diff options
Diffstat (limited to 'arch/x86/kernel')
41 files changed, 1865 insertions, 479 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 0a1e8a67cc99..c3fba8b52753 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1717,7 +1717,7 @@ 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/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 169963f471bb..50b8ed0317a3 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -109,6 +109,15 @@ ENTRY(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 +#ifdef CONFIG_KASAN + /* + * The suspend path may have poisoned some areas deeper in the stack, + * which we now need to unpoison. + */ + movq %rsp, %rdi + call kasan_unpoison_task_stack_below +#endif + xorl %eax, %eax addq $8, %rsp FRAME_END diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4f2af1ee09cb..722a76b88bcc 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -183,7 +183,7 @@ int first_system_vector = FIRST_SYSTEM_VECTOR; /* * Debug level, exported for io_apic.c */ -unsigned int apic_verbosity; +int apic_verbosity; int pic_mode; @@ -629,7 +629,7 @@ static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2; static __initdata unsigned long lapic_cal_j1, lapic_cal_j2; /* - * Temporary interrupt handler. + * Temporary interrupt handler and polled calibration function. */ static void __init lapic_cal_handler(struct clock_event_device *dev) { @@ -713,7 +713,8 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init calibrate_APIC_clock(void) { struct clock_event_device *levt = this_cpu_ptr(&lapic_events); - void (*real_handler)(struct clock_event_device *dev); + u64 tsc_perj = 0, tsc_start = 0; + unsigned long jif_start; unsigned long deltaj; long delta, deltatsc; int pm_referenced = 0; @@ -742,28 +743,64 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n" "calibrating APIC timer ...\n"); + /* + * There are platforms w/o global clockevent devices. Instead of + * making the calibration conditional on that, use a polling based + * approach everywhere. + */ local_irq_disable(); - /* Replace the global interrupt handler */ - real_handler = global_clock_event->event_handler; - global_clock_event->event_handler = lapic_cal_handler; - /* * Setup the APIC counter to maximum. There is no way the lapic * can underflow in the 100ms detection time frame */ __setup_APIC_LVTT(0xffffffff, 0, 0); - /* Let the interrupts run */ + /* + * Methods to terminate the calibration loop: + * 1) Global clockevent if available (jiffies) + * 2) TSC if available and frequency is known + */ + jif_start = READ_ONCE(jiffies); + + if (tsc_khz) { + tsc_start = rdtsc(); + tsc_perj = div_u64((u64)tsc_khz * 1000, HZ); + } + + /* + * Enable interrupts so the tick can fire, if a global + * clockevent device is available + */ local_irq_enable(); - while (lapic_cal_loops <= LAPIC_CAL_LOOPS) - cpu_relax(); + while (lapic_cal_loops <= LAPIC_CAL_LOOPS) { + /* Wait for a tick to elapse */ + while (1) { + if (tsc_khz) { + u64 tsc_now = rdtsc(); + if ((tsc_now - tsc_start) >= tsc_perj) { + tsc_start += tsc_perj; + break; + } + } else { + unsigned long jif_now = READ_ONCE(jiffies); - local_irq_disable(); + if (time_after(jif_now, jif_start)) { + jif_start = jif_now; + break; + } + } + cpu_relax(); + } - /* Restore the real event handler */ - global_clock_event->event_handler = real_handler; + /* Invoke the calibration routine */ + local_irq_disable(); + lapic_cal_handler(NULL); + local_irq_enable(); + } + + local_irq_disable(); /* Build delta t1-t2 as apic timer counts down */ delta = lapic_cal_t1 - lapic_cal_t2; @@ -814,10 +851,11 @@ static int __init calibrate_APIC_clock(void) levt->features &= ~CLOCK_EVT_FEAT_DUMMY; /* - * PM timer calibration failed or not turned on - * so lets try APIC timer based calibration + * PM timer calibration failed or not turned on so lets try APIC + * timer based calibration, if a global clockevent device is + * available. */ - if (!pm_referenced) { + if (!pm_referenced && global_clock_event) { apic_printk(APIC_VERBOSE, "... verify APIC timer\n"); /* @@ -1243,6 +1281,56 @@ static void lapic_setup_esr(void) oldvalue, value); } +static void apic_pending_intr_clear(void) +{ + long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned long long tsc = 0, ntsc; + unsigned int value, queued; + int i, j, acked = 0; + + if (boot_cpu_has(X86_FEATURE_TSC)) + tsc = rdtsc(); + /* + * After a crash, we no longer service the interrupts and a pending + * interrupt from previous kernel might still have ISR bit set. + * + * Most probably by now CPU has serviced that pending interrupt and + * it might not have done the ack_APIC_irq() because it thought, + * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it + * does not clear the ISR bit and cpu thinks it has already serivced + * the interrupt. Hence a vector might get locked. It was noticed + * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. + */ + do { + queued = 0; + for (i = APIC_ISR_NR - 1; i >= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1<<j)) { + ack_APIC_irq(); + acked++; + } + } + } + if (acked > 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (queued) { + if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { + ntsc = rdtsc(); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); +} + /** * setup_local_APIC - setup the local APIC * @@ -1252,19 +1340,22 @@ static void lapic_setup_esr(void) void setup_local_APIC(void) { int cpu = smp_processor_id(); - unsigned int value, queued; - int i, j, acked = 0; - unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz ? cpu_khz : 1000000; + unsigned int value; - if (boot_cpu_has(X86_FEATURE_TSC)) - tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); return; } + /* + * If this comes from kexec/kcrash the APIC might be enabled in + * SPIV. Soft disable it before doing further initialization. + */ + value = apic_read(APIC_SPIV); + value &= ~APIC_SPIV_APIC_ENABLED; + apic_write(APIC_SPIV, value); + #ifdef CONFIG_X86_32 /* Pound the ESR really hard over the head with a big hammer - mbligh */ if (lapic_is_integrated() && apic->disable_esr) { @@ -1290,16 +1381,21 @@ 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. - */ - i = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - WARN_ON(i != BAD_APICID && i != logical_smp_processor_id()); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = - logical_smp_processor_id(); + 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 /* @@ -1310,45 +1406,7 @@ void setup_local_APIC(void) value &= ~APIC_TPRI_MASK; apic_write(APIC_TASKPRI, value); - /* - * After a crash, we no longer service the interrupts and a pending - * interrupt from previous kernel might still have ISR bit set. - * - * Most probably by now CPU has serviced that pending interrupt and - * it might not have done the ack_APIC_irq() because it thought, - * interrupt came from i8259 as ExtInt. LAPIC did not get EOI so it - * does not clear the ISR bit and cpu thinks it has already serivced - * the interrupt. Hence a vector might get locked. It was noticed - * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. - */ - do { - queued = 0; - for (i = APIC_ISR_NR - 1; i >= 0; i--) - queued |= apic_read(APIC_IRR + i*0x10); - - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<<j)) { - ack_APIC_irq(); - acked++; - } - } - } - if (acked > 256) { - printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", - acked); - break; - } - if (queued) { - if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { - ntsc = rdtsc(); - max_loops = (cpu_khz << 10) - (ntsc - tsc); - } else - max_loops--; - } - } while (queued && max_loops > 0); - WARN_ON(max_loops <= 0); + apic_pending_intr_clear(); /* * Now that we are all set up, enable the APIC diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 56012010332c..76fe153ccc6d 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -37,32 +37,12 @@ static int bigsmp_early_logical_apicid(int cpu) return early_per_cpu(x86_cpu_to_apicid, cpu); } -static inline unsigned long calculate_ldr(int cpu) -{ - unsigned long val, id; - - val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; - id = per_cpu(x86_bios_cpu_apicid, cpu); - val |= SET_APIC_LOGICAL_ID(id); - - return val; -} - /* - * Set up the logical destination ID. - * - * Intel recommends to set DFR, LDR and TPR before enabling - * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel - * document number 292116). So here it goes... + * bigsmp enables physical destination mode + * and doesn't use LDR and DFR */ static void bigsmp_init_apic_ldr(void) { - unsigned long val; - int cpu = smp_processor_id(); - - apic_write(APIC_DFR, APIC_DFR_FLAT); - val = calculate_ldr(cpu); - apic_write(APIC_LDR, val); } static void bigsmp_setup_apic_routing(void) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d34629d70421..3401b28f1312 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1712,9 +1712,10 @@ 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; @@ -1751,7 +1752,9 @@ 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 @@ -2346,7 +2349,13 @@ unsigned int arch_dynirq_lower_bound(unsigned int from) * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use * gsi_top if ioapic_dynirq_base hasn't been initialized yet. */ - return ioapic_initialized ? ioapic_dynirq_base : gsi_top; + if (!ioapic_initialized) + return gsi_top; + /* + * For DT enabled machines ioapic_dynirq_base is irrelevant and not + * updated. So simply return @from if ioapic_dynirq_base == 0. + */ + return ioapic_dynirq_base ? : from; } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 33b63670bf09..f6e386fe510c 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -25,7 +25,7 @@ obj-y += bugs.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel.o tsx.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index be6d0543e626..9428b54fff66 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -746,6 +746,64 @@ static void init_amd_ln(struct cpuinfo_x86 *c) msr_set_bit(MSR_AMD64_DE_CFG, 31); } +static bool rdrand_force; + +static int __init rdrand_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "force")) + rdrand_force = true; + else + return -EINVAL; + + return 0; +} +early_param("rdrand", rdrand_cmdline); + +static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c) +{ + /* + * Saving of the MSR used to hide the RDRAND support during + * suspend/resume is done by arch/x86/power/cpu.c, which is + * dependent on CONFIG_PM_SLEEP. + */ + if (!IS_ENABLED(CONFIG_PM_SLEEP)) + return; + + /* + * The nordrand option can clear X86_FEATURE_RDRAND, so check for + * RDRAND support using the CPUID function directly. + */ + if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force) + return; + + msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62); + + /* + * Verify that the CPUID change has occurred in case the kernel is + * running virtualized and the hypervisor doesn't support the MSR. + */ + if (cpuid_ecx(1) & BIT(30)) { + pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n"); + return; + } + + clear_cpu_cap(c, X86_FEATURE_RDRAND); + pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n"); +} + +static void init_amd_jg(struct cpuinfo_x86 *c) +{ + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); +} + static void init_amd_bd(struct cpuinfo_x86 *c) { u64 value; @@ -760,14 +818,24 @@ static void init_amd_bd(struct cpuinfo_x86 *c) wrmsrl_safe(MSR_F15H_IC_CFG, value); } } + + /* + * Some BIOS implementations do not restore proper RDRAND support + * across suspend and resume. Check on whether to hide the RDRAND + * instruction support via CPUID. + */ + clear_rdrand_cpuid_bit(c); } static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); - /* Fix erratum 1076: CPB feature bit not being set in CPUID. */ - if (!cpu_has(c, X86_FEATURE_CPB)) + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. + * Always set it, except when running under a hypervisor. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) set_cpu_cap(c, X86_FEATURE_CPB); } @@ -801,6 +869,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x16: init_amd_jg(c); break; case 0x17: init_amd_zn(c); break; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 6221166e3fca..24307d5bb4b8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/nospec.h> #include <linux/prctl.h> +#include <linux/sched/smt.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> @@ -24,21 +25,26 @@ #include <asm/vmx.h> #include <asm/paravirt.h> #include <asm/alternative.h> +#include <asm/hypervisor.h> #include <asm/pgtable.h> #include <asm/cacheflush.h> #include <asm/intel-family.h> #include <asm/e820.h> +#include "cpu.h" + +static void __init spectre_v1_select_mitigation(void); 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); -/* - * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any - * writes to SPEC_CTRL contain whatever reserved bits have been set. - */ -u64 __ro_after_init x86_spec_ctrl_base; +/* The base value of the SPEC_CTRL MSR that always has to be preserved. */ +u64 x86_spec_ctrl_base; EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); +static DEFINE_MUTEX(spec_ctrl_mutex); /* * The vendor and possibly platform specific bits which can be modified in @@ -53,6 +59,20 @@ static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; u64 __ro_after_init x86_amd_ls_cfg_base; u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; +/* Control conditional STIPB in switch_to() */ +DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp); +/* Control conditional IBPB in switch_mm() */ +DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); +/* Control unconditional IBPB in switch_mm() */ +DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); + +/* Control MDS CPU buffer clear before returning to user space */ +DEFINE_STATIC_KEY_FALSE(mds_user_clear); +EXPORT_SYMBOL_GPL(mds_user_clear); +/* Control MDS CPU buffer clear before idling (halt, mwait) */ +DEFINE_STATIC_KEY_FALSE(mds_idle_clear); +EXPORT_SYMBOL_GPL(mds_idle_clear); + void __init check_bugs(void) { identify_boot_cpu(); @@ -80,16 +100,21 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_STIBP)) x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper spectre mitigation before patching alternatives */ + /* Select the proper CPU mitigations before patching alternatives: */ + spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); + ssb_select_mitigation(); + l1tf_select_mitigation(); + mds_select_mitigation(); + taa_select_mitigation(); /* - * Select proper mitigation for any exposure to the Speculative Store - * Bypass vulnerability. + * As MDS and TAA mitigations are inter-related, print MDS + * mitigation until after TAA mitigation selection is done. */ - ssb_select_mitigation(); + mds_print_mitigation(); - l1tf_select_mitigation(); + arch_smt_update(); #ifdef CONFIG_X86_32 /* @@ -123,31 +148,6 @@ void __init check_bugs(void) #endif } -/* The kernel command line selection */ -enum spectre_v2_mitigation_cmd { - SPECTRE_V2_CMD_NONE, - SPECTRE_V2_CMD_AUTO, - SPECTRE_V2_CMD_FORCE, - SPECTRE_V2_CMD_RETPOLINE, - SPECTRE_V2_CMD_RETPOLINE_GENERIC, - SPECTRE_V2_CMD_RETPOLINE_AMD, -}; - -static const char *spectre_v2_strings[] = { - [SPECTRE_V2_NONE] = "Vulnerable", - [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", - [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", - [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", - [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", - [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", -}; - -#undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 : " fmt - -static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = - SPECTRE_V2_NONE; - void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { @@ -165,9 +165,14 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + /* Conditional STIBP enabled? */ + if (static_branch_unlikely(&switch_to_cond_stibp)) + hostval |= stibp_tif_to_spec_ctrl(ti->flags); + if (hostval != guestval) { msrval = setguest ? guestval : hostval; wrmsrl(MSR_IA32_SPEC_CTRL, msrval); @@ -201,7 +206,7 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : ssbd_spec_ctrl_to_tif(hostval); - speculative_store_bypass_update(tif); + speculation_ctrl_update(tif); } } EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); @@ -216,6 +221,275 @@ static void x86_amd_ssb_disable(void) wrmsrl(MSR_AMD64_LS_CFG, msrval); } +#undef pr_fmt +#define pr_fmt(fmt) "MDS: " fmt + +/* Default mitigation for MDS-affected CPUs */ +static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL; +static bool mds_nosmt __ro_after_init = false; + +static const char * const mds_strings[] = { + [MDS_MITIGATION_OFF] = "Vulnerable", + [MDS_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", + [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode", +}; + +static void __init mds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) { + mds_mitigation = MDS_MITIGATION_OFF; + return; + } + + if (mds_mitigation == MDS_MITIGATION_FULL) { + if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) + mds_mitigation = MDS_MITIGATION_VMWERV; + + static_branch_enable(&mds_user_clear); + + if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && + (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]); +} + +static int __init mds_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_MDS)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + mds_mitigation = MDS_MITIGATION_OFF; + else if (!strcmp(str, "full")) + mds_mitigation = MDS_MITIGATION_FULL; + else if (!strcmp(str, "full,nosmt")) { + mds_mitigation = MDS_MITIGATION_FULL; + mds_nosmt = true; + } + + return 0; +} +early_param("mds", mds_cmdline); + +#undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* + * 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)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + 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]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V1 : " fmt + +enum spectre_v1_mitigation { + SPECTRE_V1_MITIGATION_NONE, + SPECTRE_V1_MITIGATION_AUTO, +}; + +static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init = + SPECTRE_V1_MITIGATION_AUTO; + +static const char * const spectre_v1_strings[] = { + [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers", + [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization", +}; + +/* + * Does SMAP provide full mitigation against speculative kernel access to + * userspace? + */ +static bool smap_works_speculatively(void) +{ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return false; + + /* + * On CPUs which are vulnerable to Meltdown, SMAP does not + * prevent speculative access to user data in the L1 cache. + * Consider SMAP to be non-functional as a mitigation on these + * CPUs. + */ + if (boot_cpu_has(X86_BUG_CPU_MELTDOWN)) + return false; + + return true; +} + +static void __init spectre_v1_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) { + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return; + } + + if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) { + /* + * With Spectre v1, a user can speculatively control either + * path of a conditional swapgs with a user-controlled GS + * value. The mitigation is to add lfences to both code paths. + * + * If FSGSBASE is enabled, the user can put a kernel address in + * GS, in which case SMAP provides no protection. + * + * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the + * FSGSBASE enablement patches have been merged. ] + * + * If FSGSBASE is disabled, the user can only put a user space + * address in GS. That makes an attack harder, but still + * possible if there's no SMAP protection. + */ + if (!smap_works_speculatively()) { + /* + * Mitigation can be provided from SWAPGS itself or + * PTI as the CR3 write in the Meltdown mitigation + * is serializing. + * + * If neither is there, mitigate with an LFENCE to + * stop speculation through swapgs. + */ + if (boot_cpu_has_bug(X86_BUG_SWAPGS) && + !boot_cpu_has(X86_FEATURE_KAISER)) + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER); + + /* + * Enable lfences in the kernel entry (non-swapgs) + * paths, to prevent user entry from speculatively + * skipping swapgs. + */ + setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL); + } + } + + pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]); +} + +static int __init nospectre_v1_cmdline(char *str) +{ + spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE; + return 0; +} +early_param("nospectre_v1", nospectre_v1_cmdline); + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + +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 = + SPECTRE_V2_USER_NONE; + #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -237,67 +511,225 @@ static inline const char *spectre_v2_module_string(void) static inline const char *spectre_v2_module_string(void) { return ""; } #endif -static void __init spec2_print_if_insecure(const char *reason) +static inline bool match_option(const char *arg, int arglen, const char *opt) { - if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s selected on command line.\n", reason); + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); } -static void __init spec2_print_if_secure(const char *reason) +/* The kernel command line selection for spectre v2 */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +enum spectre_v2_user_cmd { + SPECTRE_V2_USER_CMD_NONE, + SPECTRE_V2_USER_CMD_AUTO, + SPECTRE_V2_USER_CMD_FORCE, + SPECTRE_V2_USER_CMD_PRCTL, + SPECTRE_V2_USER_CMD_PRCTL_IBPB, + SPECTRE_V2_USER_CMD_SECCOMP, + SPECTRE_V2_USER_CMD_SECCOMP_IBPB, +}; + +static const char * const spectre_v2_user_strings[] = { + [SPECTRE_V2_USER_NONE] = "User space: Vulnerable", + [SPECTRE_V2_USER_STRICT] = "User space: Mitigation: STIBP protection", + [SPECTRE_V2_USER_PRCTL] = "User space: Mitigation: STIBP via prctl", + [SPECTRE_V2_USER_SECCOMP] = "User space: Mitigation: STIBP via seccomp and prctl", +}; + +static const struct { + const char *option; + enum spectre_v2_user_cmd cmd; + bool secure; +} v2_user_options[] __initconst = { + { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, + { "off", SPECTRE_V2_USER_CMD_NONE, false }, + { "on", SPECTRE_V2_USER_CMD_FORCE, true }, + { "prctl", SPECTRE_V2_USER_CMD_PRCTL, false }, + { "prctl,ibpb", SPECTRE_V2_USER_CMD_PRCTL_IBPB, false }, + { "seccomp", SPECTRE_V2_USER_CMD_SECCOMP, false }, + { "seccomp,ibpb", SPECTRE_V2_USER_CMD_SECCOMP_IBPB, false }, +}; + +static void __init spec_v2_user_print_cond(const char *reason, bool secure) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s selected on command line.\n", reason); + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure) + pr_info("spectre_v2_user=%s forced on command line.\n", reason); } -static inline bool retp_compiler(void) +static enum spectre_v2_user_cmd __init +spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) { - return __is_defined(RETPOLINE); + char arg[20]; + int ret, i; + + switch (v2_cmd) { + case SPECTRE_V2_CMD_NONE: + return SPECTRE_V2_USER_CMD_NONE; + case SPECTRE_V2_CMD_FORCE: + return SPECTRE_V2_USER_CMD_FORCE; + default: + break; + } + + ret = cmdline_find_option(boot_command_line, "spectre_v2_user", + arg, sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_USER_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) { + if (match_option(arg, ret, v2_user_options[i].option)) { + spec_v2_user_print_cond(v2_user_options[i].option, + v2_user_options[i].secure); + return v2_user_options[i].cmd; + } + } + + pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg); + return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool match_option(const char *arg, int arglen, const char *opt) +static void __init +spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) { - int len = strlen(opt); + enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE; + bool smt_possible = IS_ENABLED(CONFIG_SMP); + enum spectre_v2_user_cmd cmd; - return len == arglen && !strncmp(arg, opt, len); + if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP)) + return; + + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || + cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + smt_possible = false; + + cmd = spectre_v2_parse_user_cmdline(v2_cmd); + switch (cmd) { + case SPECTRE_V2_USER_CMD_NONE: + goto set_mode; + case SPECTRE_V2_USER_CMD_FORCE: + mode = SPECTRE_V2_USER_STRICT; + break; + case SPECTRE_V2_USER_CMD_PRCTL: + case SPECTRE_V2_USER_CMD_PRCTL_IBPB: + mode = SPECTRE_V2_USER_PRCTL; + break; + case SPECTRE_V2_USER_CMD_AUTO: + case SPECTRE_V2_USER_CMD_SECCOMP: + case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPECTRE_V2_USER_SECCOMP; + else + mode = SPECTRE_V2_USER_PRCTL; + break; + } + + /* Initialize Indirect Branch Prediction Barrier */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + + switch (cmd) { + case SPECTRE_V2_USER_CMD_FORCE: + case SPECTRE_V2_USER_CMD_PRCTL_IBPB: + case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: + static_branch_enable(&switch_mm_always_ibpb); + break; + case SPECTRE_V2_USER_CMD_PRCTL: + case SPECTRE_V2_USER_CMD_AUTO: + case SPECTRE_V2_USER_CMD_SECCOMP: + static_branch_enable(&switch_mm_cond_ibpb); + break; + default: + break; + } + + pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", + static_key_enabled(&switch_mm_always_ibpb) ? + "always-on" : "conditional"); + } + + /* If enhanced IBRS is enabled no STIPB required */ + if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + return; + + /* + * If SMT is not possible or STIBP is not available clear the STIPB + * mode. + */ + if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP)) + mode = SPECTRE_V2_USER_NONE; +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]); } +static const char * const spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", + [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", +}; + static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; -} mitigation_options[] = { - { "off", SPECTRE_V2_CMD_NONE, false }, - { "on", SPECTRE_V2_CMD_FORCE, true }, - { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, - { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, - { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, - { "auto", SPECTRE_V2_CMD_AUTO, false }, +} mitigation_options[] __initconst = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, }; +static void __init spec_v2_print_cond(const char *reason, bool secure) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure) + pr_info("%s selected on command line.\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; char arg[20]; int ret, i; - enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; - if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") || + cpu_mitigations_off()) return SPECTRE_V2_CMD_NONE; - else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); - if (ret < 0) - return SPECTRE_V2_CMD_AUTO; - for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { - if (!match_option(arg, ret, mitigation_options[i].option)) - continue; - cmd = mitigation_options[i].cmd; - break; - } + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; - if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", arg); - return SPECTRE_V2_CMD_AUTO; - } + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPECTRE_V2_CMD_AUTO; } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || @@ -314,11 +746,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } - if (mitigation_options[i].secure) - spec2_print_if_secure(mitigation_options[i].option); - else - spec2_print_if_insecure(mitigation_options[i].option); - + spec_v2_print_cond(mitigation_options[i].option, + mitigation_options[i].secure); return cmd; } @@ -400,12 +829,6 @@ specv2_set_mode: setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); - /* Initialize Indirect Branch Prediction Barrier if supported */ - if (boot_cpu_has(X86_FEATURE_IBPB)) { - setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); - } - /* * Retpoline means the kernel is safe because it has no indirect * branches. Enhanced IBRS protects firmware too, so, enable restricted @@ -421,6 +844,107 @@ specv2_set_mode: setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } + + /* Set up IBPB and STIBP depending on the general spectre V2 command */ + spectre_v2_user_select_mitigation(cmd); +} + +static void update_stibp_msr(void * __unused) +{ + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); +} + +/* Update x86_spec_ctrl_base in case SMT state changed. */ +static void update_stibp_strict(void) +{ + u64 mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP; + + if (sched_smt_active()) + mask |= SPEC_CTRL_STIBP; + + if (mask == x86_spec_ctrl_base) + return; + + pr_info("Update user space SMT mitigation: STIBP %s\n", + mask & SPEC_CTRL_STIBP ? "always-on" : "off"); + x86_spec_ctrl_base = mask; + on_each_cpu(update_stibp_msr, NULL, 1); +} + +/* Update the static key controlling the evaluation of TIF_SPEC_IB */ +static void update_indir_branch_cond(void) +{ + if (sched_smt_active()) + static_branch_enable(&switch_to_cond_stibp); + else + static_branch_disable(&switch_to_cond_stibp); +} + +#undef pr_fmt +#define pr_fmt(fmt) fmt + +/* Update the static key controlling the MDS CPU buffer clear in idle */ +static void update_mds_branch_idle(void) +{ + /* + * Enable the idle clearing if SMT is active on CPUs which are + * affected only by MSBDS and not any other MDS variant. + * + * The other variants cannot be mitigated when SMT is enabled, so + * clearing the buffers on idle just to prevent the Store Buffer + * repartitioning leak would be a window dressing exercise. + */ + if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY)) + return; + + if (sched_smt_active()) + static_branch_enable(&mds_idle_clear); + else + static_branch_disable(&mds_idle_clear); +} + +#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" + +void arch_smt_update(void) +{ + mutex_lock(&spec_ctrl_mutex); + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + break; + case SPECTRE_V2_USER_STRICT: + update_stibp_strict(); + break; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + update_indir_branch_cond(); + break; + } + + switch (mds_mitigation) { + case MDS_MITIGATION_FULL: + case MDS_MITIGATION_VMWERV: + if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) + pr_warn_once(MDS_MSG_SMT); + update_mds_branch_idle(); + break; + case MDS_MITIGATION_OFF: + break; + } + + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + + mutex_unlock(&spec_ctrl_mutex); } #undef pr_fmt @@ -437,7 +961,7 @@ enum ssb_mitigation_cmd { SPEC_STORE_BYPASS_CMD_SECCOMP, }; -static const char *ssb_strings[] = { +static const char * const ssb_strings[] = { [SPEC_STORE_BYPASS_NONE] = "Vulnerable", [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", @@ -447,7 +971,7 @@ static const char *ssb_strings[] = { static const struct { const char *option; enum ssb_mitigation_cmd cmd; -} ssb_mitigation_options[] = { +} ssb_mitigation_options[] __initconst = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ @@ -461,7 +985,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) char arg[20]; int ret, i; - if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") || + cpu_mitigations_off()) { return SPEC_STORE_BYPASS_CMD_NONE; } else { ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", @@ -523,6 +1048,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) } /* + * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper + * bit in the mask to allow guests to use the mitigation even in the + * case where the host does not enable it. + */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + } + + /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass @@ -531,18 +1066,15 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) if (mode == SPEC_STORE_BYPASS_DISABLE) { setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); /* - * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses - * a completely different MSR and bit dependent on family. + * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may + * use a completely different MSR and bit dependent on family. */ - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_INTEL: + if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) && + !static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_amd_ssb_disable(); + } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); - break; - case X86_VENDOR_AMD: - x86_amd_ssb_disable(); - break; } } @@ -560,10 +1092,25 @@ static void ssb_select_mitigation(void) #undef pr_fmt #define pr_fmt(fmt) "Speculation prctl: " fmt -static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +static void task_update_spec_tif(struct task_struct *tsk) { - bool update; + /* Force the update of the real TIF bits */ + set_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE); + /* + * Immediately update the speculation control MSRs for the current + * task, but for a non-current task delay setting the CPU + * mitigation until it is scheduled next. + * + * This can only happen for SECCOMP mitigation. For PRCTL it's + * always the current task. + */ + if (tsk == current) + speculation_ctrl_update_current(); +} + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && ssb_mode != SPEC_STORE_BYPASS_SECCOMP) return -ENXIO; @@ -574,28 +1121,56 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) if (task_spec_ssb_force_disable(task)) return -EPERM; task_clear_spec_ssb_disable(task); - update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + task_update_spec_tif(task); break; case PR_SPEC_DISABLE: task_set_spec_ssb_disable(task); - update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + task_update_spec_tif(task); break; case PR_SPEC_FORCE_DISABLE: task_set_spec_ssb_disable(task); task_set_spec_ssb_force_disable(task); - update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + task_update_spec_tif(task); break; default: return -ERANGE; } + return 0; +} - /* - * If being set on non-current task, delay setting the CPU - * mitigation until it is next scheduled. - */ - if (task == current && update) - speculative_store_bypass_update_current(); - +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) + return 0; + /* + * Indirect branch speculation is always disabled in strict + * mode. + */ + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return -EPERM; + task_clear_spec_ib_disable(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + /* + * Indirect branch speculation is always allowed when + * mitigation is force disabled. + */ + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return -EPERM; + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return 0; + task_set_spec_ib_disable(task); + if (ctrl == PR_SPEC_FORCE_DISABLE) + task_set_spec_ib_force_disable(task); + task_update_spec_tif(task); + break; + default: + return -ERANGE; + } return 0; } @@ -605,6 +1180,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_set(task, ctrl); default: return -ENODEV; } @@ -615,6 +1192,8 @@ 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) + ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif @@ -637,11 +1216,35 @@ static int ssb_prctl_get(struct task_struct *task) } } +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: + return PR_SPEC_ENABLE; + case SPECTRE_V2_USER_PRCTL: + case 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: + return PR_SPEC_DISABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_get(task); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_get(task); default: return -ENODEV; } @@ -656,6 +1259,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -713,6 +1319,11 @@ static void __init l1tf_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; + if (cpu_mitigations_off()) + l1tf_mitigation = L1TF_MITIGATION_OFF; + else if (cpu_mitigations_auto_nosmt()) + l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT; + override_cache_bits(&boot_cpu_data); switch (l1tf_mitigation) { @@ -735,12 +1346,13 @@ static void __init l1tf_select_mitigation(void) #endif half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; - if (e820_any_mapped(half_pa, ULLONG_MAX - half_pa, E820_RAM)) { + if (l1tf_mitigation != L1TF_MITIGATION_OFF && + e820_any_mapped(half_pa, ULLONG_MAX - half_pa, E820_RAM)) { pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n", half_pa); pr_info("However, doing so will make a part of your RAM unusable.\n"); - pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n"); + pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n"); return; } @@ -773,13 +1385,14 @@ static int __init l1tf_cmdline(char *str) early_param("l1tf", l1tf_cmdline); #undef pr_fmt +#define pr_fmt(fmt) fmt #ifdef CONFIG_SYSFS #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" #if IS_ENABLED(CONFIG_KVM_INTEL) -static const char *l1tf_vmx_states[] = { +static const char * const l1tf_vmx_states[] = { [VMENTER_L1D_FLUSH_AUTO] = "auto", [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", @@ -795,21 +1408,99 @@ static ssize_t l1tf_show_state(char *buf) if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && - cpu_smt_control == CPU_SMT_ENABLED)) + sched_smt_active())) { return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, l1tf_vmx_states[l1tf_vmx_mitigation]); + } return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, l1tf_vmx_states[l1tf_vmx_mitigation], - cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled"); + sched_smt_active() ? "vulnerable" : "disabled"); +} + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif +static ssize_t mds_show_state(char *buf) +{ +#ifdef CONFIG_HYPERVISOR_GUEST + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); + } +#endif + + if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { + return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); + } + + return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + +static char *stibp_state(void) +{ + if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + return ""; + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + return ", STIBP: disabled"; + case SPECTRE_V2_USER_STRICT: + return ", STIBP: forced"; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + if (static_key_enabled(&switch_to_cond_stibp)) + return ", STIBP: conditional"; + } + return ""; +} + +static char *ibpb_state(void) +{ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + if (static_key_enabled(&switch_mm_always_ibpb)) + return ", IBPB: always-on"; + if (static_key_enabled(&switch_mm_cond_ibpb)) + return ", IBPB: conditional"; + return ", IBPB: disabled"; + } + return ""; +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -824,12 +1515,14 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: - return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", spectre_v2_module_string()); case X86_BUG_SPEC_STORE_BYPASS: @@ -839,6 +1532,16 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) return l1tf_show_state(buf); break; + + case X86_BUG_MDS: + return mds_show_state(buf); + + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -870,4 +1573,19 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b { return cpu_show_common(dev, attr, buf, X86_BUG_L1TF); } + +ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_MDS); +} + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3c01610c5ba9..f490a4fab2f7 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -388,7 +388,7 @@ 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 @@ -752,6 +752,12 @@ static void init_speculation_control(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_STIBP); set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); } + + if (cpu_has(c, X86_FEATURE_AMD_SSBD)) { + set_cpu_cap(c, X86_FEATURE_SSBD); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + clear_cpu_cap(c, X86_FEATURE_VIRT_SSBD); + } } void get_cpu_cap(struct cpuinfo_x86 *c) @@ -885,84 +891,134 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) c->x86_cache_bits = c->x86_phys_bits; } -static const __initconst struct x86_cpu_id cpu_no_speculation[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_CENTAUR, 5 }, - { X86_VENDOR_INTEL, 5 }, - { X86_VENDOR_NSC, 5 }, - { X86_VENDOR_ANY, 4 }, - {} -}; +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) -static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { - { X86_VENDOR_AMD }, - {} -}; +#define VULNWL(_vendor, _family, _model, _whitelist) \ + { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } -static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, - { X86_VENDOR_CENTAUR, 5, }, - { X86_VENDOR_INTEL, 5, }, - { X86_VENDOR_NSC, 5, }, - { X86_VENDOR_AMD, 0x12, }, - { X86_VENDOR_AMD, 0x11, }, - { X86_VENDOR_AMD, 0x10, }, - { X86_VENDOR_AMD, 0xf, }, - { X86_VENDOR_ANY, 4, }, - {} -}; +#define VULNWL_INTEL(model, whitelist) \ + VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist) + +#define VULNWL_AMD(family, whitelist) \ + VULNWL(AMD, family, X86_MODEL_ANY, whitelist) + +static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { + VULNWL(ANY, 4, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION), + VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), + + /* Intel Family 6 */ + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(CORE_YONAH, NO_SSB), + + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + + /* + * Technically, swapgs isn't serializing on AMD (despite it previously + * being documented as such in the APM). But according to AMD, %gs is + * updated non-speculatively, and the issuing of %gs-relative memory + * operands will be blocked until the %gs update completes, which is + * good enough for our purposes. + */ + + /* AMD Family 0xf - 0x12 */ + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), -static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { - /* in addition to cpu_no_speculation */ - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), {} }; -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +static bool __init cpu_matches(unsigned long which) +{ + const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); + + return m && !!(m->driver_data & which); +} + +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!x86_match_cpu(cpu_no_spec_store_bypass) && - !(ia32_cap & ARCH_CAP_SSB_NO)) - setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + return ia32_cap; +} + +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)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); - if (x86_match_cpu(cpu_no_speculation)) + if (cpu_matches(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) && + !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 (x86_match_cpu(cpu_no_meltdown)) + if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + setup_force_cpu_bug(X86_BUG_MDS); + if (cpu_matches(MSBDS_ONLY)) + setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); + } + + if (!cpu_matches(NO_SWAPGS)) + setup_force_cpu_bug(X86_BUG_SWAPGS); + + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + + if (cpu_matches(NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -971,7 +1027,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (x86_match_cpu(cpu_no_l1tf)) + if (cpu_matches(NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); @@ -1380,6 +1436,8 @@ void __init identify_boot_cpu(void) enable_sep_cpu(); #endif cpu_detect_tlb(&boot_cpu_data); + + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2275900d4d1b..4350f50b5deb 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -44,6 +44,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); extern int detect_extended_topology_early(struct cpuinfo_x86 *c); @@ -51,4 +67,6 @@ extern int detect_ht_early(struct cpuinfo_x86 *c); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d39cfb2c6b63..a4f6e0ec4ba0 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -121,7 +121,7 @@ static void set_cx86_reorder(void) setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* Load/Store Serialize to mem access disable (=reorder it) */ - setCx86_old(CX86_PCR0, getCx86_old(CX86_PCR0) & ~0x80); + setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80); /* set load/store serialize from 1GB to 4GB */ ccr3 |= 0xe0; setCx86(CX86_CCR3, ccr3); @@ -132,11 +132,11 @@ static void set_cx86_memwb(void) pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); /* CCR2 bit 2: unlock NW bit */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) & ~0x04); /* set 'Not Write-through' */ write_cr0(read_cr0() | X86_CR0_NW); /* CCR2 bit 2: lock NW bit and set WT1 */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x14); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } /* @@ -150,14 +150,14 @@ static void geode_configure(void) local_irq_save(flags); /* Suspend on halt power saving and enable #SUSP pin */ - setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) | 0x88); + setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* FPU fast, DTE cache, Mem bypass */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x38); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38); setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ set_cx86_memwb(); @@ -293,7 +293,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { /* Enable cxMMX extensions (GX1 Datasheet 54) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7) | 1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1); /* * GXm : 0x30 ... 0x5f GXm datasheet 51 @@ -316,7 +316,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) if (dir1 > 7) { dir0_msn++; /* M II */ /* Enable MMX extensions (App note 108) */ - setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); + setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1); } else { /* A 6x86MX - it has the bug. */ set_cpu_bug(c, X86_BUG_COMA); @@ -434,7 +434,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c) /* enable MAPEN */ setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable cpuid */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80); /* disable MAPEN */ setCx86(CX86_CCR3, ccr3); local_irq_restore(flags); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index cee0fec0d232..476a9d5c2f35 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -14,6 +14,7 @@ #include <asm/bugs.h> #include <asm/cpu.h> #include <asm/intel-family.h> +#include <asm/microcode_intel.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -137,14 +138,8 @@ static void early_init_intel(struct cpuinfo_x86 *c) (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); - if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) { - unsigned lower_word; - - wrmsr(MSR_IA32_UCODE_REV, 0, 0); - /* Required by the SDM */ - sync_core(); - rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); - } + if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) + c->microcode = intel_get_microcode_revision(); /* Now if any of them are set, check the blacklist and clear the lot */ if ((cpu_has(c, X86_FEATURE_SPEC_CTRL) || @@ -647,6 +642,11 @@ static void init_intel(struct cpuinfo_x86 *c) detect_vmx_virtcap(c); init_intel_energy_perf(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 3e0199ee5a2f..0372913e0134 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -148,6 +148,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), KERNEL ), + MCESEV( + PANIC, "Instruction fetch error in kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 25310d2b8609..07188a012492 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -139,6 +139,8 @@ void mce_setup(struct mce *m) m->socketid = cpu_data(m->extcpu).phys_proc_id; m->apicid = cpu_data(m->extcpu).initial_apicid; rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); + + m->microcode = boot_cpu_data.microcode; } DEFINE_PER_CPU(struct mce, injectm); @@ -309,7 +311,7 @@ static void print_mce(struct mce *m) */ pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, - cpu_data(m->extcpu).microcode); + m->microcode); pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } @@ -671,20 +673,50 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) barrier(); m.status = mce_rdmsrl(msr_ops.status(i)); + + /* If this entry is not valid, ignore it */ if (!(m.status & MCI_STATUS_VAL)) continue; /* - * Uncorrected or signalled events are handled by the exception - * handler when it is enabled, so don't process those here. - * - * TBD do the same check for MCI_STATUS_EN here? + * If we are logging everything (at CPU online) or this + * is a corrected error, then we must log it. */ - if (!(flags & MCP_UC) && - (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) - continue; + if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC)) + goto log_it; + + /* + * Newer Intel systems that support software error + * recovery need to make additional checks. Other + * CPUs should skip over uncorrected errors, but log + * everything else. + */ + if (!mca_cfg.ser) { + if (m.status & MCI_STATUS_UC) + continue; + goto log_it; + } + + /* Log "not enabled" (speculative) errors */ + if (!(m.status & MCI_STATUS_EN)) + goto log_it; + /* + * Log UCNA (SDM: 15.6.3 "UCR Error Classification") + * UC == 1 && PCC == 0 && S == 0 + */ + if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S)) + goto log_it; + + /* + * Skip anything else. Presumption is that our read of this + * bank is racing with a machine check. Leave the log alone + * for do_machine_check() to deal with it. + */ + continue; + +log_it: error_seen = true; mce_read_aux(&m, i); @@ -750,8 +782,8 @@ 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; @@ -1616,36 +1648,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; - /* - * Turn off MC4_MISC thresholding banks on those models since - * they're not supported there. - */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { - int i; - u64 hwcr; - bool need_toggle; - u32 msrs[] = { - 0x00000413, /* MC4_MISC0 */ - 0xc0000408, /* MC4_MISC1 */ - }; - - rdmsrl(MSR_K7_HWCR, hwcr); - - /* McStatusWrEn has to be set */ - need_toggle = !(hwcr & BIT(18)); - - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); - - /* Clear CntP bit safely */ - for (i = 0; i < ARRAY_SIZE(msrs); i++) - msr_clear_bit(msrs[i], 62); - - /* restore old settings */ - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr); - } } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 39526e1e3132..775d5f028fe8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -499,6 +499,40 @@ out: return offset; } +/* + * Turn off MC4_MISC thresholding banks on all family 0x15 models since + * they're not supported there. + */ +void disable_err_thresholding(struct cpuinfo_x86 *c) +{ + int i; + u64 hwcr; + bool need_toggle; + u32 msrs[] = { + 0x00000413, /* MC4_MISC0 */ + 0xc0000408, /* MC4_MISC1 */ + }; + + if (c->x86 != 0x15) + return; + + rdmsrl(MSR_K7_HWCR, hwcr); + + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); + + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + + /* Clear CntP bit safely */ + for (i = 0; i < ARRAY_SIZE(msrs); i++) + msr_clear_bit(msrs[i], 62); + + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -506,6 +540,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int bank, block, cpu = smp_processor_id(); int offset = -1; + disable_err_thresholding(c); + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) get_smca_bank_info(bank); @@ -810,9 +846,12 @@ 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) @@ -843,8 +882,9 @@ 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; @@ -888,16 +928,12 @@ 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: @@ -905,7 +941,7 @@ 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; @@ -990,8 +1026,6 @@ 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)) { atomic_set(&b->cpus, 1); @@ -1002,9 +1036,13 @@ 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); @@ -1038,8 +1076,12 @@ static int threshold_create_device(unsigned int cpu) 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; @@ -1049,13 +1091,11 @@ 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/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index c460c91d0c8f..be2439592b0e 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -190,7 +190,7 @@ static int 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/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 732bb03fcf91..a19fddfb6bf8 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -707,22 +707,26 @@ int apply_microcode_amd(int cpu) return -1; /* need to apply patch? */ - if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return 0; - } + if (rev >= mc_amd->hdr.patch_id) + goto out; if (__apply_microcode_amd(mc_amd)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); return -1; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); + +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; return 0; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 79291d6fb301..1308abfc4758 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -386,15 +386,8 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); csig.pf = 1 << ((val[1] >> 18) & 7); } - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - - csig.rev = val[1]; + csig.rev = intel_get_microcode_revision(); uci->cpu_sig = csig; uci->valid = 1; @@ -618,29 +611,35 @@ static inline void print_ucode(struct ucode_cpu_info *uci) static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc; - unsigned int val[2]; + u32 rev; mc = uci->mc; if (!mc) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + return 0; + } + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc->hdr.rev) + rev = intel_get_microcode_revision(); + if (rev != mc->hdr.rev) return -1; #ifdef CONFIG_X86_64 /* Flush global tlb. This is precaution. */ flush_tlb_early(); #endif - uci->cpu_sig.rev = val[1]; + uci->cpu_sig.rev = rev; if (early) print_ucode(uci); @@ -903,9 +902,9 @@ static int apply_microcode_intel(int cpu) { struct microcode_intel *mc; struct ucode_cpu_info *uci; - struct cpuinfo_x86 *c; - unsigned int val[2]; + struct cpuinfo_x86 *c = &cpu_data(cpu); static int prev_rev; + u32 rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) @@ -924,35 +923,42 @@ static int apply_microcode_intel(int cpu) if (!get_matching_mc(mc, cpu)) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) + goto out; + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - wrmsrl(MSR_IA32_UCODE_REV, 0); - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); + rev = intel_get_microcode_revision(); - /* get the current revision from MSR 0x8B */ - rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - - if (val[1] != mc->hdr.rev) { + if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); return -1; } - if (val[1] != prev_rev) { + if (rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", - val[1], + rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, (mc->hdr.date >> 16) & 0xff); - prev_rev = val[1]; + prev_rev = rev; } - c = &cpu_data(cpu); +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; - uci->cpu_sig.rev = val[1]; - c->microcode = val[1]; + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; return 0; } diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 6988c74409a8..711b74e0e623 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -3,6 +3,8 @@ # Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h # +set -e + IN=$1 OUT=$2 diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..032509adf9de --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("tsx: invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * 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) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * 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/hpet.c b/arch/x86/kernel/hpet.c index 756634f14df6..775c23d4021a 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -914,6 +914,8 @@ int __init hpet_enable(void) return 0; hpet_set_mapping(); + if (!hpet_virt_address) + return 0; /* * Read the period and check for a sane value: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8771766d46b6..9954a604a822 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -352,6 +352,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) #endif default: WARN_ON_ONCE(1); + return -EINVAL; } /* diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index bcd1b82c86e8..005e9a77a664 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -25,9 +25,18 @@ int sysctl_panic_on_stackoverflow; /* * Probabilistic stack overflow check: * - * Only check the stack in process context, because everything else - * runs on the big interrupt stacks. Checking reliably is too expensive, - * so we just check from interrupts. + * Regular device interrupts can enter on the following stacks: + * + * - User stack + * + * - Kernel task stack + * + * - Interrupt stack if a device driver reenables interrupts + * which should only happen in really old drivers. + * + * - Debug IST stack + * + * All other contexts are invalid. */ static inline void stack_overflow_check(struct pt_regs *regs) { @@ -52,8 +61,8 @@ static inline void stack_overflow_check(struct pt_regs *regs) return; oist = this_cpu_ptr(&orig_ist); - estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN; - estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1]; + estack_bottom = (u64)oist->ist[DEBUG_STACK]; + estack_top = estack_bottom - DEBUG_STKSZ + STACK_TOP_MARGIN; if (regs->sp >= estack_top && regs->sp <= estack_bottom) return; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 8e36f249646e..904e18bb38c5 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -438,7 +438,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs) */ void kgdb_roundup_cpus(unsigned long flags) { - apic->send_IPI_allbutself(APIC_DM_NMI); + apic->send_IPI_allbutself(NMI_VECTOR); } #endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 64a70b2e2285..dcd6df5943d6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -376,6 +376,10 @@ int __copy_instruction(u8 *dest, u8 *src) return 0; memcpy(dest, insn.kaddr, length); + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(&insn)) + return 0; + #ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { s64 newdisp; @@ -545,6 +549,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs); ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -746,15 +751,21 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false; 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(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = ®s->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -776,8 +787,25 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + } orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr); if (orig_ret_address != trampoline_address) /* @@ -795,6 +823,8 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue; orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index bfe4d6c96fbd..6b7b35d80264 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -32,6 +32,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> #include <asm/cache.h> +#include <asm/nospec-branch.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -544,6 +545,9 @@ nmi_restart: write_cr2(this_cpu_read(nmi_cr2)); if (this_cpu_dec_return(nmi_state)) goto nmi_restart; + + if (user_mode(regs)) + mds_user_clear_cpu_buffers(); } NOKPROBE_SYMBOL(do_nmi); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e9195a139d4e..f1f3c471438f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -35,6 +35,8 @@ #include <asm/switch_to.h> #include <asm/spec-ctrl.h> +#include "process.h" + /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, * no more per-task TSS's. The TSS size is kept cacheline-aligned @@ -170,11 +172,12 @@ int set_tsc_mode(unsigned int val) return 0; } -static inline void switch_to_bitmap(struct tss_struct *tss, - struct thread_struct *prev, +static inline void switch_to_bitmap(struct thread_struct *prev, struct thread_struct *next, unsigned long tifp, unsigned long tifn) { + struct tss_struct *tss = this_cpu_ptr(&cpu_tss); + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. @@ -308,32 +311,85 @@ static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); } -static __always_inline void intel_set_ssb_state(unsigned long tifn) +/* + * Update the MSRs managing speculation control, during context switch. + * + * tifp: Previous task's thread flags + * tifn: Next task's thread flags + */ +static __always_inline void __speculation_ctrl_update(unsigned long tifp, + unsigned long tifn) { - u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn); + unsigned long tif_diff = tifp ^ tifn; + u64 msr = x86_spec_ctrl_base; + bool updmsr = false; + + /* + * 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)) { + amd_set_ssb_virt_state(tifn); + } else if (static_cpu_has(X86_FEATURE_LS_CFG_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; + } + } + + /* + * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled, + * otherwise avoid the MSR write. + */ + if (IS_ENABLED(CONFIG_SMP) && + static_branch_unlikely(&switch_to_cond_stibp)) { + updmsr |= !!(tif_diff & _TIF_SPEC_IB); + msr |= stibp_tif_to_spec_ctrl(tifn); + } - wrmsrl(MSR_IA32_SPEC_CTRL, msr); + if (updmsr) + wrmsrl(MSR_IA32_SPEC_CTRL, msr); } -static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) { - if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) - amd_set_ssb_virt_state(tifn); - else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) - amd_set_core_ssb_state(tifn); - else - intel_set_ssb_state(tifn); + if (test_and_clear_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE)) { + if (task_spec_ssb_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SSBD); + else + clear_tsk_thread_flag(tsk, TIF_SSBD); + + if (task_spec_ib_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SPEC_IB); + else + clear_tsk_thread_flag(tsk, TIF_SPEC_IB); + } + /* Return the updated threadinfo flags*/ + return task_thread_info(tsk)->flags; } -void speculative_store_bypass_update(unsigned long tif) +void speculation_ctrl_update(unsigned long tif) { + /* Forced update. Make sure all relevant TIF flags are different */ preempt_disable(); - __speculative_store_bypass_update(tif); + __speculation_ctrl_update(~tif, tif); preempt_enable(); } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) +/* Called from seccomp/prctl update */ +void speculation_ctrl_update_current(void) +{ + preempt_disable(); + speculation_ctrl_update(speculation_ctrl_update_tif(current)); + preempt_enable(); +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev, *next; unsigned long tifp, tifn; @@ -343,7 +399,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, tifn = READ_ONCE(task_thread_info(next_p)->flags); tifp = READ_ONCE(task_thread_info(prev_p)->flags); - switch_to_bitmap(tss, prev, next, tifp, tifn); + switch_to_bitmap(prev, next, tifp, tifn); propagate_user_return_notify(prev_p, next_p); @@ -361,8 +417,15 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOTSC) cr4_toggle_bits(X86_CR4_TSD); - if ((tifp ^ tifn) & _TIF_SSBD) - __speculative_store_bypass_update(tifn); + if (likely(!((tifp | tifn) & _TIF_SPEC_FORCE_UPDATE))) { + __speculation_ctrl_update(tifp, tifn); + } else { + speculation_ctrl_update_tif(prev_p); + tifn = speculation_ctrl_update_tif(next_p); + + /* Enforce MSR update to ensure consistent state */ + __speculation_ctrl_update(~tifn, tifn); + } } /* diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h new file mode 100644 index 000000000000..898e97cf6629 --- /dev/null +++ b/arch/x86/kernel/process.h @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Code shared between 32 and 64 bit + +#include <asm/spec-ctrl.h> + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p); + +/* + * This needs to be inline to optimize for the common case where no extra + * work needs to be done. + */ +static inline void switch_to_extra(struct task_struct *prev, + struct task_struct *next) +{ + unsigned long next_tif = task_thread_info(next)->flags; + unsigned long prev_tif = task_thread_info(prev)->flags; + + if (IS_ENABLED(CONFIG_SMP)) { + /* + * Avoid __switch_to_xtra() invocation when conditional + * STIPB is disabled and the only different bit is + * TIF_SPEC_IB. For CONFIG_SMP=n TIF_SPEC_IB is not + * in the TIF_WORK_CTXSW masks. + */ + if (!static_branch_likely(&switch_to_cond_stibp)) { + prev_tif &= ~_TIF_SPEC_IB; + next_tif &= ~_TIF_SPEC_IB; + } + } + + /* + * __switch_to_xtra() handles debug registers, i/o bitmaps, + * speculation mitigations etc. + */ + if (unlikely(next_tif & _TIF_WORK_CTXSW_NEXT || + prev_tif & _TIF_WORK_CTXSW_PREV)) + __switch_to_xtra(prev, next); +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index bd7be8efdc4c..4ca26fc7aa89 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,6 +55,8 @@ #include <asm/switch_to.h> #include <asm/vm86.h> +#include "process.h" + void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; @@ -127,6 +129,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, struct task_struct *tsk; int err; + /* + * For a new task use the RESET flags value since there is no before. + * All the status flags are zero; DF and all the system flags must also + * be 0, specifically IF must be 0 because we context switch to the new + * task with interrupts disabled. + */ + frame->flags = X86_EFLAGS_FIXED; frame->bp = 0; frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; @@ -264,12 +273,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl)) set_iopl_mask(next->iopl); - /* - * Now maybe handle debug registers and/or IO bitmaps - */ - if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || - task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) - __switch_to_xtra(prev_p, next_p, tss); + switch_to_extra(prev_p, next_p); /* * Leave lazy mode, flushing any hypercalls made here. diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a2661814bde0..6d6c15cd9b9a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,6 +51,8 @@ #include <asm/xen/hypervisor.h> #include <asm/vdso.h> +#include "process.h" + __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ @@ -266,6 +268,14 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, childregs = task_pt_regs(p); fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; + + /* + * For a new task use the RESET flags value since there is no before. + * All the status flags are zero; DF and all the system flags must also + * be 0, specifically IF must be 0 because we context switch to the new + * task with interrupts disabled. + */ + frame->flags = X86_EFLAGS_FIXED; frame->bp = 0; frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; @@ -454,12 +464,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* Reload esp0 and ss1. This changes current_thread_info(). */ load_sp0(tss, next); - /* - * Now maybe reload the debug registers and handle I/O bitmaps - */ - if (unlikely(task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT || - task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) - __switch_to_xtra(prev_p, next_p, tss); + switch_to_extra(prev_p, next_p); #ifdef CONFIG_XEN /* diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index e497d374412a..7f377f8792aa 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -23,6 +23,7 @@ #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/context_tracking.h> +#include <linux/nospec.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -652,7 +653,8 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) unsigned long val = 0; if (n < HBP_NUM) { - struct perf_event *bp = thread->ptrace_bps[n]; + int index = array_index_nospec(n, HBP_NUM); + struct perf_event *bp = thread->ptrace_bps[index]; if (bp) val = bp->hw.info.address; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 4a12362a194a..c55b11fe8e9f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -82,6 +82,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) return 0; } +/* + * Some machines don't handle the default ACPI reboot method and + * require the EFI reboot method: + */ +static int __init set_efi_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) { + reboot_type = BOOT_EFI; + pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident); + } + return 0; +} + void __noreturn machine_real_restart(unsigned int type) { local_irq_disable(); @@ -167,6 +180,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), }, }, + { /* Handle reboot issue on Acer TravelMate X514-51T */ + .callback = set_efi_reboot, + .ident = "Acer TravelMate X514-51T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"), + }, + }, /* Apple */ { /* Handle problems with rebooting on Apple MacBook5 */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index b1a5d252d482..ca010dfb9682 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -129,16 +129,6 @@ static int restore_sigcontext(struct pt_regs *regs, COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); -#ifdef CONFIG_X86_64 - /* - * Fix up SS if needed for the benefit of old DOSEMU and - * CRIU. - */ - if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && - user_64bit_mode(regs))) - force_valid_ss(regs); -#endif - get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ @@ -147,6 +137,15 @@ static int restore_sigcontext(struct pt_regs *regs, buf = (void __user *)buf_val; } get_user_catch(err); +#ifdef CONFIG_X86_64 + /* + * Fix up SS if needed for the benefit of old DOSEMU and + * CRIU. + */ + if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) + force_valid_ss(regs); +#endif + err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); force_iret(); @@ -458,6 +457,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, { struct rt_sigframe __user *frame; void __user *fp = NULL; + unsigned long uc_flags; int err = 0; frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); @@ -470,9 +470,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, return -EFAULT; } + uc_flags = frame_uc_flags(regs); + put_user_try { /* Create the ucontext. */ - put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); + put_user_ex(uc_flags, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); save_altstack_ex(&frame->uc.uc_stack, regs->sp); @@ -538,6 +540,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, { #ifdef CONFIG_X86_X32_ABI struct rt_sigframe_x32 __user *frame; + unsigned long uc_flags; void __user *restorer; int err = 0; void __user *fpstate = NULL; @@ -552,9 +555,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig, return -EFAULT; } + uc_flags = frame_uc_flags(regs); + put_user_try { /* Create the ucontext. */ - put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags); + put_user_ex(uc_flags, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 2863ad306692..33ba47c44816 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -181,6 +181,12 @@ asmlinkage __visible void smp_reboot_interrupt(void) irq_exit(); } +static int register_stop_handler(void) +{ + return register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, + NMI_FLAG_FIRST, "smp_stop"); +} + static void native_stop_other_cpus(int wait) { unsigned long flags; @@ -214,39 +220,41 @@ static void native_stop_other_cpus(int wait) apic->send_IPI_allbutself(REBOOT_VECTOR); /* - * Don't wait longer than a second if the caller - * didn't ask us to wait. + * Don't wait longer than a second for IPI completion. The + * wait request is not checked here because that would + * prevent an NMI shutdown attempt in case that not all + * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; - while (num_online_cpus() > 1 && (wait || timeout--)) + while (num_online_cpus() > 1 && timeout--) udelay(1); } - - /* if the REBOOT_VECTOR didn't work, try with the NMI */ - if ((num_online_cpus() > 1) && (!smp_no_nmi_ipi)) { - if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback, - NMI_FLAG_FIRST, "smp_stop")) - /* Note: we ignore failures here */ - /* Hope the REBOOT_IRQ is good enough */ - goto finish; - - /* sync above data before sending IRQ */ - wmb(); - pr_emerg("Shutting down cpus with NMI\n"); + /* if the REBOOT_VECTOR didn't work, try with the NMI */ + if (num_online_cpus() > 1) { + /* + * If NMI IPI is enabled, try to register the stop handler + * and send the IPI. In any case try to wait for the other + * CPUs to stop. + */ + if (!smp_no_nmi_ipi && !register_stop_handler()) { + /* Sync above data before sending IRQ */ + wmb(); - apic->send_IPI_allbutself(NMI_VECTOR); + pr_emerg("Shutting down cpus with NMI\n"); + apic->send_IPI_allbutself(NMI_VECTOR); + } /* - * Don't wait longer than a 10 ms if the caller - * didn't ask us to wait. + * Don't wait longer than 10 ms if the caller didn't + * reqeust it. If wait is true, the machine hangs here if + * one or more CPUs do not reach shutdown state. */ timeout = USEC_PER_MSEC * 10; while (num_online_cpus() > 1 && (wait || timeout--)) udelay(1); } -finish: local_irq_save(flags); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 623965e86b65..897da526e40e 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -231,9 +231,55 @@ static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { {}, }; +/* + * Some devices have a portrait LCD but advertise a landscape resolution (and + * pitch). We simply swap width and height for these devices so that we can + * correctly deal with some of them coming with multiple resolutions. + */ +static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { + { + /* + * Lenovo MIIX310-10ICR, only some batches have the troublesome + * 800x1280 portrait screen. Luckily the portrait version has + * its own BIOS version, so we match on that. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"), + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"), + }, + }, + { + /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo MIIX 320-10ICR"), + }, + }, + { + /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, + "Lenovo ideapad D330-10IGM"), + }, + }, + {}, +}; + __init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) dmi_check_system(efifb_dmi_system_table); + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && + dmi_check_system(efifb_dmi_swap_width_height)) { + u16 temp = screen_info.lfb_width; + + screen_info.lfb_width = screen_info.lfb_height; + screen_info.lfb_height = temp; + screen_info.lfb_linelength = 4 * screen_info.lfb_width; + } } diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 85195d447a92..f3215346e47f 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -94,11 +94,11 @@ __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/tls.c b/arch/x86/kernel/tls.c index 9692a5e9fdab..b95693a73f12 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -4,6 +4,7 @@ #include <linux/user.h> #include <linux/regset.h> #include <linux/syscalls.h> +#include <linux/nospec.h> #include <asm/uaccess.h> #include <asm/desc.h> @@ -219,6 +220,7 @@ int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *u_info) { struct user_desc info; + int index; if (idx == -1 && get_user(idx, &u_info->entry_number)) return -EFAULT; @@ -226,8 +228,11 @@ int do_get_thread_area(struct task_struct *p, int idx, if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; - fill_user_desc(&info, idx, - &p->thread.tls_array[idx - GDT_ENTRY_TLS_MIN]); + index = idx - GDT_ENTRY_TLS_MIN; + index = array_index_nospec(index, + GDT_ENTRY_TLS_MAX - GDT_ENTRY_TLS_MIN + 1); + + fill_user_desc(&info, idx, &p->thread.tls_array[index]); if (copy_to_user(u_info, &info, sizeof(info))) return -EFAULT; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 769c370011d6..cb768417429d 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -713,7 +713,7 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index a2456d4d286a..9b8b3cb2e934 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -6,6 +6,21 @@ #define FRAME_HEADER_SIZE (sizeof(long) * 2) +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + if (task == current) \ + val = READ_ONCE(x); \ + else \ + val = READ_ONCE_NOCHECK(x); \ + val; \ +}) + unsigned long unwind_get_return_address(struct unwind_state *state) { unsigned long addr; @@ -14,7 +29,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state) if (unwind_done(state)) return 0; - addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, + addr = READ_ONCE_TASK_STACK(state->task, *addr_p); + addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); return __kernel_text_address(addr) ? addr : 0; @@ -48,7 +64,7 @@ bool unwind_next_frame(struct unwind_state *state) if (unwind_done(state)) return false; - next_bp = (unsigned long *)*state->bp; + next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp); /* make sure the next frame's data is accessible */ if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE)) diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index e78a6b1db74b..73391c1bd2a9 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -296,6 +296,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool if (is_prefix_bad(insn)) return -ENOTSUPP; + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(insn)) + return -ENOTSUPP; + if (x86_64) good_insns = good_insns_64; else @@ -514,9 +518,12 @@ struct uprobe_xol_ops { void (*abort)(struct arch_uprobe *, struct pt_regs *); }; -static inline int sizeof_long(void) +static inline int sizeof_long(struct pt_regs *regs) { - return in_ia32_syscall() ? 4 : 8; + /* + * Check registers for mode as in_xxx_syscall() does not apply here. + */ + return user_64bit_mode(regs) ? 8 : 4; } static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) @@ -527,9 +534,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) static int push_ret_address(struct pt_regs *regs, unsigned long ip) { - unsigned long new_sp = regs->sp - sizeof_long(); + unsigned long new_sp = regs->sp - sizeof_long(regs); - if (copy_to_user((void __user *)new_sp, &ip, sizeof_long())) + if (copy_to_user((void __user *)new_sp, &ip, sizeof_long(regs))) return -EFAULT; regs->sp = new_sp; @@ -562,7 +569,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs long correction = utask->vaddr - utask->xol_vaddr; regs->ip += correction; } else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) { - regs->sp += sizeof_long(); /* Pop incorrect return address */ + regs->sp += sizeof_long(regs); /* Pop incorrect return address */ if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen)) return -ERESTART; } @@ -671,7 +678,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) * "call" insn was executed out-of-line. Just restore ->sp and restart. * We could also restore ->ip and try to call branch_emulate_op() again. */ - regs->sp += sizeof_long(); + regs->sp += sizeof_long(regs); return -ERESTART; } @@ -962,7 +969,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) { - int rasize = sizeof_long(), nleft; + int rasize = sizeof_long(regs), nleft; unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize)) @@ -980,7 +987,7 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); - force_sig_info(SIGSEGV, SEND_SIG_FORCED, current); + force_sig(SIGSEGV, current); } return -1; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index e783a5daaab2..55f04875293f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -367,7 +367,7 @@ SECTIONS * Per-cpu symbols which need to be offset from __per_cpu_load * for the boot processor. */ -#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load +#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load INIT_PER_CPU(gdt_page); INIT_PER_CPU(irq_stack_union); |