diff options
Diffstat (limited to 'arch/x86/kernel')
35 files changed, 563 insertions, 135 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index b1b78ffe01d0..adaae2c781c1 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -16,9 +16,20 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif -KASAN_SANITIZE_head$(BITS).o := n -KASAN_SANITIZE_dumpstack.o := n -KASAN_SANITIZE_dumpstack_$(BITS).o := n +KASAN_SANITIZE_head$(BITS).o := n +KASAN_SANITIZE_dumpstack.o := n +KASAN_SANITIZE_dumpstack_$(BITS).o := n + +OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_test_nx.o := y + +# If instrumentation of this dir is enabled, boot hangs during first second. +# Probably could be more selective here, but note that files related to irqs, +# boot, dumpstack/stacktrace, etc are either non-interesting or can lead to +# non-deterministic coverage. +KCOV_INSTRUMENT := n CFLAGS_irq.o := -I$(src)/../include/asm/trace diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e75907601a41..8c2f1ef6ca23 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -956,7 +956,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) /* * Note that the LAPIC address is obtained from the MADT (32-bit value) - * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). + * and (optionally) overridden by a LAPIC_ADDR_OVR entry (64-bit value). */ count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, @@ -984,7 +984,7 @@ static int __init acpi_parse_madt_lapic_entries(void) /* * Note that the LAPIC address is obtained from the MADT (32-bit value) - * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). + * and (optionally) overridden by a LAPIC_ADDR_OVR entry (64-bit value). */ count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8c35df468104..169963f471bb 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -5,6 +5,7 @@ #include <asm/page_types.h> #include <asm/msr.h> #include <asm/asm-offsets.h> +#include <asm/frame.h> # Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2 @@ -39,6 +40,7 @@ bogus_64_magic: jmp bogus_64_magic ENTRY(do_suspend_lowlevel) + FRAME_BEGIN subq $8, %rsp xorl %eax, %eax call save_processor_state @@ -109,6 +111,7 @@ ENTRY(do_suspend_lowlevel) xorl %eax, %eax addq $8, %rsp + FRAME_END jmp restore_processor_state ENDPROC(do_suspend_lowlevel) diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 222a57076039..cefacbad1531 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -221,7 +221,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n, unsigned long cpu = (unsigned long)hcpu; struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu); - switch (action & 0xf) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DEAD: dw_apb_clockevent_pause(adev->timer); if (system_state == SYSTEM_RUNNING) { diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 6e85f713641d..0a2bb1f62e72 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -227,19 +227,11 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) return 0; } -static int gart_fix_e820 __initdata = 1; +static bool gart_fix_e820 __initdata = true; static int __init parse_gart_mem(char *p) { - if (!p) - return -EINVAL; - - if (!strncmp(p, "off", 3)) - gart_fix_e820 = 0; - else if (!strncmp(p, "on", 2)) - gart_fix_e820 = 1; - - return 0; + return kstrtobool(p, &gart_fix_e820); } early_param("gart_fix_e820", parse_gart_mem); diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 8bb12ddc5db8..8e63ebdcbd0b 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -2,6 +2,10 @@ # Makefile for local APIC drivers and for the IO-APIC code # +# Leads to non-deterministic coverage that is not a function of syscall inputs. +# In particualr, smp_apic_timer_interrupt() is called in random places. +KCOV_INSTRUMENT := n + obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o vector.o obj-y += hw_nmi.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 531b9611c51d..d356987a04e9 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1611,7 +1611,7 @@ void __init enable_IR_x2apic(void) legacy_pic->mask_all(); mask_ioapic_entries(); - /* If irq_remapping_prepare() succeded, try to enable it */ + /* If irq_remapping_prepare() succeeded, try to enable it */ if (ir_stat >= 0) ir_stat = try_to_enable_IR(); /* ir_stat contains the remap mode or an error code */ diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3b670df4ba7b..ad59d70bcb1a 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -213,6 +213,7 @@ update: */ cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0; d->cfg.vector = vector; cpumask_copy(d->domain, vector_cpumask); success: @@ -655,46 +656,97 @@ void irq_complete_move(struct irq_cfg *cfg) } /* - * Called with @desc->lock held and interrupts disabled. + * Called from fixup_irqs() with @desc->lock held and interrupts disabled. */ void irq_force_complete_move(struct irq_desc *desc) { struct irq_data *irqdata = irq_desc_get_irq_data(desc); struct apic_chip_data *data = apic_chip_data(irqdata); struct irq_cfg *cfg = data ? &data->cfg : NULL; + unsigned int cpu; if (!cfg) return; - __irq_complete_move(cfg, cfg->vector); - /* * This is tricky. If the cleanup of @data->old_domain has not been * done yet, then the following setaffinity call will fail with * -EBUSY. This can leave the interrupt in a stale state. * - * The cleanup cannot make progress because we hold @desc->lock. So in - * case @data->old_domain is not yet cleaned up, we need to drop the - * lock and acquire it again. @desc cannot go away, because the - * hotplug code holds the sparse irq lock. + * All CPUs are stuck in stop machine with interrupts disabled so + * calling __irq_complete_move() would be completely pointless. */ raw_spin_lock(&vector_lock); - /* Clean out all offline cpus (including ourself) first. */ + /* + * Clean out all offline cpus (including the outgoing one) from the + * old_domain mask. + */ cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); - while (!cpumask_empty(data->old_domain)) { + + /* + * If move_in_progress is cleared and the old_domain mask is empty, + * then there is nothing to cleanup. fixup_irqs() will take care of + * the stale vectors on the outgoing cpu. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) { raw_spin_unlock(&vector_lock); - raw_spin_unlock(&desc->lock); - cpu_relax(); - raw_spin_lock(&desc->lock); + return; + } + + /* + * 1) The interrupt is in move_in_progress state. That means that we + * have not seen an interrupt since the io_apic was reprogrammed to + * the new vector. + * + * 2) The interrupt has fired on the new vector, but the cleanup IPIs + * have not been processed yet. + */ + if (data->move_in_progress) { /* - * Reevaluate apic_chip_data. It might have been cleared after - * we dropped @desc->lock. + * In theory there is a race: + * + * set_ioapic(new_vector) <-- Interrupt is raised before update + * is effective, i.e. it's raised on + * the old vector. + * + * So if the target cpu cannot handle that interrupt before + * the old vector is cleaned up, we get a spurious interrupt + * and in the worst case the ioapic irq line becomes stale. + * + * But in case of cpu hotplug this should be a non issue + * because if the affinity update happens right before all + * cpus rendevouz in stop machine, there is no way that the + * interrupt can be blocked on the target cpu because all cpus + * loops first with interrupts enabled in stop machine, so the + * old vector is not yet cleaned up when the interrupt fires. + * + * So the only way to run into this issue is if the delivery + * of the interrupt on the apic/system bus would be delayed + * beyond the point where the target cpu disables interrupts + * in stop machine. I doubt that it can happen, but at least + * there is a theroretical chance. Virtualization might be + * able to expose this, but AFAICT the IOAPIC emulation is not + * as stupid as the real hardware. + * + * Anyway, there is nothing we can do about that at this point + * w/o refactoring the whole fixup_irq() business completely. + * We print at least the irq number and the old vector number, + * so we have the necessary information when a problem in that + * area arises. */ - data = apic_chip_data(irqdata); - if (!data) - return; - raw_spin_lock(&vector_lock); + pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", + irqdata->irq, cfg->old_vector); } + /* + * If old_domain is not empty, then other cpus still have the irq + * descriptor set in their vector array. Clean it up. + */ + for_each_cpu(cpu, data->old_domain) + per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED; + + /* Cleanup the left overs of the (half finished) move */ + cpumask_clear(data->old_domain); + data->move_in_progress = 0; raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 624db00583f4..8f4942e2bcbb 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -792,7 +792,8 @@ static int uv_scir_cpu_notify(struct notifier_block *self, unsigned long action, { long cpu = (long)hcpu; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_FAILED: case CPU_ONLINE: uv_heartbeat_enable(cpu); break; @@ -860,7 +861,7 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode, */ void uv_cpu_init(void) { - /* CPU 0 initilization will be done via uv_system_init. */ + /* CPU 0 initialization will be done via uv_system_init. */ if (!uv_blade_info) return; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 052c9c3026cc..9307f182fe30 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1088,7 +1088,7 @@ static int apm_get_battery_status(u_short which, u_short *status, * @device: identity of device * @enable: on/off * - * Activate or deactive power management on either a specific device + * Activate or deactivate power management on either a specific device * or the entire system (%APM_DEVICE_ALL). */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 0d373d7affc8..4a8697f7d4ef 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -8,6 +8,10 @@ CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_perf_event.o = -pg endif +# If these files are instrumented, boot hangs during the first second. +KCOV_INSTRUMENT_common.o := n +KCOV_INSTRUMENT_perf_event.o := n + # Make sure load_percpu_segment has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 97c59fd60702..6e47e3a916f1 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -75,14 +75,17 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) */ extern __visible void vide(void); -__asm__(".globl vide\n\t.align 4\nvide: ret"); +__asm__(".globl vide\n" + ".type vide, @function\n" + ".align 4\n" + "vide: ret\n"); static void init_amd_k5(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 /* * General Systems BIOSen alias the cpu frequency registers - * of the Elan at 0x000df000. Unfortuantly, one of the Linux + * of the Elan at 0x000df000. Unfortunately, one of the Linux * drivers subsequently pokes it, and changes the CPU speed. * Workaround : Remove the unneeded alias. */ @@ -306,7 +309,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - nodes_per_socket = ((ecx >> 8) & 7) + 1; node_id = ecx & 7; /* get compute unit information */ @@ -317,7 +319,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; node_id = value & 7; } else return; @@ -519,6 +520,18 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_MWAITX)) use_mwaitx_delay(); + + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 ecx; + + ecx = cpuid_ecx(0x8000001e); + nodes_per_socket = ((ecx >> 8) & 7) + 1; + } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + nodes_per_socket = ((value >> 3) & 7) + 1; + } } static void early_init_amd(struct cpuinfo_x86 *c) @@ -536,6 +549,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_sched_clock_stable(); } + /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ + if (c->x86_power & BIT(12)) + set_cpu_cap(c, X86_FEATURE_ACC_POWER); + #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSCALL32); #else diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 249461f95851..8394b3d1f94f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -304,6 +304,48 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) } /* + * Protection Keys are not available in 32-bit mode. + */ +static bool pku_disabled; + +static __always_inline void setup_pku(struct cpuinfo_x86 *c) +{ + if (!cpu_has(c, X86_FEATURE_PKU)) + return; + if (pku_disabled) + return; + + cr4_set_bits(X86_CR4_PKE); + /* + * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE + * cpuid bit to be set. We need to ensure that we + * update that bit in this CPU's "cpu_info". + */ + get_cpu_cap(c); +} + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +static __init int setup_disable_pku(char *arg) +{ + /* + * Do not clear the X86_FEATURE_PKU bit. All of the + * runtime checks are against OSPKE so clearing the + * bit does nothing. + * + * This way, we will see "pku" in cpuinfo, but not + * "ospke", which is exactly what we want. It shows + * that the CPU has PKU, but the OS has not enabled it. + * This happens to be exactly how a system would look + * if we disabled the config option. + */ + pr_info("x86: 'nopku' specified, disabling Memory Protection Keys\n"); + pku_disabled = true; + return 1; +} +__setup("nopku", setup_disable_pku); +#endif /* CONFIG_X86_64 */ + +/* * Some CPU features depend on higher CPUID levels, which may not always * be available due to CPUID level capping or broken virtualization * software. Add those features to this table to auto-disable them. @@ -625,6 +667,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_7_0_EBX] = ebx; c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); + c->x86_capability[CPUID_7_ECX] = ecx; } /* Extended state features: level 0x0000000d */ @@ -649,7 +692,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); c->x86_capability[CPUID_F_1_EDX] = edx; - if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { + if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) || + ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) || + (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) { c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; } @@ -925,7 +970,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_identify) this_cpu->c_identify(c); - /* Clear/Set all flags overriden by options, after probe */ + /* Clear/Set all flags overridden by options, after probe */ for (i = 0; i < NCAPINTS; i++) { c->x86_capability[i] &= ~cpu_caps_cleared[i]; c->x86_capability[i] |= cpu_caps_set[i]; @@ -982,9 +1027,10 @@ static void identify_cpu(struct cpuinfo_x86 *c) init_hypervisor(c); x86_init_rdrand(c); x86_init_cache_qos(c); + setup_pku(c); /* - * Clear/Set all flags overriden by options, need do it + * Clear/Set all flags overridden by options, need do it * before following smp all cpus cap AND. */ for (i = 0; i < NCAPINTS; i++) { diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fcbcb2f678ca..19f57360dfd2 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -42,7 +42,7 @@ EXPORT_SYMBOL_GPL(mtrr_state); * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD * Opteron Processors" (26094 Rev. 3.30 February 2006), section * "13.2.1.2 SYSCFG Register": "The MtrrFixDramModEn bit should be set - * to 1 during BIOS initalization of the fixed MTRRs, then cleared to + * to 1 during BIOS initialization of the fixed MTRRs, then cleared to * 0 for operation." */ static inline void k8_check_syscfg_dram_mod_en(void) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 32e5699eadfe..8efa57a5f29e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -135,7 +135,8 @@ print_context_stack_bp(struct thread_info *tinfo, if (!__kernel_text_address(addr)) break; - ops->address(data, addr, 1); + if (ops->address(data, addr, 1)) + break; frame = frame->next_frame; ret_addr = &frame->return_address; print_ftrace_graph_addr(addr, data, ops, tinfo, graph); @@ -154,10 +155,11 @@ static int print_trace_stack(void *data, char *name) /* * Print one address/symbol entries per line. */ -static void print_trace_address(void *data, unsigned long addr, int reliable) +static int print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); printk_stack_address(addr, reliable, data); + return 0; } static const struct stacktrace_ops print_trace_ops = { diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 21bf92490a7b..8a121991e5ba 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -287,7 +287,7 @@ static __init void early_pci_serial_init(char *s) } /* - * Lastly, initalize the hardware + * Lastly, initialize the hardware */ if (*s) { if (strcmp(s, "nocfg") == 0) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 0b1b9abd4d5f..8e37cc8a539a 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -354,6 +354,69 @@ void fpu__activate_fpstate_write(struct fpu *fpu) } /* + * This function must be called before we write the current + * task's fpstate. + * + * This call gets the current FPU register state and moves + * it in to the 'fpstate'. Preemption is disabled so that + * no writes to the 'fpstate' can occur from context + * swiches. + * + * Must be followed by a fpu__current_fpstate_write_end(). + */ +void fpu__current_fpstate_write_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + /* + * Ensure that the context-switching code does not write + * over the fpstate while we are doing our update. + */ + preempt_disable(); + + /* + * Move the fpregs in to the fpu's 'fpstate'. + */ + fpu__activate_fpstate_read(fpu); + + /* + * The caller is about to write to 'fpu'. Ensure that no + * CPU thinks that its fpregs match the fpstate. This + * ensures we will not be lazy and skip a XRSTOR in the + * future. + */ + fpu->last_cpu = -1; +} + +/* + * This function must be paired with fpu__current_fpstate_write_begin() + * + * This will ensure that the modified fpstate gets placed back in + * the fpregs if necessary. + * + * Note: This function may be called whether or not an _actual_ + * write to the fpstate occurred. + */ +void fpu__current_fpstate_write_end(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + /* + * 'fpu' now has an updated copy of the state, but the + * registers may still be out of date. Update them with + * an XRSTOR if they are active. + */ + if (fpregs_active()) + copy_kernel_to_fpregs(&fpu->state); + + /* + * Our update is done and the fpregs/fpstate are in sync + * if necessary. Context switches can happen again. + */ + preempt_enable(); +} + +/* * 'fpu__restore()' is called to copy FPU registers from * the FPU fpstate to the live hw registers and to activate * access to the hardware registers, so that FPU instructions diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 0bc3490420c5..8bd1c003942a 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -8,7 +8,7 @@ /* * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, * as the "regset->n" for the xstate regset will be updated based on the feature - * capabilites supported by the xsave. + * capabilities supported by the xsave. */ int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 6e8354f5a593..b48ef35b28d4 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -5,6 +5,7 @@ */ #include <linux/compat.h> #include <linux/cpu.h> +#include <linux/pkeys.h> #include <asm/fpu/api.h> #include <asm/fpu/internal.h> @@ -13,6 +14,11 @@ #include <asm/tlbflush.h> +/* + * Although we spell it out in here, the Processor Trace + * xfeature is completely unused. We use other mechanisms + * to save/restore PT state in Linux. + */ static const char *xfeature_names[] = { "x87 floating point registers" , @@ -23,6 +29,8 @@ static const char *xfeature_names[] = "AVX-512 opmask" , "AVX-512 Hi256" , "AVX-512 ZMM_Hi256" , + "Processor Trace (unused)" , + "Protection Keys User registers", "unknown xstate feature" , }; @@ -56,6 +64,7 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_AVX512VL); setup_clear_cpu_cap(X86_FEATURE_MPX); setup_clear_cpu_cap(X86_FEATURE_XGETBV1); + setup_clear_cpu_cap(X86_FEATURE_PKU); } /* @@ -234,7 +243,7 @@ static void __init print_xstate_feature(u64 xstate_mask) const char *feature_name; if (cpu_has_xfeatures(xstate_mask, &feature_name)) - pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name); + pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name); } /* @@ -250,6 +259,7 @@ static void __init print_xstate_features(void) print_xstate_feature(XFEATURE_MASK_OPMASK); print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); + print_xstate_feature(XFEATURE_MASK_PKRU); } /* @@ -466,6 +476,7 @@ static void check_xstate_against_struct(int nr) XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state); XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); + XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state); /* * Make *SURE* to add any feature numbers in below if @@ -473,7 +484,8 @@ static void check_xstate_against_struct(int nr) * numbers. */ if ((nr < XFEATURE_YMM) || - (nr >= XFEATURE_MAX)) { + (nr >= XFEATURE_MAX) || + (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR)) { WARN_ONCE(1, "no structure for xstate: %d\n", nr); XSTATE_WARN_ON(1); } @@ -671,6 +683,19 @@ void fpu__resume_cpu(void) } /* + * Given an xstate feature mask, calculate where in the xsave + * buffer the state is. Callers should ensure that the buffer + * is valid. + * + * Note: does not work for compacted buffers. + */ +void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask) +{ + int feature_nr = fls64(xstate_feature_mask) - 1; + + return (void *)xsave + xstate_comp_offsets[feature_nr]; +} +/* * Given the xsave area and a state inside, this function returns the * address of the state. * @@ -690,7 +715,6 @@ void fpu__resume_cpu(void) */ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) { - int feature_nr = fls64(xstate_feature) - 1; /* * Do we even *have* xsave state? */ @@ -718,7 +742,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) if (!(xsave->header.xfeatures & xstate_feature)) return NULL; - return (void *)xsave + xstate_comp_offsets[feature_nr]; + return __raw_xsave_addr(xsave, xstate_feature); } EXPORT_SYMBOL_GPL(get_xsave_addr); @@ -753,3 +777,156 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } + + +/* + * Set xfeatures (aka XSTATE_BV) bit for a feature that we want + * to take out of its "init state". This will ensure that an + * XRSTOR actually restores the state. + */ +static void fpu__xfeature_set_non_init(struct xregs_state *xsave, + int xstate_feature_mask) +{ + xsave->header.xfeatures |= xstate_feature_mask; +} + +/* + * This function is safe to call whether the FPU is in use or not. + * + * Note that this only works on the current task. + * + * Inputs: + * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, + * XFEATURE_MASK_SSE, etc...) + * @xsave_state_ptr: a pointer to a copy of the state that you would + * like written in to the current task's FPU xsave state. This pointer + * must not be located in the current tasks's xsave area. + * Output: + * address of the state in the xsave area or NULL if the state + * is not present or is in its 'init state'. + */ +static void fpu__xfeature_set_state(int xstate_feature_mask, + void *xstate_feature_src, size_t len) +{ + struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct fpu *fpu = ¤t->thread.fpu; + void *dst; + + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { + WARN_ONCE(1, "%s() attempted with no xsave support", __func__); + return; + } + + /* + * Tell the FPU code that we need the FPU state to be in + * 'fpu' (not in the registers), and that we need it to + * be stable while we write to it. + */ + fpu__current_fpstate_write_begin(); + + /* + * This method *WILL* *NOT* work for compact-format + * buffers. If the 'xstate_feature_mask' is unset in + * xcomp_bv then we may need to move other feature state + * "up" in the buffer. + */ + if (xsave->header.xcomp_bv & xstate_feature_mask) { + WARN_ON_ONCE(1); + goto out; + } + + /* find the location in the xsave buffer of the desired state */ + dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask); + + /* + * Make sure that the pointer being passed in did not + * come from the xsave buffer itself. + */ + WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself"); + + /* put the caller-provided data in the location */ + memcpy(dst, xstate_feature_src, len); + + /* + * Mark the xfeature so that the CPU knows there is state + * in the buffer now. + */ + fpu__xfeature_set_non_init(xsave, xstate_feature_mask); +out: + /* + * We are done writing to the 'fpu'. Reenable preeption + * and (possibly) move the fpstate back in to the fpregs. + */ + fpu__current_fpstate_write_end(); +} + +#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) +#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) + +/* + * This will go out and modify the XSAVE buffer so that PKRU is + * set to a particular state for access to 'pkey'. + * + * PKRU state does affect kernel access to user memory. We do + * not modfiy PKRU *itself* here, only the XSAVE state that will + * be restored in to PKRU when we return back to userspace. + */ +int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, + unsigned long init_val) +{ + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct pkru_state *old_pkru_state; + struct pkru_state new_pkru_state; + int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); + u32 new_pkru_bits = 0; + + /* + * This check implies XSAVE support. OSPKE only gets + * set if we enable XSAVE and we enable PKU in XCR0. + */ + if (!boot_cpu_has(X86_FEATURE_OSPKE)) + return -EINVAL; + + /* Set the bits we need in PKRU */ + if (init_val & PKEY_DISABLE_ACCESS) + new_pkru_bits |= PKRU_AD_BIT; + if (init_val & PKEY_DISABLE_WRITE) + new_pkru_bits |= PKRU_WD_BIT; + + /* Shift the bits in to the correct place in PKRU for pkey. */ + new_pkru_bits <<= pkey_shift; + + /* Locate old copy of the state in the xsave buffer */ + old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU); + + /* + * When state is not in the buffer, it is in the init + * state, set it manually. Otherwise, copy out the old + * state. + */ + if (!old_pkru_state) + new_pkru_state.pkru = 0; + else + new_pkru_state.pkru = old_pkru_state->pkru; + + /* mask off any old bits in place */ + new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); + /* Set the newly-requested bits */ + new_pkru_state.pkru |= new_pkru_bits; + + /* + * We could theoretically live without zeroing pkru.pad. + * The current XSAVE feature state definition says that + * only bytes 0->3 are used. But we do not want to + * chance leaking kernel stack out to userspace in case a + * memcpy() of the whole xsave buffer was done. + * + * They're in the same cacheline anyway. + */ + new_pkru_state.pad = 0; + + fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, + sizeof(new_pkru_state)); + + return 0; +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 702547ce33c9..d036cfb4495d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1,5 +1,5 @@ /* - * Code for replacing ftrace calls with jumps. + * Dynamic function tracing support. * * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> * diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index be0ebbb6d1d1..a1f0e4a5c47e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -717,7 +717,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n, struct hpet_work_struct work; struct hpet_dev *hdev = per_cpu(cpu_hpet_dev, cpu); - switch (action & 0xf) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work); init_completion(&work.complete); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 37dae792dbbe..589b3193f102 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) SYSCALL_DEFINE1(iopl, unsigned int, level) { struct pt_regs *regs = current_pt_regs(); - unsigned int old = (regs->flags >> 12) & 3; struct thread_struct *t = ¤t->thread; + /* + * Careful: the IOPL bits in regs->flags are undefined under Xen PV + * and changing them has no effect. + */ + unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT; + if (level > 3) return -EINVAL; /* Trying to gain more privileges? */ @@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) if (!capable(CAP_SYS_RAWIO)) return -EPERM; } - regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - t->iopl = level << 12; + regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | + (level << X86_EFLAGS_IOPL_BIT); + t->iopl = level << X86_EFLAGS_IOPL_BIT; set_iopl_mask(t->iopl); return 0; diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 0f8a6bbaaa44..2af478e3fd4e 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -271,7 +271,7 @@ static int bzImage64_probe(const char *buf, unsigned long len) int ret = -ENOEXEC; struct setup_header *header; - /* kernel should be atleast two sectors long */ + /* kernel should be at least two sectors long */ if (len < 2 * 512) { pr_err("File is too short to be a bzImage\n"); return ret; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index ed15cd486d06..2da6ee9ae69b 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -609,9 +609,9 @@ static struct notifier_block kgdb_notifier = { }; /** - * kgdb_arch_init - Perform any architecture specific initalization. + * kgdb_arch_init - Perform any architecture specific initialization. * - * This function will handle the initalization of any architecture + * This function will handle the initialization of any architecture * specific callbacks. */ int kgdb_arch_init(void) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 0f05deeff5ce..ae703acb85c1 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -49,6 +49,7 @@ #include <linux/kdebug.h> #include <linux/kallsyms.h> #include <linux/ftrace.h> +#include <linux/frame.h> #include <asm/cacheflush.h> #include <asm/desc.h> @@ -671,39 +672,39 @@ NOKPROBE_SYMBOL(kprobe_int3_handler); * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. */ -static void __used kretprobe_trampoline_holder(void) -{ - asm volatile ( - ".global kretprobe_trampoline\n" - "kretprobe_trampoline: \n" +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 */ - " 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" - RESTORE_REGS_STRING - " popfq\n" + /* We don't bother saving the ss register */ + " 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" + RESTORE_REGS_STRING + " popfq\n" #else - " pushf\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" - RESTORE_REGS_STRING - " popf\n" + " pushf\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" + RESTORE_REGS_STRING + " popf\n" #endif - " ret\n"); -} -NOKPROBE_SYMBOL(kretprobe_trampoline_holder); + " ret\n" + ".size kretprobe_trampoline, .-kretprobe_trampoline\n" +); NOKPROBE_SYMBOL(kretprobe_trampoline); +STACK_FRAME_NON_STANDARD(kretprobe_trampoline); /* * Called from kretprobe_trampoline diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 47190bd399e7..807950860fb7 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -36,6 +36,7 @@ #include <linux/kprobes.h> #include <linux/debugfs.h> #include <linux/nmi.h> +#include <linux/swait.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -91,14 +92,14 @@ static void kvm_io_delay(void) struct kvm_task_sleep_node { struct hlist_node link; - wait_queue_head_t wq; + struct swait_queue_head wq; u32 token; int cpu; bool halted; }; static struct kvm_task_sleep_head { - spinlock_t lock; + raw_spinlock_t lock; struct hlist_head list; } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE]; @@ -122,17 +123,17 @@ void kvm_async_pf_task_wait(u32 token) u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node n, *e; - DEFINE_WAIT(wait); + DECLARE_SWAITQUEUE(wait); rcu_irq_enter(); - spin_lock(&b->lock); + raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { /* dummy entry exist -> wake up was delivered ahead of PF */ hlist_del(&e->link); kfree(e); - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); rcu_irq_exit(); return; @@ -141,13 +142,13 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); n.halted = is_idle_task(current) || preempt_count() > 1; - init_waitqueue_head(&n.wq); + init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); for (;;) { if (!n.halted) - prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; @@ -166,7 +167,7 @@ void kvm_async_pf_task_wait(u32 token) } } if (!n.halted) - finish_wait(&n.wq, &wait); + finish_swait(&n.wq, &wait); rcu_irq_exit(); return; @@ -178,8 +179,8 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) hlist_del_init(&n->link); if (n->halted) smp_send_reschedule(n->cpu); - else if (waitqueue_active(&n->wq)) - wake_up(&n->wq); + else if (swait_active(&n->wq)) + swake_up(&n->wq); } static void apf_task_wake_all(void) @@ -189,14 +190,14 @@ static void apf_task_wake_all(void) for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { struct hlist_node *p, *next; struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; - spin_lock(&b->lock); + raw_spin_lock(&b->lock); hlist_for_each_safe(p, next, &b->list) { struct kvm_task_sleep_node *n = hlist_entry(p, typeof(*n), link); if (n->cpu == smp_processor_id()) apf_task_wake_one(n); } - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); } } @@ -212,7 +213,7 @@ void kvm_async_pf_task_wake(u32 token) } again: - spin_lock(&b->lock); + raw_spin_lock(&b->lock); n = _find_apf_task(b, token); if (!n) { /* @@ -225,17 +226,17 @@ again: * Allocation failed! Busy wait while other cpu * handles async PF. */ - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); cpu_relax(); goto again; } n->token = token; n->cpu = smp_processor_id(); - init_waitqueue_head(&n->wq); + init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); } else apf_task_wake_one(n); - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); @@ -486,7 +487,7 @@ void __init kvm_guest_init(void) paravirt_ops_setup(); register_reboot_notifier(&kvm_pv_reboot_nb); for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) - spin_lock_init(&async_pf_sleepers[i].lock); + raw_spin_lock_init(&async_pf_sleepers[i].lock); if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) x86_init.irqs.trap_init = kvm_apf_trap_init; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 72cef58693c7..1d39bfbd26bb 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -226,7 +226,7 @@ static void kvm_setup_secondary_clock(void) * registered memory location. If the guest happens to shutdown, this memory * won't be valid. In cases like kexec, in which you install a new kernel, this * means a random memory location will be kept being written. So before any - * kind of shutdown from our side, we unregister the clock by writting anything + * kind of shutdown from our side, we unregister the clock by writing anything * that does not have the 'enable' bit set in the msr */ #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 6acc9dd91f36..6707039b9032 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -103,7 +103,7 @@ static void free_ldt_struct(struct ldt_struct *ldt) * we do not have to muck with descriptors here, that is * done in switch_mm() as needed. */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) { struct ldt_struct *new_ldt; struct mm_struct *old_mm; @@ -144,7 +144,7 @@ out_unlock: * * 64bit: Don't touch the LDT register - we're already in the next thread. */ -void destroy_context(struct mm_struct *mm) +void destroy_context_ldt(struct mm_struct *mm) { free_ldt_struct(mm->context.ldt); mm->context.ldt = NULL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b9d99e0f82c4..6cbab31ac23a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -48,6 +48,7 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/xen/hypervisor.h> asmlinkage extern void ret_from_fork(void); @@ -116,6 +117,8 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + if (boot_cpu_has(X86_FEATURE_OSPKE)) + printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru()); } void release_thread(struct task_struct *dead_task) @@ -411,6 +414,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); +#ifdef CONFIG_XEN + /* + * On Xen PV, IOPL bits in pt_regs->flags have no effect, and + * current_pt_regs()->flags may not match the current task's + * intended IOPL. We need to switch it manually. + */ + if (unlikely(static_cpu_has(X86_FEATURE_XENPV) && + prev->iopl != next->iopl)) + xen_set_iopl_mask(next->iopl); +#endif + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but @@ -476,7 +490,7 @@ void set_personality_ia32(bool x32) if (current->mm) current->mm->context.ia32_compat = TIF_X32; current->personality &= ~READ_IMPLIES_EXEC; - /* is_compat_task() uses the presence of the x32 + /* in_compat_syscall() uses the presence of the x32 syscall bit flag to determine compat status */ current_thread_info()->status &= ~TS_COMPAT; } else { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index aa52c1009475..2367ae07eb76 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -112,6 +112,7 @@ #include <asm/alternative.h> #include <asm/prom.h> #include <asm/microcode.h> +#include <asm/mmu_context.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -1282,3 +1283,11 @@ static int __init register_kernel_offset_dumper(void) return 0; } __initcall(register_kernel_offset_dumper); + +void arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) +{ + if (!boot_cpu_has(X86_FEATURE_OSPKE)) + return; + + seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); +} diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 643dbdccf4bc..b2c99f811c3f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -274,11 +274,6 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu) if (test_and_set_bit(pkg, physical_package_map)) goto found; - if (pkg < __max_logical_packages) { - set_bit(pkg, logical_package_map); - physical_to_logical_pkg[pkg] = pkg; - goto found; - } new = find_first_zero_bit(logical_package_map, __max_logical_packages); if (new >= __max_logical_packages) { physical_to_logical_pkg[pkg] = -1; @@ -317,9 +312,27 @@ static void __init smp_init_package_map(void) /* * Today neither Intel nor AMD support heterogenous systems. That * might change in the future.... + * + * While ideally we'd want '* smp_num_siblings' in the below @ncpus + * computation, this won't actually work since some Intel BIOSes + * report inconsistent HT data when they disable HT. + * + * In particular, they reduce the APIC-IDs to only include the cores, + * but leave the CPUID topology to say there are (2) siblings. + * This means we don't know how many threads there will be until + * after the APIC enumeration. + * + * By not including this we'll sometimes over-estimate the number of + * logical packages by the amount of !present siblings, but this is + * still better than MAX_LOCAL_APIC. + * + * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited + * on the command line leading to a similar issue as the HT disable + * problem because the hyperthreads are usually enumerated after the + * primary cores. */ - ncpus = boot_cpu_data.x86_max_cores * smp_num_siblings; - __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); + ncpus = boot_cpu_data.x86_max_cores; + __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); /* * Possibly larger than what we need as the number of apic ids per diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index fdd0c6430e5a..9ee98eefc44d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -14,30 +14,34 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void +static int __save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; #ifdef CONFIG_FRAME_POINTER if (!reliable) - return; + return 0; #endif if (nosched && in_sched_functions(addr)) - return; + return 0; if (trace->skip > 0) { trace->skip--; - return; + return 0; } - if (trace->nr_entries < trace->max_entries) + if (trace->nr_entries < trace->max_entries) { trace->entries[trace->nr_entries++] = addr; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static int save_stack_address(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, false); } -static void +static int save_stack_address_nosched(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, true); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 91a4496db434..e72a07f20b05 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -135,7 +135,7 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, pmd = pmd_alloc(&tboot_mm, pud, vaddr); if (!pmd) return -1; - pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr); + pte = pte_alloc_map(&tboot_mm, pmd, vaddr); if (!pte) return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 56380440d862..c9c4c7ce3eb2 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -881,7 +881,7 @@ void tsc_restore_sched_clock_state(void) local_irq_save(flags); /* - * We're comming out of suspend, there's no concurrency yet; don't + * We're coming out of suspend, there's no concurrency yet; don't * bother being nice about the RCU stuff, just write to both * data fields. */ @@ -1306,11 +1306,15 @@ void __init tsc_init(void) unsigned long calibrate_delay_is_known(void) { int sibling, cpu = smp_processor_id(); + struct cpumask *mask = topology_core_cpumask(cpu); if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC)) return 0; - sibling = cpumask_any_but(topology_core_cpumask(cpu), cpu); + if (!mask) + return 0; + + sibling = cpumask_any_but(mask, cpu); if (sibling < nr_cpu_ids) return cpu_data(sibling).loops_per_jiffy; return 0; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 5af9958cbdb6..d239639e0c1d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -81,11 +81,11 @@ PHDRS { SECTIONS { #ifdef CONFIG_X86_32 - . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR; - phys_startup_32 = startup_32 - LOAD_OFFSET; + . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR; + phys_startup_32 = ABSOLUTE(startup_32 - LOAD_OFFSET); #else - . = __START_KERNEL; - phys_startup_64 = startup_64 - LOAD_OFFSET; + . = __START_KERNEL; + phys_startup_64 = ABSOLUTE(startup_64 - LOAD_OFFSET); #endif /* Text and read-only data */ @@ -333,6 +333,7 @@ SECTIONS __brk_limit = .; } + . = ALIGN(PAGE_SIZE); _end = .; STABS_DEBUG @@ -340,7 +341,10 @@ SECTIONS /* Sections to be discarded */ DISCARDS - /DISCARD/ : { *(.eh_frame) } + /DISCARD/ : { + *(.eh_frame) + *(__func_stack_frame_non_standard) + } } |