diff options
Diffstat (limited to 'arch/x86/kernel')
69 files changed, 1213 insertions, 529 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 17b33ef604f3..ea019ba02942 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1740,7 +1740,7 @@ int __acpi_acquire_global_lock(unsigned int *lock) new = (((old & ~0x3) + 2) + ((old >> 1) & 0x1)); val = cmpxchg(lock, old, new); } while (unlikely (val != old)); - return (new < 3) ? -1 : 0; + return ((new & 0x3) < 3) ? -1 : 0; } int __acpi_release_global_lock(unsigned int *lock) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index a5e5484988fd..a5d650a15d55 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -146,7 +146,8 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, /* Make sure we are running on right CPU */ - retval = work_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx); + retval = call_on_cpu(cpu, acpi_processor_ffh_cstate_probe_cpu, cx, + false); if (retval == 0) { /* Use the hint in CST */ percpu_entry->states[cx->index].eax = cx->address; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 390596b761e3..16f36f60a394 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -615,11 +615,98 @@ extern struct paravirt_patch_site __start_parainstructions[], __stop_parainstructions[]; #endif /* CONFIG_PARAVIRT */ +/* + * Self-test for the INT3 based CALL emulation code. + * + * This exercises int3_emulate_call() to make sure INT3 pt_regs are set up + * properly and that there is a stack gap between the INT3 frame and the + * previous context. Without this gap doing a virtual PUSH on the interrupted + * stack would corrupt the INT3 IRET frame. + * + * See entry_{32,64}.S for more details. + */ + +/* + * We define the int3_magic() function in assembly to control the calling + * convention such that we can 'call' it from assembly. + */ + +extern void int3_magic(unsigned int *ptr); /* defined in asm */ + +asm ( +" .pushsection .init.text, \"ax\", @progbits\n" +" .type int3_magic, @function\n" +"int3_magic:\n" +" movl $1, (%" _ASM_ARG1 ")\n" +" ret\n" +" .size int3_magic, .-int3_magic\n" +" .popsection\n" +); + +extern __initdata unsigned long int3_selftest_ip; /* defined in asm below */ + +static int __init +int3_exception_notify(struct notifier_block *self, unsigned long val, void *data) +{ + struct die_args *args = data; + struct pt_regs *regs = args->regs; + + if (!regs || user_mode(regs)) + return NOTIFY_DONE; + + if (val != DIE_INT3) + return NOTIFY_DONE; + + if (regs->ip - INT3_INSN_SIZE != int3_selftest_ip) + return NOTIFY_DONE; + + int3_emulate_call(regs, (unsigned long)&int3_magic); + return NOTIFY_STOP; +} + +static void __init int3_selftest(void) +{ + static __initdata struct notifier_block int3_exception_nb = { + .notifier_call = int3_exception_notify, + .priority = INT_MAX-1, /* last */ + }; + unsigned int val = 0; + + BUG_ON(register_die_notifier(&int3_exception_nb)); + + /* + * Basically: int3_magic(&val); but really complicated :-) + * + * Stick the address of the INT3 instruction into int3_selftest_ip, + * then trigger the INT3, padded with NOPs to match a CALL instruction + * length. + */ + asm volatile ("1: int3; nop; nop; nop; nop\n\t" + ".pushsection .init.data,\"aw\"\n\t" + ".align " __ASM_SEL(4, 8) "\n\t" + ".type int3_selftest_ip, @object\n\t" + ".size int3_selftest_ip, " __ASM_SEL(4, 8) "\n\t" + "int3_selftest_ip:\n\t" + __ASM_SEL(.long, .quad) " 1b\n\t" + ".popsection\n\t" + : ASM_CALL_CONSTRAINT + : __ASM_SEL_RAW(a, D) (&val) + : "memory"); + + BUG_ON(val != 1); + + unregister_die_notifier(&int3_exception_nb); +} + void __init alternative_instructions(void) { - /* The patching is not fully atomic, so try to avoid local interruptions - that might execute the to be patched code. - Other CPUs are not running. */ + int3_selftest(); + + /* + * The patching is not fully atomic, so try to avoid local + * interruptions that might execute the to be patched code. + * Other CPUs are not running. + */ stop_nmi(); /* @@ -644,10 +731,11 @@ void __init alternative_instructions(void) _text, _etext); } - if (!uniproc_patched || num_possible_cpus() == 1) + if (!uniproc_patched || num_possible_cpus() == 1) { free_init_pages("SMP alternatives", (unsigned long)__smp_locks, (unsigned long)__smp_locks_end); + } #endif apply_paravirt(__parainstructions, __parainstructions_end); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 8c26b696d893..8e283685f471 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -18,10 +18,13 @@ #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 +#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 +#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -32,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, {} }; @@ -50,8 +54,10 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -65,7 +71,9 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a18d6dd934e5..8dadfd73c5ad 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -195,7 +195,7 @@ static struct resource lapic_resource = { .flags = IORESOURCE_MEM | IORESOURCE_BUSY, }; -unsigned int lapic_timer_frequency = 0; +unsigned int lapic_timer_period = 0; static void apic_pm_activate(void); @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -501,7 +499,7 @@ lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot) if (evt->features & CLOCK_EVT_FEAT_DUMMY) return 0; - __setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1); + __setup_APIC_LVTT(lapic_timer_period, oneshot, 1); return 0; } @@ -552,7 +550,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); #define DEADLINE_MODEL_MATCH_REV(model, rev) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -562,7 +560,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -574,7 +572,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -587,7 +585,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { 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), @@ -609,18 +607,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -632,11 +631,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; 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); + return false; } /* @@ -805,11 +805,11 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init lapic_init_clockevent(void) { - if (!lapic_timer_frequency) + if (!lapic_timer_period) return -1; /* Calculate the scaled math multiplication factor */ - lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR, + lapic_clockevent.mult = div_sc(lapic_timer_period/APIC_DIVISOR, TICK_NSEC, lapic_clockevent.shift); lapic_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent); @@ -840,7 +840,7 @@ static int __init calibrate_APIC_clock(void) */ if (!lapic_init_clockevent()) { apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n", - lapic_timer_frequency); + lapic_timer_period); /* * Direct calibration methods must have an always running * local APIC timer, no need for broadcast timer. @@ -921,13 +921,13 @@ static int __init calibrate_APIC_clock(void) pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1, &delta, &deltatsc); - lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; + lapic_timer_period = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; lapic_init_clockevent(); apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", - lapic_timer_frequency); + lapic_timer_period); if (boot_cpu_has(X86_FEATURE_TSC)) { apic_printk(APIC_VERBOSE, "..... CPU clock speed is " @@ -938,13 +938,13 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "..... host bus clock speed is " "%u.%04u MHz.\n", - lapic_timer_frequency / (1000000 / HZ), - lapic_timer_frequency % (1000000 / HZ)); + lapic_timer_period / (1000000 / HZ), + lapic_timer_period % (1000000 / HZ)); /* * Do a sanity check on the APIC calibration result */ - if (lapic_timer_frequency < (1000000 / HZ)) { + if (lapic_timer_period < (1000000 / HZ)) { local_irq_enable(); pr_warning("APIC frequency too slow, disabling apic timer\n"); return -1; @@ -1540,9 +1540,6 @@ static void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value; -#ifdef CONFIG_X86_32 - int logical_apicid, ldr_apicid; -#endif if (disable_apic) { @@ -1583,16 +1580,21 @@ static void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* @@ -2035,7 +2037,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_info("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index e8c6466ef65e..70718977ce7a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1726,9 +1726,10 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data) static inline bool ioapic_irqd_mask(struct irq_data *data) { - /* If we are moving the irq we need to mask it */ + /* If we are moving the IRQ we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data))) { - mask_ioapic_irq(data); + if (!irqd_irq_masked(data)) + mask_ioapic_irq(data); return true; } return false; @@ -1765,7 +1766,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) */ if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic_irq(data); + /* If the IRQ is masked in the core, leave it: */ + if (!irqd_irq_masked(data)) + unmask_ioapic_irq(data); } } #else diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index dad0dd759de2..e0c3c57ed7c0 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -23,10 +23,8 @@ static struct irq_domain *msi_default_domain; -static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) @@ -47,6 +45,127 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) MSI_DATA_VECTOR(cfg->vector); } +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + __irq_msi_compose_msg(irqd_cfg(data), msg); +} + +static void irq_msi_update_msg(struct irq_data *irqd, struct irq_cfg *cfg) +{ + struct msi_msg msg[2] = { [1] = { }, }; + + __irq_msi_compose_msg(cfg, msg); + irq_data_get_irq_chip(irqd)->irq_write_msi_msg(irqd, msg); +} + +static int +msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) +{ + struct irq_cfg old_cfg, *cfg = irqd_cfg(irqd); + struct irq_data *parent = irqd->parent_data; + unsigned int cpu; + int ret; + + /* Save the current configuration */ + cpu = cpumask_first(irq_data_get_effective_affinity_mask(irqd)); + old_cfg = *cfg; + + /* Allocate a new target vector */ + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE) + return ret; + + /* + * For non-maskable and non-remapped MSI interrupts the migration + * to a different destination CPU and a different vector has to be + * done careful to handle the possible stray interrupt which can be + * caused by the non-atomic update of the address/data pair. + * + * Direct update is possible when: + * - The MSI is maskable (remapped MSI does not use this code path)). + * The quirk bit is not set in this case. + * - The new vector is the same as the old vector + * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The new destination CPU is the same as the old destination CPU + */ + if (!irqd_msi_nomask_quirk(irqd) || + cfg->vector == old_cfg.vector || + old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + cfg->dest_apicid == old_cfg.dest_apicid) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Paranoia: Validate that the interrupt target is the local + * CPU. + */ + if (WARN_ON_ONCE(cpu != smp_processor_id())) { + irq_msi_update_msg(irqd, cfg); + return ret; + } + + /* + * Redirect the interrupt to the new vector on the current CPU + * first. This might cause a spurious interrupt on this vector if + * the device raises an interrupt right between this update and the + * update to the final destination CPU. + * + * If the vector is in use then the installed device handler will + * denote it as spurious which is no harm as this is a rare event + * and interrupt handlers have to cope with spurious interrupts + * anyway. If the vector is unused, then it is marked so it won't + * trigger the 'No irq handler for vector' warning in do_IRQ(). + * + * This requires to hold vector lock to prevent concurrent updates to + * the affected vector. + */ + lock_vector_lock(); + + /* + * Mark the new target vector on the local CPU if it is currently + * unused. Reuse the VECTOR_RETRIGGERED state which is also used in + * the CPU hotplug path for a similar purpose. This cannot be + * undone here as the current CPU has interrupts disabled and + * cannot handle the interrupt before the whole set_affinity() + * section is done. In the CPU unplug case, the current CPU is + * about to vanish and will not handle any interrupts anymore. The + * vector is cleaned up when the CPU comes online again. + */ + if (IS_ERR_OR_NULL(this_cpu_read(vector_irq[cfg->vector]))) + this_cpu_write(vector_irq[cfg->vector], VECTOR_RETRIGGERED); + + /* Redirect it to the new vector on the local CPU temporarily */ + old_cfg.vector = cfg->vector; + irq_msi_update_msg(irqd, &old_cfg); + + /* Now transition it to the target CPU */ + irq_msi_update_msg(irqd, cfg); + + /* + * All interrupts after this point are now targeted at the new + * vector/CPU. + * + * Drop vector lock before testing whether the temporary assignment + * to the local CPU was hit by an interrupt raised in the device, + * because the retrigger function acquires vector lock again. + */ + unlock_vector_lock(); + + /* + * Check whether the transition raced with a device interrupt and + * is pending in the local APICs IRR. It is safe to do this outside + * of vector lock as the irq_desc::lock of this interrupt is still + * held and interrupts are disabled: The check is not accessing the + * underlying vector store. It's just checking the local APIC's + * IRR. + */ + if (lapic_vector_set_in_irr(cfg->vector)) + irq_data_get_irq_chip(irqd)->irq_retrigger(irqd); + + return ret; +} + /* * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, * which implement the MSI or MSI-X Capability Structure. @@ -58,6 +177,7 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_set_affinity = msi_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -146,6 +266,8 @@ void __init arch_init_msi_domain(struct irq_domain *parent) } if (!msi_default_domain) pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); + else + msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; } #ifdef CONFIG_IRQ_REMAP diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 2c5676b0a6e7..259d17d08983 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, trace_vector_activate(irqd->irq, apicd->is_managed, apicd->can_reserve, reserve); - /* Nothing to do for fixed assigned vectors */ - if (!apicd->can_reserve && !apicd->is_managed) - return 0; - raw_spin_lock_irqsave(&vector_lock, flags); - if (reserve || irqd_is_managed_and_shutdown(irqd)) + if (!apicd->can_reserve && !apicd->is_managed) + assign_irq_vector_any_locked(irqd); + else if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -557,6 +555,16 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irqd->hwirq = virq + i; irqd_set_single_target(irqd); /* + * Prevent that any of these interrupts is invoked in + * non interrupt context via e.g. generic_handle_irq() + * as that can corrupt the affinity move state. + */ + irqd_set_handle_enforce_irqctx(irqd); + + /* Don't invoke affinity setter on deactivated interrupts */ + irqd_set_affinity_on_activate(irqd); + + /* * Legacy vectors are already assigned when the IOAPIC * takes them over. They stay on the same vector. This is * required for check_timer() to work correctly as it might @@ -769,20 +777,10 @@ void lapic_offline(void) static int apic_set_affinity(struct irq_data *irqd, const struct cpumask *dest, bool force) { - struct apic_chip_data *apicd = apic_chip_data(irqd); int err; - /* - * Core code can call here for inactive interrupts. For inactive - * interrupts which use managed or reservation mode there is no - * point in going through the vector assignment right now as the - * activation will assign a vector which fits the destination - * cpumask. Let the core code store the destination mask and be - * done with it. - */ - if (!irqd_is_activated(irqd) && - (apicd->is_managed || apicd->can_reserve)) - return IRQ_SET_MASK_OK; + if (WARN_ON_ONCE(!irqd_is_activated(irqd))) + return -EIO; raw_spin_lock(&vector_lock); cpumask_and(vector_searchmask, dest, cpu_online_mask); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 168543d077d7..5c7ee3df4d0b 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -38,7 +38,6 @@ static void __used common(void) #endif BLANK(); - OFFSET(TASK_TI_flags, task_struct, thread_info.flags); OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); BLANK(); @@ -77,6 +76,7 @@ static void __used common(void) BLANK(); OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask); OFFSET(XEN_vcpu_info_pending, vcpu_info, evtchn_upcall_pending); + OFFSET(XEN_vcpu_info_arch_cr2, vcpu_info, arch.cr2); #endif BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d3d075226c0a..70e97727a26a 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -6,13 +6,28 @@ #include <asm/ia32.h> #define __SYSCALL_64(nr, sym, qual) [nr] = 1, +#define __SYSCALL_X32(nr, sym, qual) static char syscalls_64[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL_64 +#undef __SYSCALL_X32 + +#ifdef CONFIG_X86_X32_ABI +#define __SYSCALL_64(nr, sym, qual) +#define __SYSCALL_X32(nr, sym, qual) [nr] = 1, +static char syscalls_x32[] = { +#include <asm/syscalls_64.h> +}; +#undef __SYSCALL_64 +#undef __SYSCALL_X32 +#endif + #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls_ia32[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL_I386 #if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) #include <asm/kvm_para.h> @@ -80,6 +95,11 @@ int main(void) DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); +#ifdef CONFIG_X86_X32_ABI + DEFINE(__NR_syscall_x32_max, sizeof(syscalls_x32) - 1); + DEFINE(X32_NR_syscalls, sizeof(syscalls_x32)); +#endif + DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 68c363c341bf..fe3649f725dc 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -27,6 +27,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; +static const int amd_erratum_1054[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -614,9 +615,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) return; clear_all: - clear_cpu_cap(c, X86_FEATURE_SME); + setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: - clear_cpu_cap(c, X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV); } } @@ -988,6 +989,15 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + /* + * Turn on the Instructions Retired free counter on machines not + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (cpu_has(c, X86_FEATURE_IRPERF) && + !cpu_has_amd_erratum(c, amd_erratum_1054)) + msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); } #ifdef CONFIG_X86_32 @@ -1115,6 +1125,9 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); +/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ +static const int amd_erratum_1054[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 63f576836251..a277fa17c4ee 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,7 +39,9 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); +static void __init srbds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -107,6 +109,13 @@ void __init check_bugs(void) l1tf_select_mitigation(); mds_select_mitigation(); taa_select_mitigation(); + srbds_select_mitigation(); + + /* + * As MDS and TAA mitigations are inter-related, print MDS + * mitigation until after TAA mitigation selection is done. + */ + mds_print_mitigation(); arch_smt_update(); @@ -245,6 +254,12 @@ static void __init mds_select_mitigation(void) (mds_nosmt || cpu_mitigations_auto_nosmt())) cpu_smt_disable(false); } +} + +static void __init mds_print_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) + return; pr_info("%s\n", mds_strings[mds_mitigation]); } @@ -304,8 +319,12 @@ static void __init taa_select_mitigation(void) return; } - /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ - if (taa_mitigation == TAA_MITIGATION_OFF) + /* + * TAA mitigation via VERW is turned off if both + * tsx_async_abort=off and mds=off are specified. + */ + if (taa_mitigation == TAA_MITIGATION_OFF && + mds_mitigation == MDS_MITIGATION_OFF) goto out; if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) @@ -339,6 +358,15 @@ static void __init taa_select_mitigation(void) if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); + /* + * Update MDS mitigation, if necessary, as the mds_user_clear is + * now enabled for TAA mitigation. + */ + if (mds_mitigation == MDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_MDS)) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_select_mitigation(); + } out: pr_info("%s\n", taa_strings[taa_mitigation]); } @@ -365,6 +393,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str) early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "SRBDS: " fmt + +enum srbds_mitigations { + SRBDS_MITIGATION_OFF, + SRBDS_MITIGATION_UCODE_NEEDED, + SRBDS_MITIGATION_FULL, + SRBDS_MITIGATION_TSX_OFF, + SRBDS_MITIGATION_HYPERVISOR, +}; + +static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL; + +static const char * const srbds_strings[] = { + [SRBDS_MITIGATION_OFF] = "Vulnerable", + [SRBDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [SRBDS_MITIGATION_FULL] = "Mitigation: Microcode", + [SRBDS_MITIGATION_TSX_OFF] = "Mitigation: TSX disabled", + [SRBDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +static bool srbds_off; + +void update_srbds_msr(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; + + if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + switch (srbds_mitigation) { + case SRBDS_MITIGATION_OFF: + case SRBDS_MITIGATION_TSX_OFF: + mcu_ctrl |= RNGDS_MITG_DIS; + break; + case SRBDS_MITIGATION_FULL: + mcu_ctrl &= ~RNGDS_MITG_DIS; + break; + default: + break; + } + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); +} + +static void __init srbds_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + /* + * Check to see if this is one of the MDS_NO systems supporting + * TSX that are only exposed to SRBDS when TSX is enabled. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM)) + srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; + else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; + else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED; + else if (cpu_mitigations_off() || srbds_off) + srbds_mitigation = SRBDS_MITIGATION_OFF; + + update_srbds_msr(); + pr_info("%s\n", srbds_strings[srbds_mitigation]); +} + +static int __init srbds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return 0; + + srbds_off = !strcmp(str, "off"); + return 0; +} +early_param("srbds", srbds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -462,7 +581,9 @@ early_param("nospectre_v1", nospectre_v1_cmdline); static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; -static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init = +static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = + SPECTRE_V2_USER_NONE; +static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; #ifdef CONFIG_RETPOLINE @@ -608,15 +729,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) break; } - /* - * At this point, an STIBP mode other than "off" has been set. - * If STIBP support is not being forced, check if STIBP always-on - * is preferred. - */ - if (mode != SPECTRE_V2_USER_STRICT && - boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) - mode = SPECTRE_V2_USER_STRICT_PREFERRED; - /* Initialize Indirect Branch Prediction Barrier */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); @@ -639,23 +751,36 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); + + spectre_v2_user_ibpb = mode; } - /* If enhanced IBRS is enabled no STIBP required */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + /* + * If enhanced IBRS is enabled or SMT impossible, STIBP is not + * required. + */ + if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return; /* - * If SMT is not possible or STIBP is not available clear the STIBP - * mode. + * At this point, an STIBP mode other than "off" has been set. + * If STIBP support is not being forced, check if STIBP always-on + * is preferred. */ - if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP)) + if (mode != SPECTRE_V2_USER_STRICT && + boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + + /* + * If STIBP is not available, clear the STIBP mode. + */ + if (!boot_cpu_has(X86_FEATURE_STIBP)) mode = SPECTRE_V2_USER_NONE; + + spectre_v2_user_stibp = mode; + set_mode: - spectre_v2_user = mode; - /* Only print the STIBP mode when SMT possible */ - if (smt_possible) - pr_info("%s\n", spectre_v2_user_strings[mode]); + pr_info("%s\n", spectre_v2_user_strings[mode]); } static const char * const spectre_v2_strings[] = { @@ -888,7 +1013,7 @@ void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; case SPECTRE_V2_USER_STRICT: @@ -1131,14 +1256,19 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { case PR_SPEC_ENABLE: - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; /* * Indirect branch speculation is always disabled in strict - * mode. + * mode. It can neither be enabled if it was force-disabled + * by a previous prctl call. + */ - if (spectre_v2_user == SPECTRE_V2_USER_STRICT || - spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + task_spec_ib_force_disable(task)) return -EPERM; task_clear_spec_ib_disable(task); task_update_spec_tif(task); @@ -1149,10 +1279,12 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) * Indirect branch speculation is always allowed when * mitigation is force disabled. */ - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user == SPECTRE_V2_USER_STRICT || - spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) return 0; task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) @@ -1183,7 +1315,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) { if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); - if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif @@ -1214,22 +1347,24 @@ static int ib_prctl_get(struct task_struct *task) if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return PR_SPEC_NOT_AFFECTED; - switch (spectre_v2_user) { - case SPECTRE_V2_USER_NONE: + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - case SPECTRE_V2_USER_PRCTL: - case SPECTRE_V2_USER_SECCOMP: + else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - case SPECTRE_V2_USER_STRICT: - case SPECTRE_V2_USER_STRICT_PREFERRED: - return PR_SPEC_DISABLE; - default: + } else return PR_SPEC_NOT_AFFECTED; - } } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) @@ -1468,7 +1603,7 @@ static char *stibp_state(void) if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return ""; - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: @@ -1495,6 +1630,11 @@ static char *ibpb_state(void) return ""; } +static ssize_t srbds_show_state(char *buf) +{ + return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1539,6 +1679,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITLB_MULTIHIT: return itlb_multihit_show_state(buf); + case X86_BUG_SRBDS: + return srbds_show_state(buf); + default: break; } @@ -1585,4 +1728,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr { return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); } + +ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8253038fa85f..1c44715818e6 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -366,6 +366,77 @@ out: cr4_clear_bits(X86_CR4_UMIP); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; +static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); +static unsigned long cr4_pinned_bits __ro_after_init; + +void native_write_cr0(unsigned long val) +{ + unsigned long bits_missing = 0; + +set_register: + asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order)); + + if (static_branch_likely(&cr_pinning)) { + if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) { + bits_missing = X86_CR0_WP; + val |= bits_missing; + goto set_register; + } + /* Warn after we've set the missing bits. */ + WARN_ONCE(bits_missing, "CR0 WP bit went missing!?\n"); + } +} +EXPORT_SYMBOL(native_write_cr0); + +void native_write_cr4(unsigned long val) +{ + unsigned long bits_changed = 0; + +set_register: + asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); + + if (static_branch_likely(&cr_pinning)) { + if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; + goto set_register; + } + /* Warn after we've corrected the changed bits. */ + WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n", + bits_changed); + } +} +EXPORT_SYMBOL(native_write_cr4); + +void cr4_init(void) +{ + unsigned long cr4 = __read_cr4(); + + if (boot_cpu_has(X86_FEATURE_PCID)) + cr4 |= X86_CR4_PCIDE; + if (static_branch_likely(&cr_pinning)) + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits; + + __write_cr4(cr4); + + /* Initialize cr4 shadow for this CPU. */ + this_cpu_write(cpu_tlbstate.cr4, cr4); +} + +/* + * Once CPU feature detection is finished (and boot params have been + * parsed), record any of the sensitive CR bits that are set, and + * enable CR pinning. + */ +static void __init setup_cr_pinning(void) +{ + cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask; + static_key_enable(&cr_pinning.key); +} + /* * Protection Keys are not available in 32-bit mode. */ @@ -393,7 +464,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ - get_cpu_cap(c); + set_cpu_cap(c, X86_FEATURE_OSPKE); } #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS @@ -1010,9 +1081,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; -static bool __init cpu_matches(unsigned long which) +#define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ + X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, steppings, \ + X86_FEATURE_ANY, issues) + +#define SRBDS BIT(0) + +static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { + VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_CORE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_ULT, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_GT3E, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_GT3E, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_CORE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_MOBILE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_DESKTOP, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_MOBILE, X86_STEPPINGS(0x0, 0xC), SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_DESKTOP,X86_STEPPINGS(0x0, 0xD), SRBDS), + {} +}; + +static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which) { - const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); + const struct x86_cpu_id *m = x86_match_cpu(table); return m && !!(m->driver_data & which); } @@ -1032,29 +1124,32 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) u64 ia32_cap = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ - if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && + !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); - if (cpu_matches(NO_SPECULATION)) + if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && + if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && + !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); if (ia32_cap & ARCH_CAP_IBRS_ALL) setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); - if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && + !(ia32_cap & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); - if (cpu_matches(MSBDS_ONLY)) + if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } - if (!cpu_matches(NO_SWAPGS)) + if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); /* @@ -1072,7 +1167,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); - if (cpu_matches(NO_MELTDOWN)) + /* + * SRBDS affects CPUs which support RDRAND or RDSEED and are listed + * in the vulnerability blacklist. + */ + if ((cpu_has(c, X86_FEATURE_RDRAND) || + cpu_has(c, X86_FEATURE_RDSEED)) && + cpu_matches(cpu_vuln_blacklist, SRBDS)) + setup_force_cpu_bug(X86_BUG_SRBDS); + + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -1081,7 +1185,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (cpu_matches(NO_L1TF)) + if (cpu_matches(cpu_vuln_whitelist, NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); @@ -1505,6 +1609,7 @@ void __init identify_boot_cpu(void) cpu_detect_tlb(&boot_cpu_data); tsx_init(); + setup_cr_pinning(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) @@ -1517,6 +1622,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) mtrr_ap_init(); validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); + update_srbds_msr(); } static __init int setup_noclflush(char *arg) @@ -1739,12 +1845,6 @@ void cpu_init(void) wait_for_master_cpu(cpu); - /* - * Initialize the CR4 shadow before doing anything that could - * try to read it. - */ - cr4_init_shadow(); - if (cpu) load_ucode_ap(); @@ -1839,12 +1939,6 @@ void cpu_init(void) wait_for_master_cpu(cpu); - /* - * Initialize the CR4 shadow before doing anything that could - * try to read it. - */ - cr4_init_shadow(); - show_ucode_info_early(); pr_info("Initializing CPU#%d\n", cpu); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 38ab6e115eac..9d033693519a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -77,6 +77,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 92b107ab283f..c979a056a46f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +/* + * Processors which have self-snooping capability can handle conflicting + * memory type across CPUs by snooping its own cache. However, there exists + * CPU models in which having conflicting memory types still leads to + * unpredictable behavior, machine check errors, or hangs. Clear this + * feature to prevent its use on machines with known erratas. + */ +static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c) +{ + switch (c->x86_model) { + case INTEL_FAM6_CORE_YONAH: + case INTEL_FAM6_CORE2_MEROM: + case INTEL_FAM6_CORE2_MEROM_L: + case INTEL_FAM6_CORE2_PENRYN: + case INTEL_FAM6_CORE2_DUNNINGTON: + case INTEL_FAM6_NEHALEM: + case INTEL_FAM6_NEHALEM_G: + case INTEL_FAM6_NEHALEM_EP: + case INTEL_FAM6_NEHALEM_EX: + case INTEL_FAM6_WESTMERE: + case INTEL_FAM6_WESTMERE_EP: + case INTEL_FAM6_SANDYBRIDGE: + setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP); + } +} + static bool ring3mwait_disabled __read_mostly; static int __init ring3mwait_disable(char *__unused) @@ -239,9 +265,9 @@ static void early_init_intel(struct cpuinfo_x86 *c) /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ if (c->x86 == 6) { switch (c->x86_model) { - case 0x27: /* Penwell */ - case 0x35: /* Cloverview */ - case 0x4a: /* Merrifield */ + case INTEL_FAM6_ATOM_SALTWELL_MID: + case INTEL_FAM6_ATOM_SALTWELL_TABLET: + case INTEL_FAM6_ATOM_SILVERMONT_MID: set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); break; default: @@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) } check_mpx_erratum(c); + check_memory_type_self_snoop_errata(c); /* * Get the number of SMT siblings early from the extended topology diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 6dd78d8235e4..2f163e6646b6 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -34,13 +34,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; m->vendor | m->family | m->model | m->feature; m++) { + for (m = match; + m->vendor | m->family | m->model | m->steppings | m->feature; + m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) continue; if (m->model != X86_MODEL_ANY && c->x86_model != m->model) continue; + if (m->steppings != X86_STEPPING_ANY && + !(BIT(c->x86_stepping) & m->steppings)) + continue; if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) continue; return m; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 785050af85e5..f1c845416790 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -244,10 +244,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) } /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } @@ -1159,9 +1159,12 @@ static const struct sysfs_ops threshold_ops = { .store = store, }; +static void threshold_block_release(struct kobject *kobj); + static struct kobj_type threshold_ktype = { .sysfs_ops = &threshold_ops, .default_attrs = default_attrs, + .release = threshold_block_release, }; static const char *get_name(unsigned int bank, struct threshold_block *b) @@ -1194,8 +1197,9 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return buf_mcatype; } -static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, - unsigned int block, u32 address) +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -1239,16 +1243,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, INIT_LIST_HEAD(&b->miscj); - if (per_cpu(threshold_banks, cpu)[bank]->blocks) { - list_add(&b->miscj, - &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj); - } else { - per_cpu(threshold_banks, cpu)[bank]->blocks = b; - } + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, - per_cpu(threshold_banks, cpu)[bank]->kobj, - get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); if (err) goto out_free; recurse: @@ -1256,7 +1256,7 @@ recurse: if (!address) return 0; - err = allocate_threshold_blocks(cpu, bank, block, address); + err = allocate_threshold_blocks(cpu, tb, bank, block, address); if (err) goto out_free; @@ -1341,8 +1341,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out_free; } - per_cpu(threshold_banks, cpu)[bank] = b; - if (is_shared_bank(bank)) { refcount_set(&b->cpus, 1); @@ -1353,9 +1351,13 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } } - err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank)); - if (!err) - goto out; + err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); + if (err) + goto out_free; + + per_cpu(threshold_banks, cpu)[bank] = b; + + return 0; out_free: kfree(b); @@ -1364,8 +1366,12 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -static void deallocate_threshold_block(unsigned int cpu, - unsigned int bank) +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { struct threshold_block *pos = NULL; struct threshold_block *tmp = NULL; @@ -1375,13 +1381,11 @@ static void deallocate_threshold_block(unsigned int cpu, return; list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { - kobject_put(&pos->kobj); list_del(&pos->miscj); - kfree(pos); + kobject_put(&pos->kobj); } - kfree(per_cpu(threshold_banks, cpu)[bank]->blocks); - per_cpu(threshold_banks, cpu)[bank]->blocks = NULL; + kobject_put(&head->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 282916f3b8d8..db1a8a1612f9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -517,6 +517,13 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); +static bool whole_page(struct mce *m) +{ + if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV)) + return true; + return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT; +} + bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) @@ -585,7 +592,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); + set_mce_nospec(pfn, whole_page(mce)); } return NOTIFY_OK; @@ -797,8 +804,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; @@ -1086,7 +1093,7 @@ static int do_memory_failure(struct mce *m) if (ret) pr_err("Memory error not recovered"); else - set_mce_nospec(m->addr >> PAGE_SHIFT); + set_mce_nospec(m->addr >> PAGE_SHIFT, whole_page(m)); return ret; } diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index 7c8958dee103..6c9b91b773ef 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -328,6 +328,7 @@ static const struct file_operations mce_chrdev_ops = { .write = mce_chrdev_write, .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, .llseek = no_llseek, }; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 5d108f70f315..799b74b1582c 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -511,7 +511,7 @@ static void do_inject(void) */ if (inj_type == DFR_INT_INJ) { i_mce.status |= MCI_STATUS_DEFERRED; - i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + i_mce.status &= ~MCI_STATUS_UC; } /* diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index e43eb6732630..693c8cfac75d 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -489,17 +489,18 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) return; if ((val & 3UL) == 1UL) { - /* PPIN available but disabled: */ + /* PPIN locked in disabled mode */ return; } - /* If PPIN is disabled, but not locked, try to enable: */ - if (!(val & 3UL)) { + /* If PPIN is disabled, try to enable */ + if (!(val & 2UL)) { wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); rdmsrl_safe(MSR_PPIN_CTL, &val); } - if ((val & 3UL) == 2UL) + /* Is the enable bit set? */ + if (val & 2UL) set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); } } diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 6e2becf547c5..bc441d68d060 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -188,7 +188,7 @@ static void therm_throt_process(bool new_event, int event, int level) /* if we just entered the thermal event */ if (new_event) { if (event == THERMAL_THROTTLING_EVENT) - pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + pr_warn("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 7df29f08871b..920aa2f0b52b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -220,8 +220,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - pr_info("Hyper-V: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("Hyper-V: features 0x%x, hints 0x%x, misc 0x%x\n", + ms_hyperv.features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); @@ -256,6 +256,16 @@ static void __init ms_hyperv_init_platform(void) cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); } + /* + * Hyper-V expects to get crash register data or kmsg when + * crash enlightment is available and system crashes. Set + * crash_kexec_post_notifiers to be true to make sure that + * calling crash enlightment interface before running kdump + * kernel. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + crash_kexec_post_notifiers = true; + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { @@ -266,9 +276,9 @@ static void __init ms_hyperv_init_platform(void) rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); - lapic_timer_frequency = hv_lapic_frequency; + lapic_timer_period = hv_lapic_frequency; pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n", - lapic_timer_frequency); + lapic_timer_period); } register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST, diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 03eb90d00af0..d8cc5223b7ce 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -578,6 +578,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) d->id = id; cpumask_set_cpu(cpu, &d->cpu_mask); + rdt_domain_reconfigure_cdp(r); + if (r->alloc_capable && domain_setup_ctrlval(r, d)) { kfree(d); return; @@ -618,7 +620,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); list_del(&d->list); - if (is_mbm_enabled()) + if (r->mon_capable && is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { /* diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index efbd54cc4e69..055c8613b531 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e49b77283924..3dd13f3a8b23 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) } DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /** * struct mon_evt - Entry in the event list of a resource @@ -600,5 +601,6 @@ bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r); bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r); +void rdt_domain_reconfigure_cdp(struct rdt_resource *r); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 397206f23d14..773124b0e18a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); @@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2f4824793798..81200c253002 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); - rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; - rdt_last_cmd_puts("Directory was removed\n"); goto unlock; } @@ -1029,6 +1027,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } @@ -1743,9 +1742,6 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; - if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) - return -ENOMEM; - if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -1753,6 +1749,9 @@ static int set_cache_qos_cfg(int level, bool enable) else return -EINVAL; + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { /* Pick one CPU from each domain instance to update MSR */ @@ -1771,6 +1770,19 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* Restore the qos cfg state when a domain comes online */ +void rdt_domain_reconfigure_cdp(struct rdt_resource *r) +{ + if (!r->alloc_capable) + return; + + if (r == &rdt_resources_all[RDT_RESOURCE_L2DATA]) + l2_qos_cfg_update(&r->alloc_enabled); + + if (r == &rdt_resources_all[RDT_RESOURCE_L3DATA]) + l3_qos_cfg_update(&r->alloc_enabled); +} + /* * Enable or disable the MBA software controller * which helps user specify bandwidth in MBps. @@ -1972,7 +1984,7 @@ static int rdt_get_tree(struct fs_context *fc) if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, - NULL, "mon_groups", + &rdtgroup_default, "mon_groups", &kn_mongrp); if (ret < 0) goto out_info; @@ -2208,7 +2220,11 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { free_rmid(sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); - kfree(sentry); + + if (atomic_read(&sentry->waitcount) != 0) + sentry->flags = RDT_DELETED; + else + kfree(sentry); } } @@ -2246,7 +2262,11 @@ static void rmdir_all_sub(void) kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); - kfree(rdtgrp); + + if (atomic_read(&rdtgrp->waitcount) != 0) + rdtgrp->flags = RDT_DELETED; + else + kfree(rdtgrp); } /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ update_closid_rmid(cpu_online_mask, &rdtgroup_default); @@ -2449,7 +2469,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, /* * Create the mon_data directory first. */ - ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn); + ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn); if (ret) return ret; @@ -2648,11 +2668,9 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, uint files = 0; int ret; - prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); - rdt_last_cmd_clear(); + prdtgrp = rdtgroup_kn_lock_live(parent_kn); if (!prdtgrp) { ret = -ENODEV; - rdt_last_cmd_puts("Directory was removed\n"); goto out_unlock; } @@ -2723,7 +2741,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, kernfs_activate(kn); /* - * The caller unlocks the prgrp_kn upon success. + * The caller unlocks the parent_kn upon success. */ return 0; @@ -2734,7 +2752,7 @@ out_destroy: out_free_rgrp: kfree(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2772,7 +2790,7 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2815,7 +2833,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. */ - ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL); + ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL); if (ret) { rdt_last_cmd_puts("kernfs subdir error\n"); goto out_del_list; @@ -2831,7 +2849,7 @@ out_id_free: out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); out_unlock: - rdtgroup_kn_unlock(prgrp_kn); + rdtgroup_kn_unlock(parent_kn); return ret; } @@ -2957,13 +2975,13 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp, closid_free(rdtgrp->closid); free_rmid(rdtgrp->mon.rmid); + rdtgroup_ctrl_remove(kn, rdtgrp); + /* * Free all the child monitor group rmids. */ free_all_child_rdtgrp(rdtgrp); - rdtgroup_ctrl_remove(kn, rdtgrp); - return 0; } @@ -2990,7 +3008,8 @@ static int rdtgroup_rmdir(struct kernfs_node *kn) * If the rdtgroup is a mon group and parent directory * is a valid "mon_groups" directory, remove the mon group. */ - if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) { + if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn && + rdtgrp != &rdtgroup_default) { if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { ret = rdtgroup_ctrl_remove(kn, rdtgrp); diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 3e20d322bc98..032509adf9de 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -115,11 +115,12 @@ void __init tsx_init(void) tsx_disable(); /* - * tsx_disable() will change the state of the - * RTM CPUID bit. Clear it here since it is now - * expected to be not set. + * tsx_disable() will change the state of the RTM and HLE CPUID + * bits. Clear them here since they are now expected to be not + * set. */ setup_clear_cpu_cap(X86_FEATURE_RTM); + setup_clear_cpu_cap(X86_FEATURE_HLE); } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { /* @@ -131,10 +132,10 @@ void __init tsx_init(void) tsx_enable(); /* - * tsx_enable() will change the state of the - * RTM CPUID bit. Force it here since it is now - * expected to be set. + * tsx_enable() will change the state of the RTM and HLE CPUID + * bits. Force them here since they are now expected to be set. */ setup_force_cpu_cap(X86_FEATURE_RTM); + setup_force_cpu_cap(X86_FEATURE_HLE); } } diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 34ab4161fc39..88569536d529 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -158,7 +158,7 @@ static void __init vmware_platform_setup(void) #ifdef CONFIG_X86_LOCAL_APIC /* Skip lapic calibration since we know the bus frequency. */ - lapic_timer_frequency = ecx / HZ; + lapic_timer_period = ecx / HZ; pr_info("Host bus clock speed read from hypervisor : %u Hz\n", ecx); #endif diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 576b2e1bfc12..84e2d3ddd0eb 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -73,14 +73,6 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { -#ifdef CONFIG_X86_32 - struct pt_regs fixed_regs; - - if (!user_mode(regs)) { - crash_fixup_ss_esp(&fixed_regs, regs); - regs = &fixed_regs; - } -#endif crash_save_cpu(regs, cpu); /* diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 0b8cedb20d6d..d5c9b13bafdf 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -65,6 +65,9 @@ struct x86_hw_tss doublefault_tss __cacheline_aligned = { .ss = __KERNEL_DS, .ds = __USER_DS, .fs = __KERNEL_PERCPU, +#ifndef CONFIG_X86_32_LAZY_GS + .gs = __KERNEL_STACK_CANARY, +#endif .__cr3 = __pa_nodebug(swapper_pg_dir), }; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 753b8cfe8b8a..87b97897a881 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); + /* + * Handle the case where stack trace is collected _before_ + * cea_exception_stacks had been initialized. + */ + if (!begin) + return false; + end = begin + sizeof(struct cea_exception_stacks); /* Bail if @stack is outside the exception stack area. */ if (stk < begin || stk >= end) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6c4f01540833..7c9259306d74 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -709,6 +709,12 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3e20, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3ec4, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x8a12, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 649fbc3fcf9f..8ba0e53dec75 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -113,6 +113,12 @@ static void __kernel_fpu_begin(void) } } __cpu_invalidate_fpregs_state(); + + if (boot_cpu_has(X86_FEATURE_XMM)) + ldmxcsr(MXCSR_DEFAULT); + + if (boot_cpu_has(X86_FEATURE_FPU)) + asm volatile ("fninit"); } static void __kernel_fpu_end(void) diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 0071b794ed19..400a05e1c1c5 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -352,6 +352,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + fpregs_deactivate(fpu); fpregs_unlock(); } @@ -403,6 +404,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } if (!ret) fpregs_mark_activate(); + else + fpregs_deactivate(fpu); fpregs_unlock(); err_out: diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 3c36dd1784db..085afecd878c 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -959,18 +959,31 @@ static inline bool xfeatures_mxcsr_quirk(u64 xfeatures) return true; } -/* - * This is similar to user_regset_copyout(), but will not add offset to - * the source data pointer or increment pos, count, kbuf, and ubuf. - */ -static inline void -__copy_xstate_to_kernel(void *kbuf, const void *data, - unsigned int offset, unsigned int size, unsigned int size_total) +static void fill_gap(unsigned to, void **kbuf, unsigned *pos, unsigned *count) { - if (offset < size_total) { - unsigned int copy = min(size, size_total - offset); + if (*pos < to) { + unsigned size = to - *pos; + + if (size > *count) + size = *count; + memcpy(*kbuf, (void *)&init_fpstate.xsave + *pos, size); + *kbuf += size; + *pos += size; + *count -= size; + } +} - memcpy(kbuf + offset, data, copy); +static void copy_part(unsigned offset, unsigned size, void *from, + void **kbuf, unsigned *pos, unsigned *count) +{ + fill_gap(offset, kbuf, pos, count); + if (size > *count) + size = *count; + if (size) { + memcpy(*kbuf, from, size); + *kbuf += size; + *pos += size; + *count -= size; } } @@ -983,8 +996,9 @@ __copy_xstate_to_kernel(void *kbuf, const void *data, */ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total) { - unsigned int offset, size; struct xstate_header header; + const unsigned off_mxcsr = offsetof(struct fxregs_state, mxcsr); + unsigned count = size_total; int i; /* @@ -1000,46 +1014,42 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of header.xfeatures = xsave->header.xfeatures; header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(0, off_mxcsr, + &xsave->i387, &kbuf, &offset_start, &count); + if (header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM)) + copy_part(off_mxcsr, MXCSR_AND_FLAGS_SIZE, + &xsave->i387.mxcsr, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_FP) + copy_part(offsetof(struct fxregs_state, st_space), 128, + &xsave->i387.st_space, &kbuf, &offset_start, &count); + if (header.xfeatures & XFEATURE_MASK_SSE) + copy_part(xstate_offsets[XFEATURE_SSE], 256, + &xsave->i387.xmm_space, &kbuf, &offset_start, &count); + /* + * Fill xsave->i387.sw_reserved value for ptrace frame: + */ + copy_part(offsetof(struct fxregs_state, sw_reserved), 48, + xstate_fx_sw_bytes, &kbuf, &offset_start, &count); /* * Copy xregs_state->header: */ - offset = offsetof(struct xregs_state, header); - size = sizeof(header); - - __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total); + copy_part(offsetof(struct xregs_state, header), sizeof(header), + &header, &kbuf, &offset_start, &count); - for (i = 0; i < XFEATURE_MAX; i++) { + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { /* * Copy only in-use xstates: */ if ((header.xfeatures >> i) & 1) { void *src = __raw_xsave_addr(xsave, i); - offset = xstate_offsets[i]; - size = xstate_sizes[i]; - - /* The next component has to fit fully into the output buffer: */ - if (offset + size > size_total) - break; - - __copy_xstate_to_kernel(kbuf, src, offset, size, size_total); + copy_part(xstate_offsets[i], xstate_sizes[i], + src, &kbuf, &offset_start, &count); } } - - if (xfeatures_mxcsr_quirk(header.xfeatures)) { - offset = offsetof(struct fxregs_state, mxcsr); - size = MXCSR_AND_FLAGS_SIZE; - __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total); - } - - /* - * Fill xsave->i387.sw_reserved value for ptrace frame: - */ - offset = offsetof(struct fxregs_state, sw_reserved); - size = sizeof(xstate_fx_sw_bytes); - - __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total); + fill_gap(size_total, &kbuf, &offset_start, &count); return 0; } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 76228525acd0..4b73f5937f41 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -310,7 +310,6 @@ int ftrace_int3_handler(struct pt_regs *regs) ip = regs->ip - INT3_INSN_SIZE; -#ifdef CONFIG_X86_64 if (ftrace_location(ip)) { int3_emulate_call(regs, (unsigned long)ftrace_regs_caller); return 1; @@ -322,12 +321,6 @@ int ftrace_int3_handler(struct pt_regs *regs) int3_emulate_call(regs, ftrace_update_func_call); return 1; } -#else - if (ftrace_location(ip) || is_ftrace_caller(ip)) { - int3_emulate_jmp(regs, ip + CALL_INSN_SIZE); - return 1; - } -#endif return 0; } diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 2ba914a34b06..073aab525d80 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -9,6 +9,8 @@ #include <asm/export.h> #include <asm/ftrace.h> #include <asm/nospec-branch.h> +#include <asm/frame.h> +#include <asm/asm-offsets.h> # define function_hook __fentry__ EXPORT_SYMBOL(__fentry__) @@ -89,26 +91,38 @@ END(ftrace_caller) ENTRY(ftrace_regs_caller) /* - * i386 does not save SS and ESP when coming from kernel. - * Instead, to get sp, ®s->sp is used (see ptrace.h). - * Unfortunately, that means eflags must be at the same location - * as the current return ip is. We move the return ip into the - * regs->ip location, and move flags into the return ip location. + * We're here from an mcount/fentry CALL, and the stack frame looks like: + * + * <previous context> + * RET-IP + * + * The purpose of this function is to call out in an emulated INT3 + * environment with a stack frame like: + * + * <previous context> + * gap / RET-IP + * gap + * gap + * gap + * pt_regs + * + * We do _NOT_ restore: ss, flags, cs, gs, fs, es, ds */ - pushl $__KERNEL_CS - pushl 4(%esp) /* Save the return ip */ - pushl $0 /* Load 0 into orig_ax */ + subl $3*4, %esp # RET-IP + 3 gaps + pushl %ss # ss + pushl %esp # points at ss + addl $5*4, (%esp) # make it point at <previous context> + pushfl # flags + pushl $__KERNEL_CS # cs + pushl 7*4(%esp) # ip <- RET-IP + pushl $0 # orig_eax + pushl %gs pushl %fs pushl %es pushl %ds - pushl %eax - - /* Get flags and place them into the return ip slot */ - pushf - popl %eax - movl %eax, 8*4(%esp) + pushl %eax pushl %ebp pushl %edi pushl %esi @@ -116,24 +130,27 @@ ENTRY(ftrace_regs_caller) pushl %ecx pushl %ebx - movl 12*4(%esp), %eax /* Load ip (1st parameter) */ - subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ - movl 15*4(%esp), %edx /* Load parent ip (2nd parameter) */ - movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ - pushl %esp /* Save pt_regs as 4th parameter */ + ENCODE_FRAME_POINTER + + movl PT_EIP(%esp), %eax # 1st argument: IP + subl $MCOUNT_INSN_SIZE, %eax + movl 21*4(%esp), %edx # 2nd argument: parent ip + movl function_trace_op, %ecx # 3rd argument: ftrace_pos + pushl %esp # 4th argument: pt_regs GLOBAL(ftrace_regs_call) call ftrace_stub - addl $4, %esp /* Skip pt_regs */ + addl $4, %esp # skip 4th argument - /* restore flags */ - push 14*4(%esp) - popf + /* place IP below the new SP */ + movl PT_OLDESP(%esp), %eax + movl PT_EIP(%esp), %ecx + movl %ecx, -4(%eax) - /* Move return ip back to its original location */ - movl 12*4(%esp), %eax - movl %eax, 14*4(%esp) + /* place EAX below that */ + movl PT_EAX(%esp), %ecx + movl %ecx, -8(%eax) popl %ebx popl %ecx @@ -141,14 +158,9 @@ GLOBAL(ftrace_regs_call) popl %esi popl %edi popl %ebp - popl %eax - popl %ds - popl %es - popl %fs - popl %gs - /* use lea to not affect flags */ - lea 3*4(%esp), %esp /* Skip orig_ax, ip and cs */ + lea -8(%eax), %esp + popl %eax jmp .Lftrace_ret diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 10eb2760ef2c..809d54397dba 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -9,6 +9,7 @@ #include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> +#include <asm/frame.h> .code64 .section .entry.text, "ax" @@ -203,6 +204,8 @@ GLOBAL(ftrace_regs_caller_op_ptr) leaq MCOUNT_REG_SIZE+8*2(%rsp), %rcx movq %rcx, RSP(%rsp) + ENCODE_FRAME_POINTER + /* regs go into 4th parameter */ leaq (%rsp), %rcx diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 30f9cb2c0b55..2e6a0676c1f4 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -571,6 +571,16 @@ ENTRY(initial_page_table) # error "Kernel PMDs should be 1, 2 or 3" # endif .align PAGE_SIZE /* needs to be page-sized too */ + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * PTI needs another page so sync_initial_pagetable() works correctly + * and does not scribble over the data which is placed behind the + * actual initial_page_table. See clone_pgd_range(). + */ + .fill 1024, 4, 0 +#endif + #endif .data diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index bcd206c8ac90..0e2d72929a8c 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -29,9 +29,7 @@ #ifdef CONFIG_PARAVIRT_XXL #include <asm/asm-offsets.h> #include <asm/paravirt.h> -#define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg #else -#define GET_CR2_INTO(reg) movq %cr2, reg #define INTERRUPT_RETURN iretq #endif @@ -323,7 +321,7 @@ early_idt_handler_common: cmpq $14,%rsi /* Page fault? */ jnz 10f - GET_CR2_INTO(%rdi) /* Can clobber any volatile register if pv */ + GET_CR2_INTO(%rdi) /* can clobber %rax if pv */ call early_make_pgtable andl %eax,%eax jz 20f /* All good */ diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 519649ddf100..fe522691ac71 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -207,7 +207,7 @@ spurious_8259A_irq: * lets ACK and report it. [once per IRQ] */ if (!(spurious_irq_mask & irqmask)) { - printk(KERN_DEBUG + printk_deferred(KERN_DEBUG "spurious 8259A interrupt: IRQ%d.\n", irq); spurious_irq_mask |= irqmask; } diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 87ef69a72c52..7bb4c3cbf4dc 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -318,7 +318,11 @@ void __init idt_setup_apic_and_irq_gates(void) #ifdef CONFIG_X86_LOCAL_APIC for_each_clear_bit_from(i, system_vectors, NR_VECTORS) { - set_bit(i, system_vectors); + /* + * Don't set the non assigned system vectors in the + * system_vectors bitmap. Otherwise they show up in + * /proc/interrupts. + */ entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR); set_intr_gate(i, entry); } diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c index 4c407833faca..fa188de3f424 100644 --- a/arch/x86/kernel/ima_arch.c +++ b/arch/x86/kernel/ima_arch.c @@ -10,8 +10,6 @@ extern struct boot_params boot_params; static enum efi_secureboot_mode get_sb_mode(void) { - efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; - efi_char16_t efi_SetupMode_name[] = L"SecureBoot"; efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; efi_status_t status; unsigned long size; @@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } /* Get variable contents into buffer */ - status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + status = efi.get_variable(L"SecureBoot", &efi_variable_guid, NULL, &size, &secboot); if (status == EFI_NOT_FOUND) { pr_info("ima: secureboot mode disabled\n"); @@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_mode(void) } size = sizeof(setupmode); - status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid, + status = efi.get_variable(L"SetupMode", &efi_variable_guid, NULL, &size, &setupmode); if (status != EFI_SUCCESS) /* ignore unknown SetupMode */ diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 6bf6517a05bb..5bfa35f3dbac 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -52,7 +52,7 @@ static int map_irq_stack(unsigned int cpu) pages[i] = pfn_to_page(pa >> PAGE_SHIFT); } - va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); + va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, VM_MAP, PAGE_KERNEL); if (!va) return -ENOMEM; diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 1b2ee55a2dfb..ba95bc70460d 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -45,7 +45,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now) static void __init jailhouse_timer_init(void) { - lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ); + lapic_timer_period = setup_data.apic_khz * (1000 / HZ); } static unsigned long jailhouse_get_tsc(void) diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 6690c5652aeb..23297ea64f5f 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -118,14 +118,6 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) #ifdef CONFIG_X86_32 switch (regno) { - case GDB_SS: - if (!user_mode(regs)) - *(unsigned long *)mem = __KERNEL_DS; - break; - case GDB_SP: - if (!user_mode(regs)) - *(unsigned long *)mem = kernel_stack_pointer(regs); - break; case GDB_GS: case GDB_FS: *(unsigned long *)mem = 0xFFFF; diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index 2b949f4fd4d8..7d3a2e2daf01 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -5,15 +5,10 @@ /* Kprobes and Optprobes common header */ #include <asm/asm.h> - -#ifdef CONFIG_FRAME_POINTER -# define SAVE_RBP_STRING " push %" _ASM_BP "\n" \ - " mov %" _ASM_SP ", %" _ASM_BP "\n" -#else -# define SAVE_RBP_STRING " push %" _ASM_BP "\n" -#endif +#include <asm/frame.h> #ifdef CONFIG_X86_64 + #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax. */ \ " subq $24, %rsp\n" \ @@ -27,11 +22,13 @@ " pushq %r10\n" \ " pushq %r11\n" \ " pushq %rbx\n" \ - SAVE_RBP_STRING \ + " pushq %rbp\n" \ " pushq %r12\n" \ " pushq %r13\n" \ " pushq %r14\n" \ - " pushq %r15\n" + " pushq %r15\n" \ + ENCODE_FRAME_POINTER + #define RESTORE_REGS_STRING \ " popq %r15\n" \ " popq %r14\n" \ @@ -51,19 +48,22 @@ /* Skip orig_ax, ip, cs */ \ " addq $24, %rsp\n" #else + #define SAVE_REGS_STRING \ /* Skip cs, ip, orig_ax and gs. */ \ - " subl $16, %esp\n" \ + " subl $4*4, %esp\n" \ " pushl %fs\n" \ " pushl %es\n" \ " pushl %ds\n" \ " pushl %eax\n" \ - SAVE_RBP_STRING \ + " pushl %ebp\n" \ " pushl %edi\n" \ " pushl %esi\n" \ " pushl %edx\n" \ " pushl %ecx\n" \ - " pushl %ebx\n" + " pushl %ebx\n" \ + ENCODE_FRAME_POINTER + #define RESTORE_REGS_STRING \ " popl %ebx\n" \ " popl %ecx\n" \ @@ -72,8 +72,8 @@ " popl %edi\n" \ " popl %ebp\n" \ " popl %eax\n" \ - /* Skip ds, es, fs, gs, orig_ax, and ip. Note: don't pop cs here*/\ - " addl $24, %esp\n" + /* Skip ds, es, fs, gs, orig_ax, ip, and cs. */\ + " addl $7*4, %esp\n" #endif /* Ensure if the instruction can be boostable */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6afd8061dbae..27159a40dc93 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -56,7 +56,7 @@ DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); -#define stack_addr(regs) ((unsigned long *)kernel_stack_pointer(regs)) +#define stack_addr(regs) ((unsigned long *)regs->sp) #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ @@ -718,29 +718,27 @@ asm( ".global kretprobe_trampoline\n" ".type kretprobe_trampoline, @function\n" "kretprobe_trampoline:\n" -#ifdef CONFIG_X86_64 /* We don't bother saving the ss register */ +#ifdef CONFIG_X86_64 " pushq %rsp\n" " pushfq\n" SAVE_REGS_STRING " movq %rsp, %rdi\n" " call trampoline_handler\n" /* Replace saved sp with true return address. */ - " movq %rax, 152(%rsp)\n" + " movq %rax, 19*8(%rsp)\n" RESTORE_REGS_STRING " popfq\n" #else - " pushf\n" + " pushl %esp\n" + " pushfl\n" SAVE_REGS_STRING " movl %esp, %eax\n" " call trampoline_handler\n" - /* Move flags to cs */ - " movl 56(%esp), %edx\n" - " movl %edx, 52(%esp)\n" - /* Replace saved flags with true return address. */ - " movl %eax, 56(%esp)\n" + /* Replace saved sp with true return address. */ + " movl %eax, 15*4(%esp)\n" RESTORE_REGS_STRING - " popf\n" + " popfl\n" #endif " ret\n" ".size kretprobe_trampoline, .-kretprobe_trampoline\n" @@ -748,16 +746,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -767,30 +760,23 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ -#ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; - /* On x86-64, we use pt_regs->sp for return address holder. */ - frame_pointer = ®s->sp; -#else - regs->cs = __KERNEL_CS | get_kernel_rpl(); +#ifdef CONFIG_X86_32 + regs->cs |= get_kernel_rpl(); regs->gs = 0; - /* On x86-32, we use pt_regs->flags for return address holder. */ - frame_pointer = ®s->flags; #endif + /* We use pt_regs->sp for return address holder. */ + frame_pointer = ®s->sp; regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -855,7 +841,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -871,8 +857,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 7c361a24c6df..282b4eb67e30 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -102,14 +102,15 @@ asm ( "optprobe_template_call:\n" ASM_NOP5 /* Move flags to rsp */ - " movq 144(%rsp), %rdx\n" - " movq %rdx, 152(%rsp)\n" + " movq 18*8(%rsp), %rdx\n" + " movq %rdx, 19*8(%rsp)\n" RESTORE_REGS_STRING /* Skip flags entry */ " addq $8, %rsp\n" " popfq\n" #else /* CONFIG_X86_32 */ - " pushf\n" + " pushl %esp\n" + " pushfl\n" SAVE_REGS_STRING " movl %esp, %edx\n" ".global optprobe_template_val\n" @@ -118,9 +119,13 @@ asm ( ".global optprobe_template_call\n" "optprobe_template_call:\n" ASM_NOP5 + /* Move flags into esp */ + " movl 14*4(%esp), %edx\n" + " movl %edx, 15*4(%esp)\n" RESTORE_REGS_STRING - " addl $4, %esp\n" /* skip cs */ - " popf\n" + /* Skip flags entry */ + " addl $4, %esp\n" + " popfl\n" #endif ".global optprobe_template_end\n" "optprobe_template_end:\n" @@ -152,10 +157,9 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) } else { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); /* Save skipped registers */ -#ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; -#else - regs->cs = __KERNEL_CS | get_kernel_rpl(); +#ifdef CONFIG_X86_32 + regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 320b70acb211..92ef0ec8c87c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -242,23 +242,23 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); dotraplinkage void -do_async_page_fault(struct pt_regs *regs, unsigned long error_code) +do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { enum ctx_state prev_state; switch (kvm_read_and_reset_pf_reason()) { default: - do_page_fault(regs, error_code); + do_page_fault(regs, error_code, address); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ prev_state = exception_enter(); - kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs)); + kvm_async_pf_task_wait((u32)address, !user_mode(regs)); exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); - kvm_async_pf_task_wake((u32)read_cr2()); + kvm_async_pf_task_wake((u32)address); rcu_irq_exit(); break; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4df7705022b9..d7f40ad34432 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void) } fs_initcall(nmi_warning_debugfs); -static void nmi_max_handler(struct irq_work *w) +static void nmi_check_duration(struct nmiaction *action, u64 duration) { - struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; - u64 whole_msecs = READ_ONCE(a->max_duration); + + if (duration < nmi_longest_ns || duration < action->max_duration) + return; + + action->max_duration = duration; remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - a->handler, whole_msecs, decimal_msecs); + action->handler, whole_msecs, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) @@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs) delta = sched_clock() - delta; trace_nmi_handler(a->handler, (int)delta, thishandled); - if (delta < nmi_longest_ns || delta < a->max_duration) - continue; - - a->max_duration = delta; - irq_work_queue(&a->irq_work); + nmi_check_duration(a, delta); } rcu_read_unlock(); @@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; - init_irq_work(&action->irq_work, nmi_max_handler); - raw_spin_lock_irqsave(&desc->lock, flags); /* diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 06f6bb48d018..f8ea3a00bdd9 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -370,7 +370,7 @@ struct paravirt_patch_template pv_ops = { .mmu.exit_mmap = paravirt_nop, #ifdef CONFIG_PARAVIRT_XXL - .mmu.read_cr2 = native_read_cr2, + .mmu.read_cr2 = __PV_IS_CALLEE_SAVE(native_read_cr2), .mmu.write_cr2 = native_write_cr2, .mmu.read_cr3 = __native_read_cr3, .mmu.write_cr3 = native_write_cr3, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 75fea0d48c0e..a04e43ff4b5e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -428,28 +428,20 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, lockdep_assert_irqs_disabled(); - /* - * If TIF_SSBD is different, select the proper mitigation - * method. Note that if SSBD mitigation is disabled or permanentely - * enabled this branch can't be taken because nothing can set - * TIF_SSBD. - */ - if (tif_diff & _TIF_SSBD) { - if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* Handle change of TIF_SSBD depending on the mitigation method. */ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_ssb_virt_state(tifn); - } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_core_ssb_state(tifn); - } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - msr |= ssbd_tif_to_spec_ctrl(tifn); - updmsr = true; - } + } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + updmsr |= !!(tif_diff & _TIF_SSBD); + msr |= ssbd_tif_to_spec_ctrl(tifn); } - /* - * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled, - * otherwise avoid the MSR write. - */ + /* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */ if (IS_ENABLED(CONFIG_SMP) && static_branch_unlikely(&switch_to_cond_stibp)) { updmsr |= !!(tif_diff & _TIF_SPEC_IB); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2399e910d109..b8ceec4974fe 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -62,27 +62,21 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; - unsigned long sp; - unsigned short ss, gs; + unsigned short gs; - if (user_mode(regs)) { - sp = regs->sp; - ss = regs->ss; + if (user_mode(regs)) gs = get_user_gs(regs); - } else { - sp = kernel_stack_pointer(regs); - savesegment(ss, ss); + else savesegment(gs, gs); - } show_ip(regs, KERN_DEFAULT); printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", - regs->si, regs->di, regs->bp, sp); + regs->si, regs->di, regs->bp, regs->sp); printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", - (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); + (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, regs->ss, regs->flags); if (mode != SHOW_REGS_ALL) return; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 250e4c4ac6d9..d02874cddda3 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -326,7 +326,7 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task, */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; - if (unlikely(idx >= ldt->nr_entries)) + if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 00fccf952d9b..b47dfeb3a02a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -155,35 +155,6 @@ static inline bool invalid_selector(u16 value) #define FLAG_MASK FLAG_MASK_32 -/* - * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode - * when it traps. The previous stack will be directly underneath the saved - * registers, and 'sp/ss' won't even have been saved. Thus the '®s->sp'. - * - * Now, if the stack is empty, '®s->sp' is out of range. In this - * case we try to take the previous stack. To always return a non-null - * stack pointer we fall back to regs as stack if no previous stack - * exists. - * - * This is valid only for kernel mode traps. - */ -unsigned long kernel_stack_pointer(struct pt_regs *regs) -{ - unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1); - unsigned long sp = (unsigned long)®s->sp; - u32 *prev_esp; - - if (context == (sp & ~(THREAD_SIZE - 1))) - return sp; - - prev_esp = (u32 *)(context); - if (*prev_esp) - return (unsigned long)*prev_esp; - - return (unsigned long)regs; -} -EXPORT_SYMBOL_GPL(kernel_stack_pointer); - static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno) { BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 09d6bded3c1e..3f677832fc12 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -197,6 +197,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), }, }, + { /* Handle problems with rebooting on Apple MacBook6,1 */ + .callback = set_pci_reboot, + .ident = "Apple MacBook6,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBook6,1"), + }, + }, { /* Handle problems with rebooting on Apple MacBookPro5 */ .callback = set_pci_reboot, .ident = "Apple MacBookPro5", diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 362dd8953f48..5fe11d5d29c1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -210,17 +210,11 @@ static void notrace start_secondary(void *unused) * before cpu_init(), SMP booting is too fragile that we want to * limit the things done here to the most necessary things. */ - if (boot_cpu_has(X86_FEATURE_PCID)) - __write_cr4(__read_cr4() | X86_CR4_PCIDE); + cr4_init(); #ifdef CONFIG_X86_32 /* switch away from the initial page table */ load_cr3(swapper_pg_dir); - /* - * Initialize the CR4 shadow before doing anything that could - * try to read it. - */ - cr4_init_shadow(); __flush_tlb_all(); #endif load_current_idt(); @@ -263,6 +257,14 @@ static void notrace start_secondary(void *unused) wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + + /* + * Prevent tail call to cpu_startup_entry() because the stack protector + * guard has been changed a couple of function calls up, in + * boot_init_stack_canary() and must not be checked before tail calling + * another function. + */ + prevent_tail_call_optimization(); } /** diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 2d6898c2cb64..6d83b4b857e6 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * or a page fault), which can make frame pointers * unreliable. */ - if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } @@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (unwind_error(&state)) return -EINVAL; - /* Success path for non-user tasks, i.e. kthreads and idle tasks */ - if (!(task->flags & (PF_KTHREAD | PF_IDLE))) - return -EINVAL; - return 0; } diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 01f0e2263b86..298fc1edd9c9 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -90,11 +90,11 @@ __init int create_simplefb(const struct screen_info *si, if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) size <<= 16; length = mode->height * mode->stride; - length = PAGE_ALIGN(length); if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } + length = PAGE_ALIGN(length); /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 0e14f6c0d35e..befb70359551 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -25,10 +25,6 @@ #include <asm/hpet.h> #include <asm/time.h> -#ifdef CONFIG_X86_64 -__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES; -#endif - unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); @@ -37,8 +33,7 @@ unsigned long profile_pc(struct pt_regs *regs) #ifdef CONFIG_FRAME_POINTER return *(unsigned long *)(regs->bp + sizeof(long)); #else - unsigned long *sp = - (unsigned long *)kernel_stack_pointer(regs); + unsigned long *sp = (unsigned long *)regs->sp; /* * Return address is either directly at stack pointer * or above a saved flags. Eflags has bits 22-31 zero, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8b6d03e55d2f..648bfb2b021d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -313,13 +313,10 @@ __visible void __noreturn handle_stack_overflow(const char *message, #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) +dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2) { static const char str[] = "double fault"; struct task_struct *tsk = current; -#ifdef CONFIG_VMAP_STACK - unsigned long cr2; -#endif #ifdef CONFIG_X86_ESPFIX64 extern unsigned char native_irq_return_iret[]; @@ -415,7 +412,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * stack even if the actual trigger for the double fault was * something else. */ - cr2 = read_cr2(); if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE) handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2); #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 0b29e58f288e..f30730621c8a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -665,6 +665,16 @@ unsigned long native_calibrate_tsc(void) if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT) setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); +#ifdef CONFIG_X86_LOCAL_APIC + /* + * The local APIC appears to be fed by the core crystal clock + * (which sounds entirely sensible). We can set the global + * lapic_timer_period here to avoid having to calibrate the APIC + * timer later. + */ + lapic_timer_period = crystal_khz * 1000 / HZ; +#endif + return crystal_khz * ebx_numerator / eax_denominator; } @@ -1488,6 +1498,9 @@ void __init tsc_init(void) return; } + if (tsc_clocksource_reliable || no_tsc_watchdog) + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 3d0e9aeea7c8..6f56071aa909 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -15,18 +15,46 @@ #include <asm/param.h> #include <asm/tsc.h> -#define MAX_NUM_FREQS 9 +#define MAX_NUM_FREQS 16 /* 4 bits to select the frequency */ + +/* + * The frequency numbers in the SDM are e.g. 83.3 MHz, which does not contain a + * lot of accuracy which leads to clock drift. As far as we know Bay Trail SoCs + * use a 25 MHz crystal and Cherry Trail uses a 19.2 MHz crystal, the crystal + * is the source clk for a root PLL which outputs 1600 and 100 MHz. It is + * unclear if the root PLL outputs are used directly by the CPU clock PLL or + * if there is another PLL in between. + * This does not matter though, we can model the chain of PLLs as a single PLL + * with a quotient equal to the quotients of all PLLs in the chain multiplied. + * So we can create a simplified model of the CPU clock setup using a reference + * clock of 100 MHz plus a quotient which gets us as close to the frequency + * from the SDM as possible. + * For the 83.3 MHz example from above this would give us 100 MHz * 5 / 6 = + * 83 and 1/3 MHz, which matches exactly what has been measured on actual hw. + */ +#define TSC_REFERENCE_KHZ 100000 + +struct muldiv { + u32 multiplier; + u32 divider; +}; /* * If MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40]. * Unfortunately some Intel Atom SoCs aren't quite compliant to this, * so we need manually differentiate SoC families. This is what the - * field msr_plat does. + * field use_msr_plat does. */ struct freq_desc { - u8 msr_plat; /* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */ + bool use_msr_plat; + struct muldiv muldiv[MAX_NUM_FREQS]; + /* + * Some CPU frequencies in the SDM do not map to known PLL freqs, in + * that case the muldiv array is empty and the freqs array is used. + */ u32 freqs[MAX_NUM_FREQS]; + u32 mask; }; /* @@ -35,27 +63,74 @@ struct freq_desc { * by MSR based on SDM. */ static const struct freq_desc freq_desc_pnw = { - 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } + .use_msr_plat = false, + .freqs = { 0, 0, 0, 0, 0, 99840, 0, 83200 }, + .mask = 0x07, }; static const struct freq_desc freq_desc_clv = { - 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } + .use_msr_plat = false, + .freqs = { 0, 133200, 0, 0, 0, 99840, 0, 83200 }, + .mask = 0x07, }; +/* + * Bay Trail SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 000: 100 * 5 / 6 = 83.3333 MHz + * 001: 100 * 1 / 1 = 100.0000 MHz + * 010: 100 * 4 / 3 = 133.3333 MHz + * 011: 100 * 7 / 6 = 116.6667 MHz + * 100: 100 * 4 / 5 = 80.0000 MHz + */ static const struct freq_desc freq_desc_byt = { - 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 }, + { 4, 5 } }, + .mask = 0x07, }; +/* + * Cherry Trail SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0000: 100 * 5 / 6 = 83.3333 MHz + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + * 0011: 100 * 7 / 6 = 116.6667 MHz + * 0100: 100 * 4 / 5 = 80.0000 MHz + * 0101: 100 * 14 / 15 = 93.3333 MHz + * 0110: 100 * 9 / 10 = 90.0000 MHz + * 0111: 100 * 8 / 9 = 88.8889 MHz + * 1000: 100 * 7 / 8 = 87.5000 MHz + */ static const struct freq_desc freq_desc_cht = { - 1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 7, 6 }, + { 4, 5 }, { 14, 15 }, { 9, 10 }, { 8, 9 }, + { 7, 8 } }, + .mask = 0x0f, }; +/* + * Merriefield SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + */ static const struct freq_desc freq_desc_tng = { - 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 0, 0 }, { 1, 1 }, { 4, 3 } }, + .mask = 0x07, }; +/* + * Moorefield SDM MSR_FSB_FREQ frequencies simplified PLL model: + * 0000: 100 * 5 / 6 = 83.3333 MHz + * 0001: 100 * 1 / 1 = 100.0000 MHz + * 0010: 100 * 4 / 3 = 133.3333 MHz + * 0011: 100 * 1 / 1 = 100.0000 MHz + */ static const struct freq_desc freq_desc_ann = { - 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } + .use_msr_plat = true, + .muldiv = { { 5, 6 }, { 1, 1 }, { 4, 3 }, { 1, 1 } }, + .mask = 0x0f, }; static const struct x86_cpu_id tsc_msr_cpu_ids[] = { @@ -71,22 +146,24 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = { /* * MSR-based CPU/TSC frequency discovery for certain CPUs. * - * Set global "lapic_timer_frequency" to bus_clock_cycles/jiffy + * Set global "lapic_timer_period" to bus_clock_cycles/jiffy * Return processor base frequency in KHz, or 0 on failure. */ unsigned long cpu_khz_from_msr(void) { - u32 lo, hi, ratio, freq; + u32 lo, hi, ratio, freq, tscref; const struct freq_desc *freq_desc; const struct x86_cpu_id *id; + const struct muldiv *md; unsigned long res; + int index; id = x86_match_cpu(tsc_msr_cpu_ids); if (!id) return 0; freq_desc = (struct freq_desc *)id->driver_data; - if (freq_desc->msr_plat) { + if (freq_desc->use_msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); ratio = (lo >> 8) & 0xff; } else { @@ -96,15 +173,31 @@ unsigned long cpu_khz_from_msr(void) /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); + index = lo & freq_desc->mask; + md = &freq_desc->muldiv[index]; - /* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */ - freq = freq_desc->freqs[lo & 0x7]; + /* + * Note this also catches cases where the index points to an unpopulated + * part of muldiv, in that case the else will set freq and res to 0. + */ + if (md->divider) { + tscref = TSC_REFERENCE_KHZ * md->multiplier; + freq = DIV_ROUND_CLOSEST(tscref, md->divider); + /* + * Multiplying by ratio before the division has better + * accuracy than just calculating freq * ratio. + */ + res = DIV_ROUND_CLOSEST(tscref * ratio, md->divider); + } else { + freq = freq_desc->freqs[index]; + res = freq * ratio; + } - /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ - res = freq * ratio; + if (freq == 0) + pr_err("Error MSR_FSB_FREQ index %d is unknown\n", index); #ifdef CONFIG_X86_LOCAL_APIC - lapic_timer_frequency = (freq * 1000) / HZ; + lapic_timer_period = (freq * 1000) / HZ; #endif /* diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 6106760de716..a224b5ab103f 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -70,15 +70,6 @@ static void unwind_dump(struct unwind_state *state) } } -static size_t regs_size(struct pt_regs *regs) -{ - /* x86_32 regs from kernel mode are two words shorter: */ - if (IS_ENABLED(CONFIG_X86_32) && !user_mode(regs)) - return sizeof(*regs) - 2*sizeof(long); - - return sizeof(*regs); -} - static bool in_entry_code(unsigned long ip) { char *addr = (char *)ip; @@ -198,12 +189,6 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp) } #endif -#ifdef CONFIG_X86_32 -#define KERNEL_REGS_SIZE (sizeof(struct pt_regs) - 2*sizeof(long)) -#else -#define KERNEL_REGS_SIZE (sizeof(struct pt_regs)) -#endif - static bool update_stack_state(struct unwind_state *state, unsigned long *next_bp) { @@ -214,7 +199,7 @@ static bool update_stack_state(struct unwind_state *state, size_t len; if (state->regs) - prev_frame_end = (void *)state->regs + regs_size(state->regs); + prev_frame_end = (void *)state->regs + sizeof(*state->regs); else prev_frame_end = (void *)state->bp + FRAME_HEADER_SIZE; @@ -222,7 +207,7 @@ static bool update_stack_state(struct unwind_state *state, regs = decode_frame_pointer(next_bp); if (regs) { frame = (unsigned long *)regs; - len = KERNEL_REGS_SIZE; + len = sizeof(*regs); state->got_irq = true; } else { frame = next_bp; @@ -246,14 +231,6 @@ static bool update_stack_state(struct unwind_state *state, frame < prev_frame_end) return false; - /* - * On 32-bit with user mode regs, make sure the last two regs are safe - * to access: - */ - if (IS_ENABLED(CONFIG_X86_32) && regs && user_mode(regs) && - !on_stack(info, frame, len + 2*sizeof(long))) - return false; - /* Move state to the next frame: */ if (regs) { state->regs = regs; @@ -412,10 +389,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * Pretend that the frame is complete and that BP points to it, but save * the real BP so that we can use it when looking for the next frame. */ - if (regs && regs->ip == 0 && - (unsigned long *)kernel_stack_pointer(regs) >= first_frame) { + if (regs && regs->ip == 0 && (unsigned long *)regs->sp >= first_frame) { state->next_bp = bp; - bp = ((unsigned long *)kernel_stack_pointer(regs)) - 1; + bp = ((unsigned long *)regs->sp) - 1; } /* Initialize stack info and make sure the frame data is accessible: */ diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 72b997eaa1fc..187a86e0e753 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -142,9 +142,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -314,12 +311,19 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { + struct task_struct *task = state->task; + if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; + if (task != current && state->sp == task->thread.sp) { + struct inactive_task_frame *frame = (void *)task->thread.sp; + return &frame->ret_addr; + } + if (state->sp) return (unsigned long *)state->sp - 1; @@ -378,9 +382,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -398,8 +431,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) { @@ -442,39 +478,35 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { orc_warn("missing regs for base reg R10 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { orc_warn("missing regs for base reg R13 at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { orc_warn("missing regs for base reg DI at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { orc_warn("missing regs for base reg DX at ip %pB\n", (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: @@ -501,6 +533,7 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; @@ -512,6 +545,7 @@ bool unwind_next_frame(struct unwind_state *state) } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; @@ -523,6 +557,8 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; @@ -531,14 +567,14 @@ bool unwind_next_frame(struct unwind_state *state) default: orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -585,20 +621,23 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; + if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err; if (regs) { if (user_mode(regs)) - goto done; + goto the_end; state->ip = regs->ip; - state->sp = kernel_stack_pointer(regs); + state->sp = regs->sp; state->bp = regs->bp; state->regs = regs; state->full_regs = true; @@ -617,6 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = task->thread.sp; state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, @@ -628,6 +668,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -648,13 +689,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; -done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 4d1517022a14..96d8025ea1b0 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -36,13 +36,13 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT) #ifdef CONFIG_X86_32 OUTPUT_ARCH(i386) ENTRY(phys_startup_32) -jiffies = jiffies_64; #else OUTPUT_ARCH(i386:x86-64) ENTRY(phys_startup_64) -jiffies_64 = jiffies; #endif +jiffies = jiffies_64; + #if defined(CONFIG_X86_64) /* * On 64-bit, align RODATA to 2MB so we retain large page mappings for @@ -362,6 +362,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); |