diff options
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/acpi/cppc.c | 7 | ||||
-rw-r--r-- | arch/x86/kernel/amd_nb.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/apic/apic.c | 14 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/amd.c | 14 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/bugs.c | 32 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/common.c | 15 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/microcode/amd.c | 51 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/resctrl/core.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 23 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/sgx/main.c | 10 | ||||
-rw-r--r-- | arch/x86/kernel/kvm.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/reboot.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/traps.c | 12 | ||||
-rw-r--r-- | arch/x86/kernel/vmlinux.lds.S | 4 |
14 files changed, 151 insertions, 45 deletions
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 956984054bf3..aab9d0570841 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -110,7 +110,7 @@ static void amd_set_max_freq_ratio(void) static DEFINE_MUTEX(freq_invariance_lock); -void init_freq_invariance_cppc(void) +static inline void init_freq_invariance_cppc(void) { static bool init_done; @@ -127,6 +127,11 @@ void init_freq_invariance_cppc(void) mutex_unlock(&freq_invariance_lock); } +void acpi_processor_init_invariance_cppc(void) +{ + init_freq_invariance_cppc(); +} + /* * Get the highest performance register value. * @cpu: CPU from which to get highest performance. diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index dc5d3216af24..9fe9972d2071 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -44,6 +44,7 @@ #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 +#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4 0x16fc #define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c #define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc #define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 @@ -127,6 +128,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6513c53c9459..c5fb28e6451a 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -440,7 +440,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt) v = apic_read(APIC_LVTT); v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); + + /* + * Setting APIC_LVT_MASKED (above) should be enough to tell + * the hardware that this timer will never fire. But AMD + * erratum 411 and some Intel CPU behavior circa 2024 say + * otherwise. Time for belt and suspenders programming: mask + * the timer _and_ zero the counter registers: + */ + if (v & APIC_LVT_TIMER_TSCDEADLINE) + wrmsrl(MSR_IA32_TSC_DEADLINE, 0); + else + apic_write(APIC_TMICT, 0); + return 0; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 015971adadfc..823f44f7bc94 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -924,6 +924,17 @@ static void init_amd_zen4(struct cpuinfo_x86 *c) { if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); + + /* + * These Zen4 SoCs advertise support for virtualized VMLOAD/VMSAVE + * in some BIOS versions but they can lead to random host reboots. + */ + switch (c->x86_model) { + case 0x18 ... 0x1f: + case 0x60 ... 0x7f: + clear_cpu_cap(c, X86_FEATURE_V_VMSAVE_VMLOAD); + break; + } } static void init_amd_zen5(struct cpuinfo_x86 *c) @@ -1202,5 +1213,6 @@ void amd_check_microcode(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return; - on_each_cpu(zenbleed_check_cpu, NULL, 1); + if (cpu_feature_enabled(X86_FEATURE_ZEN2)) + on_each_cpu(zenbleed_check_cpu, NULL, 1); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d1915427b4ff..47a01d4028f6 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1115,8 +1115,25 @@ do_cmd_auto: case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like SRSO has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); mitigate_smt = true; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); + break; case RETBLEED_MITIGATION_STUFF: @@ -2627,6 +2644,14 @@ static void __init srso_select_mitigation(void) if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like Retbleed has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); } } else { pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); @@ -2638,6 +2663,13 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 07a34d723505..f43bb974fc66 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -69,6 +69,7 @@ #include <asm/sev.h> #include <asm/tdx.h> #include <asm/posted_intr.h> +#include <asm/runtime-const.h> #include "cpu.h" @@ -1443,6 +1444,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) + setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -2085,8 +2089,10 @@ void syscall_init(void) #ifdef CONFIG_STACKPROTECTOR DEFINE_PER_CPU(unsigned long, __stack_chk_guard); +#ifndef CONFIG_SMP EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); #endif +#endif #endif /* CONFIG_X86_64 */ @@ -2386,6 +2392,15 @@ void __init arch_cpu_finalize_init(void) alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { + unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1; + + /* + * Enable this when LAM is gated on LASS support + if (cpu_feature_enabled(X86_FEATURE_LAM)) + USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1; + */ + runtime_const_init(ptr, USER_PTR_MAX); + /* * Make sure the first 2MB area is not mapped by huge pages * There are typically fixed size MTRRs in there and overlapping diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index f63b051f25a0..31a73715d755 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -584,7 +584,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_ native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy); } -static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); +static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size); static int __init save_microcode_in_initrd(void) { @@ -605,7 +605,7 @@ static int __init save_microcode_in_initrd(void) if (!desc.mc) return -EINVAL; - ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size); + ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size); if (ret > UCODE_UPDATED) return -EINVAL; @@ -613,16 +613,19 @@ static int __init save_microcode_in_initrd(void) } early_initcall(save_microcode_in_initrd); -static inline bool patch_cpus_equivalent(struct ucode_patch *p, struct ucode_patch *n) +static inline bool patch_cpus_equivalent(struct ucode_patch *p, + struct ucode_patch *n, + bool ignore_stepping) { /* Zen and newer hardcode the f/m/s in the patch ID */ if (x86_family(bsp_cpuid_1_eax) >= 0x17) { union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id); union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id); - /* Zap stepping */ - p_cid.stepping = 0; - n_cid.stepping = 0; + if (ignore_stepping) { + p_cid.stepping = 0; + n_cid.stepping = 0; + } return p_cid.full == n_cid.full; } else { @@ -644,13 +647,13 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi WARN_ON_ONCE(!n.patch_id); list_for_each_entry(p, µcode_cache, plist) - if (patch_cpus_equivalent(p, &n)) + if (patch_cpus_equivalent(p, &n, false)) return p; return NULL; } -static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) +static inline int patch_newer(struct ucode_patch *p, struct ucode_patch *n) { /* Zen and newer hardcode the f/m/s in the patch ID */ if (x86_family(bsp_cpuid_1_eax) >= 0x17) { @@ -659,6 +662,9 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) zp.ucode_rev = p->patch_id; zn.ucode_rev = n->patch_id; + if (zn.stepping != zp.stepping) + return -1; + return zn.rev > zp.rev; } else { return n->patch_id > p->patch_id; @@ -668,10 +674,14 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) static void update_cache(struct ucode_patch *new_patch) { struct ucode_patch *p; + int ret; list_for_each_entry(p, µcode_cache, plist) { - if (patch_cpus_equivalent(p, new_patch)) { - if (!patch_newer(p, new_patch)) { + if (patch_cpus_equivalent(p, new_patch, true)) { + ret = patch_newer(p, new_patch); + if (ret < 0) + continue; + else if (!ret) { /* we already have the latest patch */ kfree(new_patch->data); kfree(new_patch); @@ -944,21 +954,30 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size) { - struct cpuinfo_x86 *c; - unsigned int nid, cpu; - struct ucode_patch *p; enum ucode_state ret; /* free old equiv table */ free_equiv_cpu_table(); ret = __load_microcode_amd(family, data, size); - if (ret != UCODE_OK) { + if (ret != UCODE_OK) cleanup(); + + return ret; +} + +static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +{ + struct cpuinfo_x86 *c; + unsigned int nid, cpu; + struct ucode_patch *p; + enum ucode_state ret; + + ret = _load_microcode_amd(family, data, size); + if (ret != UCODE_OK) return ret; - } for_each_node(nid) { cpu = cpumask_first(cpumask_of_node(nid)); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 8591d53c144b..b681c2e07dbf 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -207,7 +207,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r) return false; } -static bool __get_mem_config_intel(struct rdt_resource *r) +static __init bool __get_mem_config_intel(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; @@ -241,7 +241,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) return true; } -static bool __rdt_get_mem_config_amd(struct rdt_resource *r) +static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); u32 eax, ebx, ecx, edx, subleaf; diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 50fa1fe9a073..200d89a64027 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -29,10 +29,10 @@ * hardware. The allocated bandwidth percentage is rounded to the next * control step available on the hardware. */ -static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r) { - unsigned long bw; int ret; + u32 bw; /* * Only linear delay values is supported for current Intel SKUs. @@ -42,16 +42,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return false; } - ret = kstrtoul(buf, 10, &bw); + ret = kstrtou32(buf, 10, &bw); if (ret) { - rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); + rdt_last_cmd_printf("Invalid MB value %s\n", buf); return false; } - if ((bw < r->membw.min_bw || bw > r->default_ctrl) && - !is_mba_sc(r)) { - rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, - r->membw.min_bw, r->default_ctrl); + /* Nothing else to do if software controller is enabled. */ + if (is_mba_sc(r)) { + *data = bw; + return true; + } + + if (bw < r->membw.min_bw || bw > r->default_ctrl) { + rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n", + bw, r->membw.min_bw, r->default_ctrl); return false; } @@ -65,7 +70,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct resctrl_staged_config *cfg; u32 closid = data->rdtgrp->closid; struct rdt_resource *r = s->res; - unsigned long bw_val; + u32 bw_val; cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 9ace84486499..eb5848d1851a 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -901,19 +901,15 @@ static struct miscdevice sgx_dev_provision = { int sgx_set_attribute(unsigned long *allowed_attributes, unsigned int attribute_fd) { - struct fd f = fdget(attribute_fd); + CLASS(fd, f)(attribute_fd); - if (!fd_file(f)) + if (fd_empty(f)) return -EINVAL; - if (fd_file(f)->f_op != &sgx_provision_fops) { - fdput(f); + if (fd_file(f)->f_op != &sgx_provision_fops) return -EINVAL; - } *allowed_attributes |= SGX_ATTR_PROVISIONKEY; - - fdput(f); return 0; } EXPORT_SYMBOL_GPL(sgx_set_attribute); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 263f8aed4e2c..21e9e4845354 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -37,6 +37,7 @@ #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> +#include <asm/mtrr.h> #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> #include <asm/ptrace.h> @@ -980,6 +981,9 @@ static void __init kvm_init_platform(void) } kvmclock_init(); x86_platform.apic_post_init = kvm_apic_init; + + /* Set WB as the default cache mode for SEV-SNP and TDX */ + mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); } #if defined(CONFIG_AMD_MEM_ENCRYPT) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0e0a4cf6b5eb..615922838c51 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -530,7 +530,7 @@ static inline void kb_wait(void) static inline void nmi_shootdown_cpus_on_restart(void); -#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) +#if IS_ENABLED(CONFIG_KVM_X86) /* RCU-protected callback to disable virtualization prior to reboot. */ static cpu_emergency_virt_cb __rcu *cpu_emergency_virt_callback; @@ -600,7 +600,7 @@ static void emergency_reboot_disable_virtualization(void) } #else static void emergency_reboot_disable_virtualization(void) { } -#endif /* CONFIG_KVM_INTEL || CONFIG_KVM_AMD */ +#endif /* CONFIG_KVM_X86 */ void __attribute__((weak)) mach_reboot_fixups(void) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d05392db5d0f..2dbadf347b5f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -261,12 +261,6 @@ static noinstr bool handle_bug(struct pt_regs *regs) int ud_type; u32 imm; - /* - * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() - * is a rare case that uses @regs without passing them to - * irqentry_enter(). - */ - kmsan_unpoison_entry_regs(regs); ud_type = decode_bug(regs->ip, &imm); if (ud_type == BUG_NONE) return handled; @@ -276,6 +270,12 @@ static noinstr bool handle_bug(struct pt_regs *regs) */ instrumentation_begin(); /* + * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() + * is a rare case that uses @regs without passing them to + * irqentry_enter(). + */ + kmsan_unpoison_entry_regs(regs); + /* * Since we're emulating a CALL with exceptions, restore the interrupt * state to what it was at the exception site. */ diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 6726be89b7a6..feb8102a9ca7 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -358,6 +358,7 @@ SECTIONS #endif RUNTIME_CONST_VARIABLES + RUNTIME_CONST(ptr, USER_PTR_MAX) . = ALIGN(PAGE_SIZE); @@ -490,6 +491,9 @@ SECTIONS . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +/* needed for Clang - see arch/x86/entry/entry.S */ +PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); + #ifdef CONFIG_X86_64 /* * Per-cpu symbols which need to be offset from __per_cpu_load |