + pr_err("%s: error writing HWCR\n", __func__); - if ((unsigned long)usize > sizeof(struct mce)) - usize = sizeof(struct mce); - if (copy_from_user(&m, ubuf, usize)) + return err; +} + +static int __set_inj(const char *buf) +{ + int i; + + for (i = 0; i < N_INJ_TYPES; i++) { + if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { + inj_type = i; + return 0; + } + } + return -EINVAL; +} + +static ssize_t flags_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE]; + int n; + + n = sprintf(buf, "%s\n", flags_options[inj_type]); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static ssize_t flags_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE], *__buf; + int err; + + if (cnt > MAX_FLAG_OPT_SIZE) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; - if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu)) + buf[cnt - 1] = 0; + + /* strip whitespace */ + __buf = strstrip(buf); + + err = __set_inj(__buf); + if (err) { + pr_err("%s: Invalid flags value: %s\n", __func__, __buf); + return err; + } + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations flags_fops = { + .read = flags_read, + .write = flags_write, + .llseek = generic_file_llseek, +}; + +/* + * On which CPU to inject? + */ +MCE_INJECT_GET(extcpu); + +static int inj_extcpu_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= nr_cpu_ids || !cpu_online(val)) { + pr_err("%s: Invalid CPU: %llu\n", __func__, val); return -EINVAL; + } + m->extcpu = val; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); + +static void trigger_mce(void *info) +{ + asm volatile("int $18"); +} + +static void trigger_dfr_int(void *info) +{ + asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); +} + +static void trigger_thr_int(void *info) +{ + asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); +} + +static u32 get_nbc_for_node(int node_id) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + u32 cores_per_node; + + cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); + + return cores_per_node * node_id; +} + +static void toggle_nb_mca_mst_cpu(u16 nid) +{ + struct amd_northbridge *nb; + struct pci_dev *F3; + u32 val; + int err; + + nb = node_to_amd_nb(nid); + if (!nb) + return; + + F3 = nb->misc; + if (!F3) + return; + + err = pci_read_config_dword(F3, NBCFG, &val); + if (err) { + pr_err("%s: Error reading F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); + return; + } + + if (val & BIT(27)) + return; + + pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", + __func__); + + val |= BIT(27); + err = pci_write_config_dword(F3, NBCFG, val); + if (err) + pr_err("%s: Error writing F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); +} + +static void prepare_msrs(void *info) +{ + struct mce m = *(struct mce *)info; + u8 b = m.bank; + + wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); + + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (m.inject_flags == DFR_INT_INJ) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr); + } else { + wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr); + } + + wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); + wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd); + } else { + wrmsrl(MSR_IA32_MCx_STATUS(b), m.status); + wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr); + wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); + } +} + +static void do_inject(void) +{ + u64 mcg_status = 0; + unsigned int cpu = i_mce.extcpu; + u8 b = i_mce.bank; + + rdtscll(i_mce.tsc); + + if (i_mce.misc) + i_mce.status |= MCI_STATUS_MISCV; + + if (i_mce.synd) + i_mce.status |= MCI_STATUS_SYNDV; + + if (inj_type == SW_INJ) { + mce_inject_log(&i_mce); + return; + } + + /* prep MCE global settings for the injection */ + mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; + + if (!(i_mce.status & MCI_STATUS_PCC)) + mcg_status |= MCG_STATUS_RIPV; /* - * Need to give user space some time to set everything up, - * so do it a jiffie or two later everywhere. + * Ensure necessary status bits for deferred errors: + * - MCx_STATUS[Deferred]: make sure it is a deferred error + * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC */ - schedule_timeout(2); + if (inj_type == DFR_INT_INJ) { + i_mce.status |= MCI_STATUS_DEFERRED; + i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + } - mutex_lock(&mce_inject_mutex); - raise_mce(&m); - mutex_unlock(&mce_inject_mutex); - return usize; + /* + * For multi node CPUs, logging and reporting of bank 4 errors happens + * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for + * Fam10h and later BKDGs. + */ + if (static_cpu_has(X86_FEATURE_AMD_DCM) && + b == 4 && + boot_cpu_data.x86 < 0x17) { + toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); + cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + } + + get_online_cpus(); + if (!cpu_online(cpu)) + goto err; + + toggle_hw_mce_inject(cpu, true); + + i_mce.mcgstatus = mcg_status; + i_mce.inject_flags = inj_type; + smp_call_function_single(cpu, prepare_msrs, &i_mce, 0); + + toggle_hw_mce_inject(cpu, false); + + switch (inj_type) { + case DFR_INT_INJ: + smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); + break; + case THR_INT_INJ: + smp_call_function_single(cpu, trigger_thr_int, NULL, 0); + break; + default: + smp_call_function_single(cpu, trigger_mce, NULL, 0); + } + +err: + put_online_cpus(); + +} + +/* + * This denotes into which bank we're injecting and triggers + * the injection, at the same time. + */ +static int inj_bank_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= n_banks) { + pr_err("Non-existent MCE bank: %llu\n", val); + return -EINVAL; + } + + m->bank = val; + do_inject(); + + return 0; +} + +MCE_INJECT_GET(bank); + +DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); + +static const char readme_msg[] = +"Description of the files and their usages:\n" +"\n" +"Note1: i refers to the bank number below.\n" +"Note2: See respective BKDGs for the exact bit definitions of the files below\n" +"as they mirror the hardware registers.\n" +"\n" +"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" +"\t attributes of the error which caused the MCE.\n" +"\n" +"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" +"\t used for error thresholding purposes and its validity is indicated by\n" +"\t MCi_STATUS[MiscV].\n" +"\n" +"synd:\t Set MCi_SYND: provide syndrome info about the error. Only valid on\n" +"\t Scalable MCA systems, and its validity is indicated by MCi_STATUS[SyndV].\n" +"\n" +"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" +"\t associated with the error.\n" +"\n" +"cpu:\t The CPU to inject the error on.\n" +"\n" +"bank:\t Specify the bank you want to inject the error into: the number of\n" +"\t banks in a processor varies and is family/model-specific, therefore, the\n" +"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" +"\t injection.\n" +"\n" +"flags:\t Injection type to be performed. Writing to this file will trigger a\n" +"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" +"\t for AMD processors.\n" +"\n" +"\t Allowed error injection types:\n" +"\t - \"sw\": Software error injection. Decode error to a human-readable \n" +"\t format only. Safe to use.\n" +"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" +"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" +"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" +"\t before injecting.\n" +"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" +"\t error APIC interrupt handler to handle the error if the feature is \n" +"\t is present in hardware. \n" +"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" +"\t APIC interrupt handler to handle the error. \n" +"\n"; + +static ssize_t +inj_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static const struct file_operations readme_fops = { + .read = inj_readme_read, +}; + +static struct dfs_node { + char *name; + struct dentry *d; + const struct file_operations *fops; + umode_t perm; +} dfs_fls[] = { + { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, +}; + +static int __init debugfs_init(void) +{ + unsigned int i; + u64 cap; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + n_banks = cap & MCG_BANKCNT_MASK; + + dfs_inj = debugfs_create_dir("mce-inject", NULL); + if (!dfs_inj) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { + dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, + dfs_fls[i].perm, + dfs_inj, + &i_mce, + dfs_fls[i].fops); + + if (!dfs_fls[i].d) + goto err_dfs_add; + } + + return 0; + +err_dfs_add: + while (i-- > 0) + debugfs_remove(dfs_fls[i].d); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; + + return -ENODEV; } -static int inject_init(void) +static int __init inject_init(void) { + int err; + if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) return -ENOMEM; + + err = debugfs_init(); + if (err) { + free_cpumask_var(mce_inject_cpumask); + return err; + } + + register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify"); + mce_register_injector_chain(&inject_nb); + + setup_inj_struct(&i_mce); + pr_info("Machine check injector initialized\n"); - register_mce_write_callback(mce_write); - register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, - "mce_notify"); + return 0; } +static void __exit inject_exit(void) +{ + + mce_unregister_injector_chain(&inject_nb); + unregister_nmi_handler(NMI_LOCAL, "mce_notify"); + + debugfs_remove_recursive(dfs_inj); + dfs_inj = NULL; + + memset(&dfs_fls, 0, sizeof(dfs_fls)); + + free_cpumask_var(mce_inject_cpumask); +} + module_init(inject_init); -/* - * Cannot tolerate unloading currently because we cannot - * guarantee all openers of mce_chrdev will get a reference to us. - */ +module_exit(inject_exit); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 654ad0668d72..098530a93bb7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -100,7 +100,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2) extern struct device_attribute dev_attr_trigger; #ifdef CONFIG_X86_MCELOG_LEGACY -extern void mce_work_trigger(void); +void mce_work_trigger(void); +void mce_register_injector_chain(struct notifier_block *nb); +void mce_unregister_injector_chain(struct notifier_block *nb); #else static inline void mce_work_trigger(void) { } +static inline void mce_register_injector_chain(struct notifier_block *nb) { } +static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5abd4bf73d6e..6dde0497efc7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -499,16 +499,14 @@ static int mce_usable_address(struct mce *m) return 1; } -static bool memory_error(struct mce *m) +bool mce_is_memory_error(struct mce *m) { - struct cpuinfo_x86 *c = &boot_cpu_data; - - if (c->x86_vendor == X86_VENDOR_AMD) { + if (m->cpuvendor == X86_VENDOR_AMD) { /* ErrCodeExt[20:16] */ u8 xec = (m->status >> 16) & 0x1f; return (xec == 0x0 || xec == 0x8); - } else if (c->x86_vendor == X86_VENDOR_INTEL) { + } else if (m->cpuvendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes * @@ -529,6 +527,7 @@ static bool memory_error(struct mce *m) return false; } +EXPORT_SYMBOL_GPL(mce_is_memory_error); static bool cec_add_mce(struct mce *m) { @@ -536,7 +535,7 @@ static bool cec_add_mce(struct mce *m) return false; /* We eat only correctable DRAM errors with usable addresses. */ - if (memory_error(m) && + if (mce_is_memory_error(m) && !(m->status & MCI_STATUS_UC) && mce_usable_address(m)) if (!cec_add_elem(m->addr >> PAGE_SHIFT)) @@ -674,7 +673,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { bool error_seen = false; struct mce m; - int severity; int i; this_cpu_inc(mce_poll_count); @@ -711,11 +709,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_read_aux(&m, i); - severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) - if (m.status & MCI_STATUS_ADDRV) - m.severity = severity; + m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); /* * Don't get the IP here because it's unlikely to @@ -1551,7 +1545,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 < 17 && cfg->bootlog < 0) { + if (c->x86 < 0x11 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: @@ -1833,7 +1827,8 @@ void mce_disable_bank(int bank) * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) * monarchtimeout is how long to wait for other CPUs on machine * check, or 0 to not wait - * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. + * mce=bootlog Log MCEs from before booting. Disabled by default on AMD Fam10h + and older. * mce=nobootlog Don't log MCEs from before booting. * mce=bios_cmci_threshold Don't program the CMCI threshold * mce=recovery force enable memcpy_mcsafe() @@ -1913,12 +1908,13 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel CPUs. Some of these MSRs are socket-wide. + * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide. * Disabling them for just a single offlined CPU is bad, since it will * inhibit reporting for all shared resources on the socket like the * last level cache (LLC), the integrated memory controller (iMC), etc. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || + boot_cpu_data.x86_vendor == X86_VENDOR_AMD) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 6e4a047e4b68..9e314bcf67cc 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -164,17 +164,48 @@ static void default_deferred_error_interrupt(void) } void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; -static void get_smca_bank_info(unsigned int bank) +static void smca_configure(unsigned int bank, unsigned int cpu) { - unsigned int i, hwid_mcatype, cpu = smp_processor_id(); + unsigned int i, hwid_mcatype; struct smca_hwid *s_hwid; - u32 high, instance_id; + u32 high, low; + u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank); + + /* Set appropriate bits in MCA_CONFIG */ + if (!rdmsr_safe(smca_config, &low, &high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + high |= BIT(0); + + /* + * SMCA sets the Deferred Error Interrupt type per bank. + * + * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us + * if the DeferredIntType bit field is available. + * + * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the + * high portion of the MSR). OS should set this to 0x1 to enable + * APIC based interrupt. First, check that no interrupt has been + * set. + */ + if ((low & BIT(5)) && !((high >> 5) & 0x3)) + high |= BIT(5); + + wrmsr(smca_config, low, high); + } /* Collect bank_info using CPU 0 for now. */ if (cpu) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instance_id, &high)) { + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } @@ -191,7 +222,7 @@ static void get_smca_bank_info(unsigned int bank) smca_get_name(s_hwid->bank_type)); smca_banks[bank].hwid = s_hwid; - smca_banks[bank].id = instance_id; + smca_banks[bank].id = low; smca_banks[bank].sysfs_id = s_hwid->count++; break; } @@ -433,7 +464,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); - u32 smca_low, smca_high, smca_addr; + u32 smca_low, smca_high; struct threshold_block b; int new; @@ -457,51 +488,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, goto set_offset; } - smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - /* - * OS is required to set the MCAX bit to acknowledge that it is - * now using the new MSR ranges and new registers under each - * bank. It also means that the OS will configure deferred - * errors in the new MCx_CONFIG register. If the bit is not set, - * uncorrectable errors will cause a system panic. - * - * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) - */ - smca_high |= BIT(0); - - /* - * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} - * registers with the option of additionally logging to - * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. - * - * This bit is usually set by BIOS to retain the old behavior - * for OSes that don't use the new registers. Linux supports the - * new registers so let's disable that additional logging here. - * - * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high - * portion of the MSR). - */ - smca_high &= ~BIT(2); - - /* - * SMCA sets the Deferred Error Interrupt type per bank. - * - * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us - * if the DeferredIntType bit field is available. - * - * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the - * high portion of the MSR). OS should set this to 0x1 to enable - * APIC based interrupt. First, check that no interrupt has been - * set. - */ - if ((smca_low & BIT(5)) && !((smca_high >> 5) & 0x3)) - smca_high |= BIT(5); - - wrmsr(smca_addr, smca_low, smca_high); - } - /* Gather LVT offset for thresholding: */ if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) goto out; @@ -530,7 +516,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) - get_smca_bank_info(bank); + smca_configure(bank, cpu); for (block = 0; block < NR_BLOCKS; ++block) { address = get_block_address(cpu, address, low, high, bank, block); @@ -755,37 +741,19 @@ out_err: } EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr); -static void -__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) +static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) { - u32 msr_status = msr_ops.status(bank); - u32 msr_addr = msr_ops.addr(bank); struct mce m; - u64 status; - - WARN_ON_ONCE(deferred_err && threshold_err); - - if (deferred_err && mce_flags.smca) { - msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); - msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); - } - - rdmsrl(msr_status, status); - - if (!(status & MCI_STATUS_VAL)) - return; mce_setup(&m); m.status = status; + m.misc = misc; m.bank = bank; m.tsc = rdtsc(); - if (threshold_err) - m.misc = misc; - if (m.status & MCI_STATUS_ADDRV) { - rdmsrl(msr_addr, m.addr); + m.addr = addr; /* * Extract [55:<lsb>] where lsb is the least significant @@ -806,8 +774,6 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) } mce_log(&m); - - wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -832,87 +798,126 @@ asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) exiting_ack_irq(); } -/* APIC interrupt handler for deferred errors */ -static void amd_deferred_error_interrupt(void) +/* + * Returns true if the logged error is deferred. False, otherwise. + */ +static inline bool +_log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) { - unsigned int bank; - u32 msr_status; - u64 status; + u64 status, addr = 0; - for (bank = 0; bank < mca_cfg.banks; ++bank) { - msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) - : msr_ops.status(bank); + rdmsrl(msr_stat, status); + if (!(status & MCI_STATUS_VAL)) + return false; - rdmsrl(msr_status, status); + if (status & MCI_STATUS_ADDRV) + rdmsrl(msr_addr, addr); - if (!(status & MCI_STATUS_VAL) || - !(status & MCI_STATUS_DEFERRED)) - continue; + __log_error(bank, status, addr, misc); - __log_error(bank, true, false, 0); - break; - } + wrmsrl(msr_stat, 0); + + return status & MCI_STATUS_DEFERRED; } /* - * APIC Interrupt Handler + * We have three scenarios for checking for Deferred errors: + * + * 1) Non-SMCA systems check MCA_STATUS and log error if found. + * 2) SMCA systems check MCA_STATUS. If error is found then log it and also + * clear MCA_DESTAT. + * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and + * log it. */ +static void log_error_deferred(unsigned int bank) +{ + bool defrd; -/* - * threshold interrupt handler will service THRESHOLD_APIC_VECTOR. - * the interrupt goes off when error_count reaches threshold_limit. - * the handler will simply log mcelog w/ software defined bank number. - */ + defrd = _log_error_bank(bank, msr_ops.status(bank), + msr_ops.addr(bank), 0); -static void amd_threshold_interrupt(void) + if (!mce_flags.smca) + return; + + /* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */ + if (defrd) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return; + } + + /* + * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check + * for a valid error. + */ + _log_error_bank(bank, MSR_AMD64_SMCA_MCx_DESTAT(bank), + MSR_AMD64_SMCA_MCx_DEADDR(bank), 0); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) { - u32 low = 0, high = 0, address = 0; - unsigned int bank, block, cpu = smp_processor_id(); - struct thresh_restart tr; + unsigned int bank; - /* assume first bank caused it */ - for (bank = 0; bank < mca_cfg.banks; ++bank) { - if (!(per_cpu(bank_map, cpu) & (1 << bank))) - continue; - for (block = 0; block < NR_BLOCKS; ++block) { - address = get_block_address(cpu, address, low, high, bank, block); - if (!address) - break; + for (bank = 0; bank < mca_cfg.banks; ++bank) + log_error_deferred(bank); +} - if (rdmsr_safe(address, &low, &high)) - break; +static void log_error_thresholding(unsigned int bank, u64 misc) +{ + _log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc); +} - if (!(high & MASK_VALID_HI)) { - if (block) - continue; - else - break; - } +static void log_and_reset_block(struct threshold_block *block) +{ + struct thresh_restart tr; + u32 low = 0, high = 0; - if (!(high & MASK_CNTP_HI) || - (high & MASK_LOCKED_HI)) - continue; + if (!block) + return; - /* - * Log the machine check that caused the threshold - * event. - */ - if (high & MASK_OVERFLOW_HI) - goto log; - } - } - return; + if (rdmsr_safe(block->address, &low, &high)) + return; + + if (!(high & MASK_OVERFLOW_HI)) + return; -log: - __log_error(bank, false, true, ((u64)high << 32) | low); + /* Log the MCE which caused the threshold event. */ + log_error_thresholding(block->bank, ((u64)high << 32) | low); /* Reset threshold block after logging error. */ memset(&tr, 0, sizeof(tr)); - tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block]; + tr.b = block; threshold_restart_bank(&tr); } /* + * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt + * goes off when error_count reaches threshold_limit. + */ +static void amd_threshold_interrupt(void) +{ + struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL; + unsigned int bank, cpu = smp_processor_id(); + + for (bank = 0; bank < mca_cfg.banks; ++bank) { + if (!(per_cpu(bank_map, cpu) & (1 << bank))) + continue; + + first_block = per_cpu(threshold_banks, cpu)[bank]->blocks; + if (!first_block) + continue; + + /* + * The first block is also the head of the list. Check it first + * before iterating over the rest. + */ + log_and_reset_block(first_block); + list_for_each_entry_safe(block, tmp, &first_block->miscj, miscj) + log_and_reset_block(block); + } +} + +/* * Sysfs Interface */ @@ -1202,7 +1207,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; per_cpu(threshold_banks, cpu)[bank] = b; - atomic_inc(&b->cpus); + refcount_inc(&b->cpus); err = __threshold_add_blocks(b); @@ -1225,7 +1230,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) per_cpu(threshold_banks, cpu)[bank] = b; if (is_shared_bank(bank)) { - atomic_set(&b->cpus, 1); + refcount_set(&b->cpus, 1); /* nb is already initialized, see above */ if (nb) { @@ -1289,7 +1294,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) goto free_out; if (is_shared_bank(bank)) { - if (!atomic_dec_and_test(&b->cpus)) { + if (!refcount_dec_and_test(&b->cpus)) { __threshold_remove_blocks(b); per_cpu(threshold_banks, cpu)[bank] = NULL; return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 45db4d2ebd01..21b185793c80 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -251,7 +251,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) #endif } -void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; struct cpio_data cp; @@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) } static enum ucode_state -load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size); int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { @@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) if (!desc.mc) return -EINVAL; - ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax), - desc.data, desc.size); + ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size); if (ret != UCODE_OK) return -EINVAL; @@ -675,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, } static enum ucode_state -load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) { enum ucode_state ret; @@ -689,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) #ifdef CONFIG_X86_32 /* save BSP's matching patch for early load */ - if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(cpu); + if (save) { + struct ucode_patch *p = find_patch(0); if (p) { memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), @@ -722,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; /* reload ucode container only on the boot cpu */ - if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + if (!refresh_fw || !bsp) return UCODE_OK; if (c->x86 >= 0x15) @@ -743,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size); + ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index e53d3c909840..9cb98ee103db 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -290,6 +290,17 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) return (struct cpio_data){ NULL, 0, "" }; if (initrd_start) start = initrd_start; + } else { + /* + * The picture with physical addresses is a bit different: we + * need to get the *physical* address to which the ramdisk was + * relocated, i.e., relocated_ramdisk (not initrd_start) and + * since we're running from physical addresses, we need to access + * relocated_ramdisk through its *physical* address too. + */ + u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk); + if (*rr) + start = *rr; } return find_cpio_data(path, (void *)start, size, NULL); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index afdfd237b59f..59edbe9d4ccb 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -42,7 +42,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ -struct microcode_intel *intel_ucode_patch; +static struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, unsigned int s2, unsigned int p2) @@ -166,7 +166,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) static void save_microcode_patch(void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - struct ucode_patch *iter, *tmp, *p; + struct ucode_patch *iter, *tmp, *p = NULL; bool prev_found = false; unsigned int sig, pf; @@ -202,6 +202,18 @@ static void save_microcode_patch(void *data, unsigned int size) else list_add_tail(&p->plist, µcode_cache); } + + /* + * Save for early loading. On 32-bit, that needs to be a physical + * address as the APs are running from physical addresses, before + * paging has been enabled. + */ + if (p) { + if (IS_ENABLED(CONFIG_X86_32)) + intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + else + intel_ucode_patch = p->data; + } } static int microcode_sanity_check(void *mc, int print_err) @@ -607,6 +619,14 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; + /* + * initrd is going away, clear patch ptr. We will scan the microcode one + * last time before jettisoning and save a patch, if found. Then we will + * update that pointer too, with a stable patch address to use when + * resuming the cores. + */ + intel_ucode_patch = NULL; + if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 04cb8d34ccb8..70e717fccdd6 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -161,6 +161,15 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) } #endif +static unsigned long hv_get_tsc_khz(void) +{ + unsigned long freq; + + rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq); + + return freq / 1000; +} + static void __init ms_hyperv_init_platform(void) { int hv_host_info_eax; @@ -193,8 +202,15 @@ static void __init ms_hyperv_init_platform(void) hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF); } + if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { + x86_platform.calibrate_tsc = hv_get_tsc_khz; + x86_platform.calibrate_cpu = hv_get_tsc_khz; + } + #ifdef CONFIG_X86_LOCAL_APIC - if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { + if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { /* * Get the APIC frequency. */ diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 2bce84d91c2b..c5bb63be4ba1 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -807,10 +807,8 @@ void mtrr_save_state(void) 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); - put_online_cpus(); } void set_mtrr_aps_delayed_init(void) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 8e598a1ad986..6b91e2eb8d3f 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -125,7 +125,7 @@ void __init init_espfix_bsp(void) p4d_t *p4d; /* Install the espfix pud into the kernel page directory */ - pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); p4d_populate(&init_mm, p4d, espfix_pud_page); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index c2f8dde3255c..d5d44c452624 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) * Boot time FPU feature detection code: */ unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +EXPORT_SYMBOL_GPL(mxcsr_feature_mask); static void __init fpu__init_system_mxcsr(void) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 0651e974dcb3..9bef1bbeba63 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -689,8 +689,12 @@ static inline void *alloc_tramp(unsigned long size) { return module_alloc(size); } -static inline void tramp_free(void *tramp) +static inline void tramp_free(void *tramp, int size) { + int npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + + set_memory_nx((unsigned long)tramp, npages); + set_memory_rw((unsigned long)tramp, npages); module_memfree(tramp); } #else @@ -699,7 +703,7 @@ static inline void *alloc_tramp(unsigned long size) { return NULL; } -static inline void tramp_free(void *tramp) { } +static inline void tramp_free(void *tramp, int size) { } #endif /* Defined as markers to the end of the ftrace default trampolines */ @@ -771,7 +775,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* Copy ftrace_caller onto the trampoline memory */ ret = probe_kernel_read(trampoline, (void *)start_offset, size); if (WARN_ON(ret < 0)) { - tramp_free(trampoline); + tramp_free(trampoline, *tramp_size); return 0; } @@ -797,7 +801,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* Are we pointing to the reference? */ if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) { - tramp_free(trampoline); + tramp_free(trampoline, *tramp_size); return 0; } @@ -839,7 +843,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops) unsigned long offset; unsigned long ip; unsigned int size; - int ret; + int ret, npages; if (ops->trampoline) { /* @@ -848,11 +852,14 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops) */ if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) return; + npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT; + set_memory_rw(ops->trampoline, npages); } else { ops->trampoline = create_trampoline(ops, &size); if (!ops->trampoline) return; ops->trampoline_size = size; + npages = PAGE_ALIGN(size) >> PAGE_SHIFT; } offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); @@ -863,6 +870,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops) /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); ret = update_ftrace_func(ip, new); + set_memory_ro(ops->trampoline, npages); /* The update should never fail */ WARN_ON(ret); @@ -939,7 +947,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) return; - tramp_free((void *)ops->trampoline); + tramp_free((void *)ops->trampoline, ops->trampoline_size); ops->trampoline = 0; } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 43b7002f44fb..46c3c73e7f43 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -33,17 +33,120 @@ /* * Manage page tables very early on. */ -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; -static unsigned int __initdata next_early_pgt = 2; +static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +#define __head __section(.head.text) + +static void __head *fixup_pointer(void *ptr, unsigned long physaddr) +{ + return ptr - (void *)_text + (void *)physaddr; +} + +void __head __startup_64(unsigned long physaddr) +{ + unsigned long load_delta, *p; + pgdval_t *pgd; + p4dval_t *p4d; + pudval_t *pud; + pmdval_t *pmd, pmd_entry; + int i; + + /* Is the address too large? */ + if (physaddr >> MAX_PHYSMEM_BITS) + for (;;); + + /* + * Compute the delta between the address I am compiled to run at + * and the address I am actually running at. + */ + load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + + /* Is the address not 2M aligned? */ + if (load_delta & ~PMD_PAGE_MASK) + for (;;); + + /* Fixup the physical addresses in the page table */ + + pgd = fixup_pointer(&early_top_pgt, physaddr); + pgd[pgd_index(__START_KERNEL_map)] += load_delta; + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(&level4_kernel_pgt, physaddr); + p4d[511] += load_delta; + } + + pud = fixup_pointer(&level3_kernel_pgt, physaddr); + pud[510] += load_delta; + pud[511] += load_delta; + + pmd = fixup_pointer(level2_fixmap_pgt, physaddr); + pmd[506] += load_delta; + + /* + * Set up the identity mapping for the switchover. These + * entries should *NOT* have the global bit set! This also + * creates a bunch of nonsense entries but that is fine -- + * it avoids problems around wraparound. + */ + + pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + + i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; + p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } else { + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } + + i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; + pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + + pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += physaddr; + + for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { + int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; + pmd[idx] = pmd_entry + i * PMD_SIZE; + } + + /* + * Fixup the kernel text+data virtual addresses. Note that + * we might write invalid pmds, when the kernel is relocated + * cleanup_highmap() fixes this up along with the mappings + * beyond _end. + */ + + pmd = fixup_pointer(level2_kernel_pgt, physaddr); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (pmd[i] & _PAGE_PRESENT) + pmd[i] += load_delta; + } + + /* Fixup phys_base */ + p = fixup_pointer(&phys_base, physaddr); + *p += load_delta; +} + /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { - memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); + memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_level4_pgt)); + write_cr3(__pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ @@ -51,15 +154,16 @@ int __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; + p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; pmdval_t pmd, *pmd_p; /* Invalid address or early pgt is done ? */ - if (physaddr >= MAXMEM || read_cr3() != __pa_nodebug(early_level4_pgt)) + if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) return -1; again: - pgd_p = &early_level4_pgt[pgd_index(address)].pgd; + pgd_p = &early_top_pgt[pgd_index(address)].pgd; pgd = *pgd_p; /* @@ -67,8 +171,25 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (pgd) - pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + p4d_p = pgd_p; + else if (pgd) + p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { + reset_early_page_tables(); + goto again; + } + + p4d_p = (p4dval_t *)early_dynamic_pgts[next_early_pgt++]; + memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); + *pgd_p = (pgdval_t)p4d_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + } + p4d_p += p4d_index(address); + p4d = *p4d_p; + + if (p4d) + pud_p = (pudval_t *)((p4d & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); else { if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { reset_early_page_tables(); @@ -77,7 +198,7 @@ again: pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + *p4d_p = (p4dval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } pud_p += pud_index(address); pud = *pud_p; @@ -156,7 +277,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); - clear_page(init_level4_pgt); + clear_page(init_top_pgt); kasan_early_init(); @@ -171,8 +292,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - /* set init_level4_pgt kernel high mapping*/ - init_level4_pgt[511] = early_level4_pgt[511]; + /* set init_top_pgt kernel high mapping*/ + init_top_pgt[511] = early_top_pgt[511]; x86_64_start_reservations(real_mode_data); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ac9d327d2e42..6225550883df 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -37,10 +37,11 @@ * */ +#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) -L4_START_KERNEL = pgd_index(__START_KERNEL_map) +PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) +PGD_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -72,101 +73,12 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu - /* - * Compute the delta between the address I am compiled to run at and the - * address I am actually running at. - */ - leaq _text(%rip), %rbp - subq $_text - __START_KERNEL_map, %rbp - - /* Is the address not 2M aligned? */ - testl $~PMD_PAGE_MASK, %ebp - jnz bad_address - - /* - * Is the address too large? - */ - leaq _text(%rip), %rax - shrq $MAX_PHYSMEM_BITS, %rax - jnz bad_address - - /* - * Fixup the physical addresses in the page table - */ - addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip) - - addq %rbp, level3_kernel_pgt + (510*8)(%rip) - addq %rbp, level3_kernel_pgt + (511*8)(%rip) - - addq %rbp, level2_fixmap_pgt + (506*8)(%rip) - - /* - * Set up the identity mapping for the switchover. These - * entries should *NOT* have the global bit set! This also - * creates a bunch of nonsense entries but that is fine -- - * it avoids problems around wraparound. - */ leaq _text(%rip), %rdi - leaq early_level4_pgt(%rip), %rbx - - movq %rdi, %rax - shrq $PGDIR_SHIFT, %rax - - leaq (PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx - movq %rdx, 0(%rbx,%rax,8) - movq %rdx, 8(%rbx,%rax,8) - - addq $PAGE_SIZE, %rdx - movq %rdi, %rax - shrq $PUD_SHIFT, %rax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - incl %eax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - - addq $PAGE_SIZE * 2, %rbx - movq %rdi, %rax - shrq $PMD_SHIFT, %rdi - addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax - leaq (_end - 1)(%rip), %rcx - shrq $PMD_SHIFT, %rcx - subq %rdi, %rcx - incl %ecx - -1: - andq $(PTRS_PER_PMD - 1), %rdi - movq %rax, (%rbx,%rdi,8) - incq %rdi - addq $PMD_SIZE, %rax - decl %ecx - jnz 1b - - test %rbp, %rbp - jz .Lskip_fixup + pushq %rsi + call __startup_64 + popq %rsi - /* - * Fixup the kernel text+data virtual addresses. Note that - * we might write invalid pmds, when the kernel is relocated - * cleanup_highmap() fixes this up along with the mappings - * beyond _end. - */ - leaq level2_kernel_pgt(%rip), %rdi - leaq PAGE_SIZE(%rdi), %r8 - /* See if it is a valid page table entry */ -1: testb $_PAGE_PRESENT, 0(%rdi) - jz 2f - addq %rbp, 0(%rdi) - /* Go to the next page */ -2: addq $8, %rdi - cmp %r8, %rdi - jne 1b - - /* Fixup phys_base */ - addq %rbp, phys_base(%rip) - -.Lskip_fixup: - movq $(early_level4_pgt - __START_KERNEL_map), %rax + movq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) /* @@ -186,14 +98,17 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_level4_pgt - __START_KERNEL_map), %rax + movq $(init_top_pgt - __START_KERNEL_map), %rax 1: - /* Enable PAE mode and PGE */ + /* Enable PAE mode, PGE and LA57 */ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx +#ifdef CONFIG_X86_5LEVEL + orl $X86_CR4_LA57, %ecx +#endif movq %rcx, %cr4 - /* Setup early boot stage 4 level pagetables. */ + /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax movq %rax, %cr3 @@ -417,9 +332,13 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_level4_pgt) +NEXT_PAGE(early_top_pgt) .fill 511,8,0 +#ifdef CONFIG_X86_5LEVEL + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#else .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -427,14 +346,14 @@ NEXT_PAGE(early_dynamic_pgts) .data #ifndef CONFIG_XEN -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .fill 512,8,0 #else -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 + .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_START_KERNEL*8, 0 + .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE @@ -448,6 +367,12 @@ NEXT_PAGE(level2_ident_pgt) PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif +#ifdef CONFIG_X86_5LEVEL +NEXT_PAGE(level4_kernel_pgt) + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif + NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 89ff7af2de50..16f82a3aaec7 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -285,7 +285,7 @@ static void hpet_legacy_clockevent_register(void) * Start hpet with the boot cpu mask and make it * global after the IO_APIC has been initialized. */ - hpet_clockevent.cpumask = cpumask_of(smp_processor_id()); + hpet_clockevent.cpumask = cpumask_of(boot_cpu_data.cpu_index); clockevents_config_and_register(&hpet_clockevent, hpet_freq, HPET_MIN_PROG_DELTA, 0x7FFFFFFF); global_clock_event = &hpet_clockevent; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f34fe7444836..4aa03c5a14c9 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -432,84 +432,12 @@ int check_irq_vectors_for_cpu_disable(void) /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { - unsigned int irq, vector; - static int warned; + unsigned int irr, vector; struct irq_desc *desc; struct irq_data *data; struct irq_chip *chip; - int ret; - for_each_irq_desc(irq, desc) { - int break_affinity = 0; - int set_affinity = 1; - const struct cpumask *affinity; - - if (!desc) - continue; - if (irq == 2) - continue; - - /* interrupt's are disabled at this point */ - raw_spin_lock(&desc->lock); - - data = irq_desc_get_irq_data(desc); - affinity = irq_data_get_affinity_mask(data); - if (!irq_has_action(irq) || irqd_is_per_cpu(data) || - cpumask_subset(affinity, cpu_online_mask)) { - raw_spin_unlock(&desc->lock); - continue; - } - - /* - * Complete the irq move. This cpu is going down and for - * non intr-remapping case, we can't wait till this interrupt - * arrives at this cpu before completing the irq move. - */ - irq_force_complete_move(desc); - - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - break_affinity = 1; - affinity = cpu_online_mask; - } - - chip = irq_data_get_irq_chip(data); - /* - * The interrupt descriptor might have been cleaned up - * already, but it is not yet removed from the radix tree - */ - if (!chip) { - raw_spin_unlock(&desc->lock); - continue; - } - - if (!irqd_can_move_in_process_context(data) && chip->irq_mask) - chip->irq_mask(data); - - if (chip->irq_set_affinity) { - ret = chip->irq_set_affinity(data, affinity, true); - if (ret == -ENOSPC) - pr_crit("IRQ %d set affinity failed because there are no available vectors. The device assigned to this IRQ is unstable.\n", irq); - } else { - if (!(warned++)) - set_affinity = 0; - } - - /* - * We unmask if the irq was not marked masked by the - * core code. That respects the lazy irq disable - * behaviour. - */ - if (!irqd_can_move_in_process_context(data) && - !irqd_irq_masked(data) && chip->irq_unmask) - chip->irq_unmask(data); - - raw_spin_unlock(&desc->lock); - - if (break_affinity && set_affinity) - pr_notice("Broke affinity for irq %i\n", irq); - else if (!set_affinity) - pr_notice("Cannot set affinity for irq %i\n", irq); - } + irq_migrate_all_off_this_cpu(); /* * We can remove mdelay() and then send spuriuous interrupts to @@ -528,8 +456,6 @@ void fixup_irqs(void) * nothing else will touch it. */ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - unsigned int irr; - if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector]))) continue; diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index c37bd0f39c70..ab4f491da2a9 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry, void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - get_online_cpus(); mutex_lock(&text_mutex); __jump_label_transform(entry, type, NULL, 0); mutex_unlock(&text_mutex); - put_online_cpus(); } static enum { diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 5b2bbfbb3712..6b877807598b 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -52,6 +52,7 @@ #include <linux/ftrace.h> #include <linux/frame.h> #include <linux/kasan.h> +#include <linux/moduleloader.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -417,6 +418,14 @@ static void prepare_boost(struct kprobe *p, struct insn *insn) } } +/* Recover page to RW mode before releasing it */ +void free_insn_page(void *page) +{ + set_memory_nx((unsigned long)page & PAGE_MASK, 1); + set_memory_rw((unsigned long)page & PAGE_MASK, 1); + module_memfree(page); +} + static int arch_copy_kprobe(struct kprobe *p) { struct insn insn; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 901c640d152f..69ea0bc1cfa3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -28,6 +28,7 @@ #include <linux/kdebug.h> #include <linux/kallsyms.h> #include <linux/ftrace.h> +#include <linux/frame.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -94,6 +95,7 @@ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) } asm ( + "optprobe_template_func:\n" ".global optprobe_template_entry\n" "optprobe_template_entry:\n" #ifdef CONFIG_X86_64 @@ -131,7 +133,12 @@ asm ( " popf\n" #endif ".global optprobe_template_end\n" - "optprobe_template_end:\n"); + "optprobe_template_end:\n" + ".type optprobe_template_func, @function\n" + ".size optprobe_template_func, .-optprobe_template_func\n"); + +void optprobe_template_func(void); +STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_MOVE_IDX \ ((long)&optprobe_template_val - (long)&optprobe_template_entry) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index da5c09789984..43e10d6fdbed 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token) */ rcu_irq_exit(); native_safe_halt(); - rcu_irq_enter(); local_irq_disable(); + rcu_irq_enter(); } } if (!n.halted) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d4a15831ac58..a870910c8565 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -22,24 +22,25 @@ #include <asm/syscalls.h> /* context.lock is held for us, so we don't need any locking. */ -static void flush_ldt(void *current_mm) +static void flush_ldt(void *__mm) { + struct mm_struct *mm = __mm; mm_context_t *pc; - if (current->active_mm != current_mm) + if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; - pc = ¤t->active_mm->context; - set_ldt(pc->ldt->entries, pc->ldt->size); + pc = &mm->context; + set_ldt(pc->ldt->entries, pc->ldt->nr_entries); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ -static struct ldt_struct *alloc_ldt_struct(unsigned int size) +static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) { struct ldt_struct *new_ldt; unsigned int alloc_size; - if (size > LDT_ENTRIES) + if (num_entries > LDT_ENTRIES) return NULL; new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); @@ -47,7 +48,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); - alloc_size = size * LDT_ENTRY_SIZE; + alloc_size = num_entries * LDT_ENTRY_SIZE; /* * Xen is very picky: it requires a page-aligned LDT that has no @@ -65,14 +66,14 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; } - new_ldt->size = size; + new_ldt->nr_entries = num_entries; return new_ldt; } /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { - paravirt_alloc_ldt(ldt->entries, ldt->size); + paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } /* context.lock is held */ @@ -91,8 +92,8 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (likely(!ldt)) return; - paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + paravirt_free_ldt(ldt->entries, ldt->nr_entries); + if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE) vfree_atomic(ldt->entries); else free_page((unsigned long)ldt->entries); @@ -122,14 +123,14 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) goto out_unlock; } - new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { retval = -ENOMEM; goto out_unlock; } memcpy(new_ldt->entries, old_mm->context.ldt->entries, - new_ldt->size * LDT_ENTRY_SIZE); + new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); mm->context.ldt = new_ldt; @@ -152,9 +153,9 @@ void destroy_context_ldt(struct mm_struct *mm) static int read_ldt(void __user *ptr, unsigned long bytecount) { - int retval; - unsigned long size; struct mm_struct *mm = current->mm; + unsigned long entries_size; + int retval; mutex_lock(&mm->context.lock); @@ -166,18 +167,18 @@ static int read_ldt(void __user *ptr, unsigned long bytecount) if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - size = mm->context.ldt->size * LDT_ENTRY_SIZE; - if (size > bytecount) - size = bytecount; + entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE; + if (entries_size > bytecount) + entries_size = bytecount; - if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) { retval = -EFAULT; goto out_unlock; } - if (size != bytecount) { + if (entries_size != bytecount) { /* Zero-fill the rest and pretend we read bytecount bytes. */ - if (clear_user(ptr + size, bytecount - size)) { + if (clear_user(ptr + entries_size, bytecount - entries_size)) { retval = -EFAULT; goto out_unlock; } @@ -208,7 +209,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; struct ldt_struct *new_ldt, *old_ldt; - unsigned int oldsize, newsize; + unsigned int old_nr_entries, new_nr_entries; struct user_desc ldt_info; struct desc_struct ldt; int error; @@ -247,17 +248,18 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) mutex_lock(&mm->context.lock); - old_ldt = mm->context.ldt; - oldsize = old_ldt ? old_ldt->size : 0; - newsize = max(ldt_info.entry_number + 1, oldsize); + old_ldt = mm->context.ldt; + old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; + new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries); error = -ENOMEM; - new_ldt = alloc_ldt_struct(newsize); + new_ldt = alloc_ldt_struct(new_nr_entries); if (!new_ldt) goto out_unlock; if (old_ldt) - memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6f5ca4ebe6e5..cb0a30473c23 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -347,7 +347,7 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_level4_pgt); + VMCOREINFO_SYMBOL(init_top_pgt); #ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index 6d9582ec0324..d27f8d84c4ff 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -78,7 +78,7 @@ static void __init test_nmi_ipi(struct cpumask *mask) /* Don't wait longer than a second */ timeout = USEC_PER_SEC; - while (!cpumask_empty(mask) && timeout--) + while (!cpumask_empty(mask) && --timeout) udelay(1); /* What happens if we timeout, do we still unregister?? */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 3586996fc50d..bc0a849589bb 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -391,7 +391,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, - .read_cr3 = native_read_cr3, + .read_cr3 = __native_read_cr3, .write_cr3 = native_write_cr3, .flush_tlb_user = native_flush_tlb, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 0bb88428cbf2..3ca198080ea9 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -545,17 +545,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } /* - * Return saved PC of a blocked thread. - * What is this good for? it will be always the scheduler or ret_from_fork. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct inactive_task_frame *frame = - (struct inactive_task_frame *) READ_ONCE(tsk->thread.sp); - return READ_ONCE_NOCHECK(frame->ret_addr); -} - -/* * Called from fs/proc with a reference on @p to find the function * which called into schedule(). This needs to be done carefully * because the task might wake up and we might look at a stack diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ff40e74c9181..c6d6dc5f8bb2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip); printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags, - smp_processor_id()); + raw_smp_processor_id()); printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); @@ -92,7 +92,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b6840bf3940b..c3169be4c596 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -104,7 +104,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", @@ -142,7 +142,7 @@ void release_thread(struct task_struct *dead_task) pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt->entries, - dead_task->mm->context.ldt->size); + dead_task->mm->context.ldt->nr_entries); BUG(); } #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2544700a2a87..67393fc88353 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/tboot.h> #include <linux/delay.h> +#include <linux/frame.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -123,6 +124,7 @@ void __noreturn machine_real_restart(unsigned int type) #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(machine_real_restart); #endif +STACK_FRAME_NON_STANDARD(machine_real_restart); /* * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0b4d3c686b1e..65622f07e633 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -503,7 +503,7 @@ static int __init reserve_crashkernel_low(void) return 0; } - low_base = memblock_find_in_range(low_size, 1ULL << 32, low_size, CRASH_ALIGN); + low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN); if (!low_base) { pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n", (unsigned long)(low_size >> 20)); @@ -980,8 +980,6 @@ void __init setup_arch(char **cmdline_p) */ x86_configure_nx(); - simple_udelay_calibration(); - parse_early_param(); #ifdef CONFIG_MEMORY_HOTPLUG @@ -1041,6 +1039,8 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor_platform(); + simple_udelay_calibration(); + x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f04479a8f74f..b474c8de7fba 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -863,7 +863,7 @@ static void announce_cpu(int cpu, int apicid) if (cpu == 1) printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state == SYSTEM_BOOTING) { + if (system_state < SYSTEM_RUNNING) { if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); @@ -1589,7 +1589,6 @@ void native_cpu_die(unsigned int cpu) void play_dead_common(void) { idle_task_exit(); - reset_lazy_tlbstate(); /* Ack it */ (void)cpu_report_death(); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index f07f83b3611b..5f25cfbd952e 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -34,7 +34,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re mutex_lock(&child->mm->context.lock); if (unlikely(!child->mm->context.ldt || - seg >= child->mm->context.ldt->size)) + seg >= child->mm->context.ldt->nr_entries)) addr = -1L; /* bogus selector, access would fault */ else { desc = &child->mm->context.ldt->entries[seg]; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 207b8f2582c7..213ddf3e937d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (end - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -187,7 +187,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 4b1724059909..a4eb27918ceb 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,7 +514,7 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (!intel_iommu_tboot_noforce) + if (intel_iommu_tboot_noforce) return 1; if (no_iommu || swiotlb || dmar_disabled) diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index d39c09119db6..e0754cdbad37 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -66,7 +66,7 @@ static struct irqaction irq0 = { .name = "timer" }; -void __init setup_default_timer_irq(void) +static void __init setup_default_timer_irq(void) { if (!nr_legacy_irqs()) return; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 3995d3a777d4..bf54309b85da 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -182,7 +182,7 @@ int is_valid_bugaddr(unsigned long addr) return ud == INSN_UD0 || ud == INSN_UD2; } -static int fixup_bug(struct pt_regs *regs, int trapnr) +int fixup_bug(struct pt_regs *regs, int trapnr) { if (trapnr != X86_TRAP_UD) return 0; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 714dfba6a1e7..796d96bb0821 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -51,115 +51,34 @@ static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; struct clocksource *art_related_clocksource; -/* - * Use a ring-buffer like data structure, where a writer advances the head by - * writing a new data entry and a reader advances the tail when it observes a - * new entry. - * - * Writers are made to wait on readers until there's space to write a new - * entry. - * - * This means that we can always use an {offset, mul} pair to compute a ns - * value that is 'roughly' in the right direction, even if we're writing a new - * {offset, mul} pair during the clock read. - * - * The down-side is that we can no longer guarantee strict monotonicity anymore - * (assuming the TSC was that to begin with), because while we compute the - * intersection point of the two clock slopes and make sure the time is - * continuous at the point of switching; we can no longer guarantee a reader is - * strictly before or after the switch point. - * - * It does mean a reader no longer needs to disable IRQs in order to avoid - * CPU-Freq updates messing with his times, and similarly an NMI reader will - * no longer run the risk of hitting half-written state. - */ - struct cyc2ns { - struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */ - struct cyc2ns_data *head; /* 48 + 8 = 56 */ - struct cyc2ns_data *tail; /* 56 + 8 = 64 */ -}; /* exactly fits one cacheline */ - -static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); - -struct cyc2ns_data *cyc2ns_read_begin(void) -{ - struct cyc2ns_data *head; - - preempt_disable(); + struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ + seqcount_t seq; /* 32 + 4 = 36 */ - head = this_cpu_read(cyc2ns.head); - /* - * Ensure we observe the entry when we observe the pointer to it. - * matches the wmb from cyc2ns_write_end(). - */ - smp_read_barrier_depends(); - head->__count++; - barrier(); - - return head; -} +}; /* fits one cacheline */ -void cyc2ns_read_end(struct cyc2ns_data *head) -{ - barrier(); - /* - * If we're the outer most nested read; update the tail pointer - * when we're done. This notifies possible pending writers - * that we've observed the head pointer and that the other - * entry is now free. - */ - if (!--head->__count) { - /* - * x86-TSO does not reorder writes with older reads; - * therefore once this write becomes visible to another - * cpu, we must be finished reading the cyc2ns_data. - * - * matches with cyc2ns_write_begin(). - */ - this_cpu_write(cyc2ns.tail, head); - } - preempt_enable(); -} +static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); -/* - * Begin writing a new @data entry for @cpu. - * - * Assumes some sort of write side lock; currently 'provided' by the assumption - * that cpufreq will call its notifiers sequentially. - */ -static struct cyc2ns_data *cyc2ns_write_begin(int cpu) +void cyc2ns_read_begin(struct cyc2ns_data *data) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - struct cyc2ns_data *data = c2n->data; + int seq, idx; - if (data == c2n->head) - data++; + preempt_disable_notrace(); - /* XXX send an IPI to @cpu in order to guarantee a read? */ + do { + seq = this_cpu_read(cyc2ns.seq.sequence); + idx = seq & 1; - /* - * When we observe the tail write from cyc2ns_read_end(), - * the cpu must be done with that entry and its safe - * to start writing to it. - */ - while (c2n->tail == data) - cpu_relax(); + data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); + data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); + data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); - return data; + } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); } -static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) +void cyc2ns_read_end(void) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - - /* - * Ensure the @data writes are visible before we publish the - * entry. Matches the data-depencency in cyc2ns_read_begin(). - */ - smp_wmb(); - - ACCESS_ONCE(c2n->head) = data; + preempt_enable_notrace(); } /* @@ -191,7 +110,6 @@ static void cyc2ns_data_init(struct cyc2ns_data *data) data->cyc2ns_mul = 0; data->cyc2ns_shift = 0; data->cyc2ns_offset = 0; - data->__count = 0; } static void cyc2ns_init(int cpu) @@ -201,51 +119,29 @@ static void cyc2ns_init(int cpu) cyc2ns_data_init(&c2n->data[0]); cyc2ns_data_init(&c2n->data[1]); - c2n->head = c2n->data; - c2n->tail = c2n->data; + seqcount_init(&c2n->seq); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data, *tail; + struct cyc2ns_data data; unsigned long long ns; - /* - * See cyc2ns_read_*() for details; replicated in order to avoid - * an extra few instructions that came with the abstraction. - * Notable, it allows us to only do the __count and tail update - * dance when its actually needed. - */ - - preempt_disable_notrace(); - data = this_cpu_read(cyc2ns.head); - tail = this_cpu_read(cyc2ns.tail); - - if (likely(data == tail)) { - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); - } else { - data->__count++; - - barrier(); + cyc2ns_read_begin(&data); - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + ns = data.cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); - barrier(); - - if (!--data->__count) - this_cpu_write(cyc2ns.tail, data); - } - preempt_enable_notrace(); + cyc2ns_read_end(); return ns; } -static void set_cyc2ns_scale(unsigned long khz, int cpu) +static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { - unsigned long long tsc_now, ns_now; - struct cyc2ns_data *data; + unsigned long long ns_now; + struct cyc2ns_data data; + struct cyc2ns *c2n; unsigned long flags; local_irq_save(flags); @@ -254,9 +150,6 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) if (!khz) goto done; - data = cyc2ns_write_begin(cpu); - - tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -264,7 +157,7 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, khz, + clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* @@ -273,20 +166,26 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ - if (data->cyc2ns_shift == 32) { - data->cyc2ns_shift = 31; - data->cyc2ns_mul >>= 1; + if (data.cyc2ns_shift == 32) { + data.cyc2ns_shift = 31; + data.cyc2ns_mul >>= 1; } - data->cyc2ns_offset = ns_now - - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); + data.cyc2ns_offset = ns_now - + mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); - cyc2ns_write_end(cpu, data); + c2n = per_cpu_ptr(&cyc2ns, cpu); + + raw_write_seqcount_latch(&c2n->seq); + c2n->data[0] = data; + raw_write_seqcount_latch(&c2n->seq); + c2n->data[1] = data; done: - sched_clock_idle_wakeup_event(0); + sched_clock_idle_wakeup_event(); local_irq_restore(flags); } + /* * Scheduler clock - returns current time in nanosec units. */ @@ -374,6 +273,8 @@ static int __init tsc_setup(char *str) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; + if (!strcmp(str, "unstable")) + mark_tsc_unstable("boot parameter"); return 1; } @@ -986,7 +887,6 @@ void tsc_restore_sched_clock_state(void) } #ifdef CONFIG_CPU_FREQ - /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency * changes. * @@ -1027,7 +927,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); - set_cyc2ns_scale(tsc_khz, freq->cpu); + set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc()); } return 0; @@ -1127,6 +1027,15 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) pr_info("Marking TSC unstable due to clocksource watchdog\n"); } +static void tsc_cs_tick_stable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + + if (using_native_sched_clock()) + sched_clock_tick_stable(); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1140,6 +1049,7 @@ static struct clocksource clocksource_tsc = { .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, + .tick_stable = tsc_cs_tick_stable, }; void mark_tsc_unstable(char *reason) @@ -1255,6 +1165,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; + int cpu; /* Don't bother refining TSC on unstable systems */ if (check_tsc_unstable()) @@ -1305,6 +1216,10 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); + /* Update the sched_clock() rate to match the clocksource one */ + for_each_possible_cpu(cpu) + set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; @@ -1350,7 +1265,7 @@ device_initcall(init_tsc_clocksource); void __init tsc_init(void) { - u64 lpj; + u64 lpj, cyc; int cpu; if (!boot_cpu_has(X86_FEATURE_TSC)) { @@ -1390,9 +1305,10 @@ void __init tsc_init(void) * speed as the bootup CPU. (cpufreq notifiers will fix this * up if their speed diverges) */ + cyc = rdtsc(); for_each_possible_cpu(cpu) { cyc2ns_init(cpu); - set_cyc2ns_scale(tsc_khz, cpu); + set_cyc2ns_scale(tsc_khz, cpu, cyc); } if (tsc_disabled > 0) @@ -1412,11 +1328,11 @@ void __init tsc_init(void) use_tsc_delay(); + check_system_tsc_reliable(); + if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - check_system_tsc_reliable(); - detect_art(); } diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 728f75378475..7842371bc9e4 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -71,13 +71,8 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, * non zero. We don't do that on non boot cpus because physical * hotplug should have set the ADJUST register to a value > 0 so * the TSC is in sync with the already running cpus. - * - * But we always force positive ADJUST values. Otherwise the TSC - * deadline timer creates an interrupt storm. We also have to - * prevent values > 0x7FFFFFFF as those wreckage the timer as well. */ - if ((bootcpu && bootval != 0) || (!bootcpu && bootval < 0) || - (bootval > 0x7FFFFFFF)) { + if (bootcpu && bootval != 0) { pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", cpu, bootval); wrmsrl(MSR_IA32_TSC_ADJUST, 0); @@ -451,20 +446,6 @@ retry: */ cur->adjusted += cur_max_warp; - /* - * TSC deadline timer stops working or creates an interrupt storm - * with adjust values < 0 and > x07ffffff. - * - * To allow adjust values > 0x7FFFFFFF we need to disable the - * deadline timer and use the local APIC timer, but that requires - * more intrusive changes and we do not have any useful information - * from Intel about the underlying HW wreckage yet. - */ - if (cur->adjusted < 0) - cur->adjusted = 0; - if (cur->adjusted > 0x7FFFFFFF) - cur->adjusted = 0x7FFFFFFF; - pr_warn("TSC ADJUST compensate: CPU%u observed %lld warp. Adjust: %lld\n", cpu, cur_max_warp, cur->adjusted); diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 82c6d7f1fd73..b9389d72b2f7 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -104,6 +104,11 @@ static inline unsigned long *last_frame(struct unwind_state *state) return (unsigned long *)task_pt_regs(state->task) - 2; } +static bool is_last_frame(struct unwind_state *state) +{ + return state->bp == last_frame(state); +} + #ifdef CONFIG_X86_32 #define GCC_REALIGN_WORDS 3 #else @@ -115,16 +120,15 @@ static inline unsigned long *last_aligned_frame(struct unwind_state *state) return last_frame(state) - GCC_REALIGN_WORDS; } -static bool is_last_task_frame(struct unwind_state *state) +static bool is_last_aligned_frame(struct unwind_state *state) { unsigned long *last_bp = last_frame(state); unsigned long *aligned_bp = last_aligned_frame(state); /* - * We have to check for the last task frame at two different locations - * because gcc can occasionally decide to realign the stack pointer and - * change the offset of the stack frame in the prologue of a function - * called by head/entry code. Examples: + * GCC can occasionally decide to realign the stack pointer and change + * the offset of the stack frame in the prologue of a function called + * by head/entry code. Examples: * * <start_secondary>: * push %edi @@ -141,11 +145,38 @@ static bool is_last_task_frame(struct unwind_state *state) * push %rbp * mov %rsp,%rbp * - * Note that after aligning the stack, it pushes a duplicate copy of - * the return address before pushing the frame pointer. + * After aligning the stack, it pushes a duplicate copy of the return + * address before pushing the frame pointer. + */ + return (state->bp == aligned_bp && *(aligned_bp + 1) == *(last_bp + 1)); +} + +static bool is_last_ftrace_frame(struct unwind_state *state) +{ + unsigned long *last_bp = last_frame(state); + unsigned long *last_ftrace_bp = last_bp - 3; + + /* + * When unwinding from an ftrace handler of a function called by entry + * code, the stack layout of the last frame is: + * + * bp + * parent ret addr + * bp + * function ret addr + * parent ret addr + * pt_regs + * ----------------- */ - return (state->bp == last_bp || - (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1))); + return (state->bp == last_ftrace_bp && + *state->bp == *(state->bp + 2) && + *(state->bp + 1) == *(state->bp + 4)); +} + +static bool is_last_task_frame(struct unwind_state *state) +{ + return is_last_frame(state) || is_last_aligned_frame(state) || + is_last_ftrace_frame(state); } /* |