diff options
Diffstat (limited to 'arch/x86/kernel')
60 files changed, 982 insertions, 825 deletions
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index aae7456ece07..1d85cb7071cb 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -30,6 +30,7 @@ #include <asm/fixmap.h> #include <asm/paravirt.h> #include <asm/asm-prototypes.h> +#include <asm/cfi.h> int __read_mostly alternatives_patched; @@ -160,7 +161,6 @@ extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern s32 __return_sites[], __return_sites_end[]; extern s32 __cfi_sites[], __cfi_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; -extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -395,6 +395,63 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) } } +/* Low-level backend functions usable from alternative code replacements. */ +DEFINE_ASM_FUNC(nop_func, "", .entry.text); +EXPORT_SYMBOL_GPL(nop_func); + +noinstr void BUG_func(void) +{ + BUG(); +} +EXPORT_SYMBOL(BUG_func); + +#define CALL_RIP_REL_OPCODE 0xff +#define CALL_RIP_REL_MODRM 0x15 + +/* + * Rewrite the "call BUG_func" replacement to point to the target of the + * indirect pv_ops call "call *disp(%ip)". + */ +static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) +{ + void *target, *bug = &BUG_func; + s32 disp; + + if (a->replacementlen != 5 || insn_buff[0] != CALL_INSN_OPCODE) { + pr_err("ALT_FLAG_DIRECT_CALL set for a non-call replacement instruction\n"); + BUG(); + } + + if (a->instrlen != 6 || + instr[0] != CALL_RIP_REL_OPCODE || + instr[1] != CALL_RIP_REL_MODRM) { + pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n"); + BUG(); + } + + /* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */ + disp = *(s32 *)(instr + 2); +#ifdef CONFIG_X86_64 + /* ff 15 00 00 00 00 call *0x0(%rip) */ + /* target address is stored at "next instruction + disp". */ + target = *(void **)(instr + a->instrlen + disp); +#else + /* ff 15 00 00 00 00 call *0x0 */ + /* target address is stored at disp. */ + target = *(void **)disp; +#endif + if (!target) + target = bug; + + /* (BUG_func - .) + (target - BUG_func) := target - . */ + *(s32 *)(insn_buff + 1) += target - bug; + + if (target == &nop_func) + return 0; + + return 5; +} + /* * Replace instructions with better alternatives for this CPU type. This runs * before SMP is initialized to avoid SMP problems with self modifying code. @@ -452,16 +509,21 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, continue; } - DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", - (a->flags & ALT_FLAG_NOT) ? "!" : "", + DPRINTK(ALT, "feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d) flags: 0x%x", a->cpuid >> 5, a->cpuid & 0x1f, instr, instr, a->instrlen, - replacement, a->replacementlen); + replacement, a->replacementlen, a->flags); memcpy(insn_buff, replacement, a->replacementlen); insn_buff_sz = a->replacementlen; + if (a->flags & ALT_FLAG_DIRECT_CALL) { + insn_buff_sz = alt_replace_call(instr, insn_buff, a); + if (insn_buff_sz < 0) + continue; + } + for (; insn_buff_sz < a->instrlen; insn_buff_sz++) insn_buff[insn_buff_sz] = 0x90; @@ -842,15 +904,82 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } #endif /* CONFIG_X86_KERNEL_IBT */ #ifdef CONFIG_FINEIBT +#define __CFI_DEFAULT CFI_DEFAULT +#elif defined(CONFIG_CFI_CLANG) +#define __CFI_DEFAULT CFI_KCFI +#else +#define __CFI_DEFAULT CFI_OFF +#endif -enum cfi_mode { - CFI_DEFAULT, - CFI_OFF, - CFI_KCFI, - CFI_FINEIBT, -}; +enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT; + +#ifdef CONFIG_CFI_CLANG +struct bpf_insn; + +/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ +extern unsigned int __bpf_prog_runX(const void *ctx, + const struct bpf_insn *insn); + +/* + * Force a reference to the external symbol so the compiler generates + * __kcfi_typid. + */ +__ADDRESSABLE(__bpf_prog_runX); + +/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_hash,@object \n" +" .globl cfi_bpf_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_hash: \n" +" .long __kcfi_typeid___bpf_prog_runX \n" +" .size cfi_bpf_hash, 4 \n" +" .popsection \n" +); + +/* Must match bpf_callback_t */ +extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); + +__ADDRESSABLE(__bpf_callback_fn); + +/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_subprog_hash,@object \n" +" .globl cfi_bpf_subprog_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_subprog_hash: \n" +" .long __kcfi_typeid___bpf_callback_fn \n" +" .size cfi_bpf_subprog_hash, 4 \n" +" .popsection \n" +); + +u32 cfi_get_func_hash(void *func) +{ + u32 hash; + + func -= cfi_get_offset(); + switch (cfi_mode) { + case CFI_FINEIBT: + func += 7; + break; + case CFI_KCFI: + func += 1; + break; + default: + return 0; + } + + if (get_kernel_nofault(hash, func)) + return 0; + + return hash; +} +#endif + +#ifdef CONFIG_FINEIBT -static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT; static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; @@ -1159,8 +1288,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, goto err; if (cfi_rand) { - if (builtin) + if (builtin) { cfi_seed = get_random_u32(); + cfi_bpf_hash = cfi_rehash(cfi_bpf_hash); + cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash); + } ret = cfi_rand_preamble(start_cfi, end_cfi); if (ret) @@ -1421,46 +1553,6 @@ int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_PARAVIRT - -/* Use this to add nops to a buffer, then text_poke the whole buffer. */ -static void __init_or_module add_nops(void *insns, unsigned int len) -{ - while (len > 0) { - unsigned int noplen = len; - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - memcpy(insns, x86_nops[noplen], noplen); - insns += noplen; - len -= noplen; - } -} - -void __init_or_module apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{ - struct paravirt_patch_site *p; - char insn_buff[MAX_PATCH_LEN]; - - for (p = start; p < end; p++) { - unsigned int used; - - BUG_ON(p->len > MAX_PATCH_LEN); - /* prep the buffer with the original instructions */ - memcpy(insn_buff, p->instr, p->len); - used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len); - - BUG_ON(used > p->len); - - /* Pad the rest with nops */ - add_nops(insn_buff + used, p->len - used); - text_poke_early(p->instr, insn_buff, p->len); - } -} -extern struct paravirt_patch_site __start_parainstructions[], - __stop_parainstructions[]; -#endif /* CONFIG_PARAVIRT */ - /* * Self-test for the INT3 based CALL emulation code. * @@ -1596,28 +1688,11 @@ void __init alternative_instructions(void) */ /* - * Paravirt patching and alternative patching can be combined to - * replace a function call with a short direct code sequence (e.g. - * by setting a constant return value instead of doing that in an - * external function). - * In order to make this work the following sequence is required: - * 1. set (artificial) features depending on used paravirt - * functions which can later influence alternative patching - * 2. apply paravirt patching (generally replacing an indirect - * function call with a direct one) - * 3. apply alternative patching (e.g. replacing a direct function - * call with a custom code sequence) - * Doing paravirt patching after alternative patching would clobber - * the optimization of the custom code with a function call again. + * Make sure to set (artificial) features depending on used paravirt + * functions which can later influence alternative patching. */ paravirt_set_cap(); - /* - * First patch paravirt functions, such that we overwrite the indirect - * call with the direct call. - */ - apply_paravirt(__parainstructions, __parainstructions_end); - __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); @@ -1628,10 +1703,6 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); - /* - * Then patch alternatives, such that those paravirt calls that are in - * alternatives can be overwritten by their immediate fragments. - */ apply_alternatives(__alt_instructions, __alt_instructions_end); /* @@ -1906,7 +1977,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l * Note that the caller must ensure that if the modified code is part of a * module, the module would not be removed during poking. This can be achieved * by registering a module notifier, and ordering module removal and patching - * trough a mutex. + * through a mutex. */ void *text_poke(void *addr, const void *opcode, size_t len) { diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 56a917df410d..2ae98f754e59 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -776,7 +776,7 @@ int __init gart_iommu_init(void) iommu_size >> PAGE_SHIFT); /* * Tricky. The GART table remaps the physical memory range, - * so the CPU wont notice potential aliases and if the memory + * so the CPU won't notice potential aliases and if the memory * is remapped to UC later on, we might surprise the PCI devices * with a stray writeout of a cacheline. So play it sure and * do an explicit, full-scale wbinvd() _after_ having marked all diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 4feaa670d578..89c0c8a3fc7e 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -259,10 +259,9 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) order); } - /* No multi-function device? */ type = read_pci_config_byte(bus, slot, func, PCI_HEADER_TYPE); - if (!(type & 0x80)) + if (!(type & PCI_HEADER_TYPE_MFD)) break; } } diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 2ee867d796d9..3bf0487cf3b7 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -4,7 +4,7 @@ # # Leads to non-deterministic coverage that is not a function of syscall inputs. -# In particualr, smp_apic_timer_interrupt() is called in random places. +# In particular, smp_apic_timer_interrupt() is called in random places. KCOV_INSTRUMENT := n obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_common.o apic_noop.o ipi.o vector.o init.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 41093cf20acd..4667bc4b00ab 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -782,7 +782,7 @@ bool __init apic_needs_pit(void) /* * If interrupt delivery mode is legacy PIC or virtual wire without - * configuration, the local APIC timer wont be set up. Make sure + * configuration, the local APIC timer won't be set up. Make sure * that the PIT is initialized. */ if (apic_intr_mode == APIC_PIC || diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 7139867d69cd..b295a056a4fc 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -82,7 +82,6 @@ static struct apic apic_flat __ro_after_init = { .acpi_madt_oem_check = flat_acpi_madt_oem_check, .apic_id_registered = default_apic_id_registered, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, @@ -154,7 +153,6 @@ static struct apic apic_physflat __ro_after_init = { .acpi_madt_oem_check = physflat_acpi_madt_oem_check, .apic_id_registered = default_apic_id_registered, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index b00d52ae84fa..9f1d553eb48f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -47,7 +47,6 @@ static void noop_apic_write(u32 reg, u32 val) struct apic apic_noop __ro_after_init = { .name = "noop", - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 456a14c44f67..7d0c51b9d3bc 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -222,7 +222,6 @@ static const struct apic apic_numachip1 __refconst = { .probe = numachip1_probe, .acpi_madt_oem_check = numachip1_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, @@ -259,7 +258,6 @@ static const struct apic apic_numachip2 __refconst = { .probe = numachip2_probe, .acpi_madt_oem_check = numachip2_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 7ee3c486cb33..5a0d60b38e6b 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -80,7 +80,6 @@ static struct apic apic_bigsmp __ro_after_init = { .name = "bigsmp", .probe = probe_bigsmp, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 1, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07d..40c7cf180c20 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -997,7 +997,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, /* * Legacy ISA IRQ has already been allocated, just add pin to * the pin list associated with this IRQ and program the IOAPIC - * entry. The IOAPIC entry + * entry. */ if (irq_data && irq_data->parent_data) { if (!mp_check_pin_attr(irq, info)) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 5eb3fbe472da..c0f78059f06a 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -45,7 +45,6 @@ static struct apic apic_default __ro_after_init = { .probe = probe_default, .apic_id_registered = default_apic_id_registered, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 319448d87b99..185738c72766 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -738,8 +738,8 @@ int __init arch_probe_nr_irqs(void) void lapic_assign_legacy_vector(unsigned int irq, bool replace) { /* - * Use assign system here so it wont get accounted as allocated - * and moveable in the cpu hotplug check and it prevents managed + * Use assign system here so it won't get accounted as allocated + * and movable in the cpu hotplug check and it prevents managed * irq reservation from touching it. */ irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index a8306089c91b..28a7d3f2312d 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -227,7 +227,6 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .probe = x2apic_cluster_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 558a4a8824f4..409815a40668 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -145,7 +145,6 @@ static struct apic apic_x2apic_phys __ro_after_init = { .probe = x2apic_phys_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1b0d7336a28f..f1766b18dcd0 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -805,7 +805,6 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .probe = uv_probe, .acpi_madt_oem_check = uv_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5934ee5bc087..76a5ced278c2 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -420,7 +420,7 @@ static DEFINE_MUTEX(apm_mutex); * This is for buggy BIOS's that refer to (real mode) segment 0x40 * even though they are called in protected mode. */ -static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(0x4092, +static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(DESC_DATA32_BIOS, (unsigned long)__va(0x400UL), PAGE_SIZE - 0x400 - 1); static const char driver_version[] = "1.16ac"; /* no spaces */ diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index e9ad518a5003..64ad2ddea121 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -233,14 +233,13 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct) } static __init_or_module void -patch_paravirt_call_sites(struct paravirt_patch_site *start, - struct paravirt_patch_site *end, - const struct core_text *ct) +patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end, + const struct core_text *ct) { - struct paravirt_patch_site *p; + struct alt_instr *a; - for (p = start; p < end; p++) - patch_call(p->instr, ct); + for (a = start; a < end; a++) + patch_call((void *)&a->instr_offset + a->instr_offset, ct); } static __init_or_module void @@ -248,7 +247,7 @@ callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct) { prdbg("Patching call sites %s\n", ct->name); patch_call_sites(cs->call_start, cs->call_end, ct); - patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct); + patch_alt_call_sites(cs->alt_start, cs->alt_end, ct); prdbg("Patching call sites done%s\n", ct->name); } @@ -257,8 +256,8 @@ void __init callthunks_patch_builtin_calls(void) struct callthunk_sites cs = { .call_start = __call_sites, .call_end = __call_sites_end, - .pv_start = __parainstructions, - .pv_end = __parainstructions_end + .alt_start = __alt_instructions, + .alt_end = __alt_instructions_end }; if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c index 8674a5c0c031..e6bf78fac146 100644 --- a/arch/x86/kernel/cfi.c +++ b/arch/x86/kernel/cfi.c @@ -4,10 +4,10 @@ * * Copyright (C) 2022 Google LLC */ -#include <asm/cfi.h> +#include <linux/string.h> +#include <linux/cfi.h> #include <asm/insn.h> #include <asm/insn-eval.h> -#include <linux/string.h> /* * Returns the target address and the expected type when regs->ip points diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f322ebd053a9..f3abca334199 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -34,87 +34,6 @@ */ static u32 nodes_per_socket = 1; -/* - * AMD errata checking - * - * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or - * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that - * have an OSVW id assigned, which it takes as first argument. Both take a - * variable number of family-specific model-stepping ranges created by - * AMD_MODEL_RANGE(). - * - * Example: - * - * const int amd_erratum_319[] = - * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), - * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), - * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); - */ - -#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } -#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } -#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ - ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) -#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) -#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) -#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) - -static const int amd_erratum_400[] = - AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), - AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); - -static const int amd_erratum_383[] = - AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); - -/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ -static const int amd_erratum_1054[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - -static const int amd_zenbleed[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), - AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), - AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), - AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); - -static const int amd_div0[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), - AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); - -static const int amd_erratum_1485[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf), - AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf)); - -static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) -{ - int osvw_id = *erratum++; - u32 range; - u32 ms; - - if (osvw_id >= 0 && osvw_id < 65536 && - cpu_has(cpu, X86_FEATURE_OSVW)) { - u64 osvw_len; - - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); - if (osvw_id < osvw_len) { - u64 osvw_bits; - - rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), - osvw_bits); - return osvw_bits & (1ULL << (osvw_id & 0x3f)); - } - } - - /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_stepping; - while ((range = *erratum++)) - if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && - (ms >= AMD_MODEL_RANGE_START(range)) && - (ms <= AMD_MODEL_RANGE_END(range))) - return true; - - return false; -} - static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -616,6 +535,62 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } resctrl_cpu_detect(c); + + /* Figure out Zen generations: */ + switch (c->x86) { + case 0x17: + switch (c->x86_model) { + case 0x00 ... 0x2f: + case 0x50 ... 0x5f: + setup_force_cpu_cap(X86_FEATURE_ZEN1); + break; + case 0x30 ... 0x4f: + case 0x60 ... 0x7f: + case 0x90 ... 0x91: + case 0xa0 ... 0xaf: + setup_force_cpu_cap(X86_FEATURE_ZEN2); + break; + default: + goto warn; + } + break; + + case 0x19: + switch (c->x86_model) { + case 0x00 ... 0x0f: + case 0x20 ... 0x5f: + setup_force_cpu_cap(X86_FEATURE_ZEN3); + break; + case 0x10 ... 0x1f: + case 0x60 ... 0xaf: + setup_force_cpu_cap(X86_FEATURE_ZEN4); + break; + default: + goto warn; + } + break; + + case 0x1a: + switch (c->x86_model) { + case 0x00 ... 0x0f: + case 0x20 ... 0x2f: + case 0x40 ... 0x4f: + case 0x70 ... 0x7f: + setup_force_cpu_cap(X86_FEATURE_ZEN5); + break; + default: + goto warn; + } + break; + + default: + break; + } + + return; + +warn: + WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model); } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -739,15 +714,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86 == 0x16 && c->x86_model <= 0xf) msr_set_bit(MSR_AMD64_LS_CFG, 15); - /* - * Check whether the machine is affected by erratum 400. This is - * used to select the proper idle routine and to enable the check - * whether the machine is affected in arch_post_acpi_init(), which - * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check. - */ - if (cpu_has_amd_erratum(c, amd_erratum_400)) - set_cpu_bug(c, X86_BUG_AMD_E400); - early_detect_mem_encrypt(c); /* Re-enable TopologyExtensions if switched off by BIOS */ @@ -814,6 +780,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c) msr_set_bit(MSR_K7_HWCR, 6); #endif set_cpu_bug(c, X86_BUG_SWAPGS_FENCE); + + /* + * Check models and steppings affected by erratum 400. This is + * used to select the proper idle routine and to enable the + * check whether the machine is affected in arch_post_acpi_subsys_init() + * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check. + */ + if (c->x86_model > 0x41 || + (c->x86_model == 0x41 && c->x86_stepping >= 0x2)) + setup_force_cpu_bug(X86_BUG_AMD_E400); } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -847,8 +823,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c) */ msr_clear_bit(MSR_AMD64_BU_CFG2, 24); - if (cpu_has_amd_erratum(c, amd_erratum_383)) - set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); + set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); + + /* + * Check models and steppings affected by erratum 400. This is + * used to select the proper idle routine and to enable the + * check whether the machine is affected in arch_post_acpi_subsys_init() + * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check. + */ + if (c->x86_model > 0x2 || + (c->x86_model == 0x2 && c->x86_stepping >= 0x1)) + setup_force_cpu_bug(X86_BUG_AMD_E400); } static void init_amd_ln(struct cpuinfo_x86 *c) @@ -941,6 +926,19 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } +static void fix_erratum_1386(struct cpuinfo_x86 *c) +{ + /* + * Work around Erratum 1386. The XSAVES instruction malfunctions in + * certain circumstances on Zen1/2 uarch, and not all parts have had + * updated microcode at the time of writing (March 2023). + * + * Affected parts all have no supervisor XSAVE states, meaning that + * the XSAVEC instruction (which works fine) is equivalent. + */ + clear_cpu_cap(c, X86_FEATURE_XSAVES); +} + void init_spectral_chicken(struct cpuinfo_x86 *c) { #ifdef CONFIG_CPU_UNRET_ENTRY @@ -951,34 +949,28 @@ void init_spectral_chicken(struct cpuinfo_x86 *c) * * This suppresses speculation from the middle of a basic block, i.e. it * suppresses non-branch predictions. - * - * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H */ - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) { + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) { value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT; wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value); } } #endif - /* - * Work around Erratum 1386. The XSAVES instruction malfunctions in - * certain circumstances on Zen1/2 uarch, and not all parts have had - * updated microcode at the time of writing (March 2023). - * - * Affected parts all have no supervisor XSAVE states, meaning that - * the XSAVEC instruction (which works fine) is equivalent. - */ - clear_cpu_cap(c, X86_FEATURE_XSAVES); } -static void init_amd_zn(struct cpuinfo_x86 *c) +static void init_amd_zen_common(void) { - set_cpu_cap(c, X86_FEATURE_ZEN); - + setup_force_cpu_cap(X86_FEATURE_ZEN); #ifdef CONFIG_NUMA node_reclaim_distance = 32; #endif +} + +static void init_amd_zen1(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + fix_erratum_1386(c); /* Fix up CPUID bits, but only if not virtualised. */ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { @@ -986,15 +978,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c) /* Erratum 1076: CPB feature bit not being set in CPUID. */ if (!cpu_has(c, X86_FEATURE_CPB)) set_cpu_cap(c, X86_FEATURE_CPB); - - /* - * Zen3 (Fam19 model < 0x10) parts are not susceptible to - * Branch Type Confusion, but predate the allocation of the - * BTC_NO bit. - */ - if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) - set_cpu_cap(c, X86_FEATURE_BTC_NO); } + + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); } static bool cpu_has_zenbleed_microcode(void) @@ -1018,11 +1005,8 @@ static bool cpu_has_zenbleed_microcode(void) return true; } -static void zenbleed_check(struct cpuinfo_x86 *c) +static void zen2_zenbleed_check(struct cpuinfo_x86 *c) { - if (!cpu_has_amd_erratum(c, amd_zenbleed)) - return; - if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return; @@ -1037,6 +1021,42 @@ static void zenbleed_check(struct cpuinfo_x86 *c) } } +static void init_amd_zen2(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + init_spectral_chicken(c); + fix_erratum_1386(c); + zen2_zenbleed_check(c); +} + +static void init_amd_zen3(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { + /* + * Zen3 (Fam19 model < 0x10) parts are not susceptible to + * Branch Type Confusion, but predate the allocation of the + * BTC_NO bit. + */ + if (!cpu_has(c, X86_FEATURE_BTC_NO)) + set_cpu_cap(c, X86_FEATURE_BTC_NO); + } +} + +static void init_amd_zen4(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); +} + +static void init_amd_zen5(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); +} + static void init_amd(struct cpuinfo_x86 *c) { u64 vm_cr; @@ -1072,11 +1092,19 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; case 0x16: init_amd_jg(c); break; - case 0x17: init_spectral_chicken(c); - fallthrough; - case 0x19: init_amd_zn(c); break; } + if (boot_cpu_has(X86_FEATURE_ZEN1)) + init_amd_zen1(c); + else if (boot_cpu_has(X86_FEATURE_ZEN2)) + init_amd_zen2(c); + else if (boot_cpu_has(X86_FEATURE_ZEN3)) + init_amd_zen3(c); + else if (boot_cpu_has(X86_FEATURE_ZEN4)) + init_amd_zen4(c); + else if (boot_cpu_has(X86_FEATURE_ZEN5)) + init_amd_zen5(c); + /* * Enable workaround for FXSAVE leak on CPUs * without a XSaveErPtr feature @@ -1136,7 +1164,7 @@ static void init_amd(struct cpuinfo_x86 *c) * Counter May Be Inaccurate". */ if (cpu_has(c, X86_FEATURE_IRPERF) && - !cpu_has_amd_erratum(c, amd_erratum_1054)) + (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); check_null_seg_clears_base(c); @@ -1152,16 +1180,8 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_has(c, X86_FEATURE_AUTOIBRS)) WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); - zenbleed_check(c); - - if (cpu_has_amd_erratum(c, amd_div0)) { - pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); - setup_force_cpu_bug(X86_BUG_DIV0); - } - - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && - cpu_has_amd_erratum(c, amd_erratum_1485)) - msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); + /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } #ifdef CONFIG_X86_32 @@ -1315,7 +1335,7 @@ static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - zenbleed_check(c); + zen2_zenbleed_check(c); } void amd_check_microcode(void) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bb0ab8466b91..48d049cd74e7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -111,9 +111,6 @@ 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); @@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV; - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void) * 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); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else static_branch_enable(&mmio_stale_data_clear); @@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return; - if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out; /* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b14fc8c1c953..fbc4e60d027c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -66,6 +66,7 @@ #include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> +#include <asm/tdx.h> #include "cpu.h" @@ -188,45 +189,37 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { * TLS descriptors are currently at a different place compared to i386. * Hopefully nobody expects them at a fixed place (Wine?) */ - [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff), + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA64 | DESC_USER, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE64 | DESC_USER, 0, 0xfffff), #else - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xc09a, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA32 | DESC_USER, 0, 0xfffff), /* * Segments used for calling PnP BIOS have byte granularity. * They code segments and data segments have fixed 64k limits, * the transfer segment sizes are set at run time. */ - /* 32-bit code */ - [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(0x409a, 0, 0xffff), - /* 16-bit code */ - [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(0x009a, 0, 0xffff), - /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(0x0092, 0, 0xffff), - /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(0x0092, 0, 0), - /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(0x0092, 0, 0), + [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff), + [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff), + [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0xffff), + [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0), + [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0), /* * The APM segments have byte granularity and their bases * are set at run time. All have 64k limits. */ - /* 32-bit code */ - [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(0x409a, 0, 0xffff), - /* 16-bit code */ - [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(0x009a, 0, 0xffff), - /* data */ - [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(0x4092, 0, 0xffff), - - [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), - [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), + [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff), + [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff), + [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(DESC_DATA32_BIOS, 0, 0xffff), + + [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff), + [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff), #endif } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); @@ -1596,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_vendor(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); cpu_parse_early_param(); if (this_cpu->c_early_init) @@ -1608,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); } - get_cpu_address_sizes(c); - setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c); @@ -1856,6 +1849,13 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); #endif + + /* + * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and + * Hygon will clear it in ->c_init() below. + */ + set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); + /* * Vendor-specific initialization. In this section we * canonicalize the feature flags, meaning if there are @@ -1987,6 +1987,7 @@ static __init void identify_boot_cpu(void) setup_cr_pinning(); tsx_init(); + tdx_init(); lkgs_init(); } diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 6f247d66758d..f0cd95502faa 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -354,6 +354,9 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); check_null_seg_clears_base(c); + + /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a927a8fc9624..40dec9b56f87 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index e4c3ba91321c..f18d35fe27a9 100644 --- a/arch/x86/kernel/cpu/intel_epb.c +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -237,4 +237,4 @@ err_out_online: cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE); return ret; } -subsys_initcall(intel_epb_init); +late_initcall(intel_epb_init); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index f3517b8a8e91..2b46eb0fdf3a 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -87,42 +87,40 @@ struct smca_bank { static DEFINE_PER_CPU_READ_MOSTLY(struct smca_bank[MAX_NR_BANKS], smca_banks); static DEFINE_PER_CPU_READ_MOSTLY(u8[N_SMCA_BANK_TYPES], smca_bank_counts); -struct smca_bank_name { - const char *name; /* Short name for sysfs */ - const char *long_name; /* Long name for pretty-printing */ -}; - -static struct smca_bank_name smca_names[] = { - [SMCA_LS ... SMCA_LS_V2] = { "load_store", "Load Store Unit" }, - [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, - [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, - [SMCA_DE] = { "decode_unit", "Decode Unit" }, - [SMCA_RESERVED] = { "reserved", "Reserved" }, - [SMCA_EX] = { "execution_unit", "Execution Unit" }, - [SMCA_FP] = { "floating_point", "Floating Point Unit" }, - [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, - [SMCA_CS ... SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, - [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, +static const char * const smca_names[] = { + [SMCA_LS ... SMCA_LS_V2] = "load_store", + [SMCA_IF] = "insn_fetch", + [SMCA_L2_CACHE] = "l2_cache", + [SMCA_DE] = "decode_unit", + [SMCA_RESERVED] = "reserved", + [SMCA_EX] = "execution_unit", + [SMCA_FP] = "floating_point", + [SMCA_L3_CACHE] = "l3_cache", + [SMCA_CS ... SMCA_CS_V2] = "coherent_slave", + [SMCA_PIE] = "pie", /* UMC v2 is separate because both of them can exist in a single system. */ - [SMCA_UMC] = { "umc", "Unified Memory Controller" }, - [SMCA_UMC_V2] = { "umc_v2", "Unified Memory Controller v2" }, - [SMCA_PB] = { "param_block", "Parameter Block" }, - [SMCA_PSP ... SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, - [SMCA_SMU ... SMCA_SMU_V2] = { "smu", "System Management Unit" }, - [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, - [SMCA_MPDMA] = { "mpdma", "MPDMA Unit" }, - [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, - [SMCA_PCIE ... SMCA_PCIE_V2] = { "pcie", "PCI Express Unit" }, - [SMCA_XGMI_PCS] = { "xgmi_pcs", "Ext Global Memory Interconnect PCS Unit" }, - [SMCA_NBIF] = { "nbif", "NBIF Unit" }, - [SMCA_SHUB] = { "shub", "System Hub Unit" }, - [SMCA_SATA] = { "sata", "SATA Unit" }, - [SMCA_USB] = { "usb", "USB Unit" }, - [SMCA_GMI_PCS] = { "gmi_pcs", "Global Memory Interconnect PCS Unit" }, - [SMCA_XGMI_PHY] = { "xgmi_phy", "Ext Global Memory Interconnect PHY Unit" }, - [SMCA_WAFL_PHY] = { "wafl_phy", "WAFL PHY Unit" }, - [SMCA_GMI_PHY] = { "gmi_phy", "Global Memory Interconnect PHY Unit" }, + [SMCA_UMC] = "umc", + [SMCA_UMC_V2] = "umc_v2", + [SMCA_MA_LLC] = "ma_llc", + [SMCA_PB] = "param_block", + [SMCA_PSP ... SMCA_PSP_V2] = "psp", + [SMCA_SMU ... SMCA_SMU_V2] = "smu", + [SMCA_MP5] = "mp5", + [SMCA_MPDMA] = "mpdma", + [SMCA_NBIO] = "nbio", + [SMCA_PCIE ... SMCA_PCIE_V2] = "pcie", + [SMCA_XGMI_PCS] = "xgmi_pcs", + [SMCA_NBIF] = "nbif", + [SMCA_SHUB] = "shub", + [SMCA_SATA] = "sata", + [SMCA_USB] = "usb", + [SMCA_USR_DP] = "usr_dp", + [SMCA_USR_CP] = "usr_cp", + [SMCA_GMI_PCS] = "gmi_pcs", + [SMCA_XGMI_PHY] = "xgmi_phy", + [SMCA_WAFL_PHY] = "wafl_phy", + [SMCA_GMI_PHY] = "gmi_phy", }; static const char *smca_get_name(enum smca_bank_types t) @@ -130,17 +128,8 @@ static const char *smca_get_name(enum smca_bank_types t) if (t >= N_SMCA_BANK_TYPES) return NULL; - return smca_names[t].name; -} - -const char *smca_get_long_name(enum smca_bank_types t) -{ - if (t >= N_SMCA_BANK_TYPES) - return NULL; - - return smca_names[t].long_name; + return smca_names[t]; } -EXPORT_SYMBOL_GPL(smca_get_long_name); enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank) { @@ -178,6 +167,7 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_CS, HWID_MCATYPE(0x2E, 0x0) }, { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1) }, { SMCA_CS_V2, HWID_MCATYPE(0x2E, 0x2) }, + { SMCA_MA_LLC, HWID_MCATYPE(0x2E, 0x4) }, /* Unified Memory Controller MCA type */ { SMCA_UMC, HWID_MCATYPE(0x96, 0x0) }, @@ -212,6 +202,8 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_SHUB, HWID_MCATYPE(0x80, 0x0) }, { SMCA_SATA, HWID_MCATYPE(0xA8, 0x0) }, { SMCA_USB, HWID_MCATYPE(0xAA, 0x0) }, + { SMCA_USR_DP, HWID_MCATYPE(0x170, 0x0) }, + { SMCA_USR_CP, HWID_MCATYPE(0x180, 0x0) }, { SMCA_GMI_PCS, HWID_MCATYPE(0x241, 0x0) }, { SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0) }, { SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0) }, diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 7b397370b4d6..bc39252bc54f 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -44,6 +44,7 @@ #include <linux/sync_core.h> #include <linux/task_work.h> #include <linux/hardirq.h> +#include <linux/kexec.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -52,6 +53,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/tdx.h> #include "internal.h" @@ -228,11 +230,20 @@ static void wait_for_panic(void) panic("Panicing machine check CPU died"); } +static const char *mce_dump_aux_info(struct mce *m) +{ + if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE)) + return tdx_dump_mce_info(m); + + return NULL; +} + static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) { struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; + const char *memmsg; /* * Allow instrumentation around external facilities usage. Not that it @@ -283,9 +294,29 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) } if (exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); + + memmsg = mce_dump_aux_info(final); + if (memmsg) + pr_emerg(HW_ERR "Machine check: %s\n", memmsg); + if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; + + /* + * Kdump skips the poisoned page in order to avoid + * touching the error bits again. Poison the page even + * if the error is fatal and the machine is about to + * panic. + */ + if (kexec_crash_loaded()) { + if (final && (final->status & MCI_STATUS_ADDRV)) { + struct page *p; + p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + if (p) + SetPageHWPoison(p); + } + } panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -670,6 +701,16 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) barrier(); m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); + /* + * Update storm tracking here, before checking for the + * MCI_STATUS_VAL bit. Valid corrected errors count + * towards declaring, or maintaining, storm status. No + * error in a bank counts towards avoiding, or ending, + * storm status. + */ + if (!mca_cfg.cmci_disabled) + mce_track_storm(&m); + /* If this entry is not valid, ignore it */ if (!(m.status & MCI_STATUS_VAL)) continue; @@ -1601,13 +1642,6 @@ static unsigned long check_interval = INITIAL_CHECK_INTERVAL; static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); -static unsigned long mce_adjust_timer_default(unsigned long interval) -{ - return interval; -} - -static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; - static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; @@ -1637,15 +1671,9 @@ static void mce_timer_fn(struct timer_list *t) iv = __this_cpu_read(mce_next_interval); - if (mce_available(this_cpu_ptr(&cpu_info))) { + if (mce_available(this_cpu_ptr(&cpu_info))) mc_poll_banks(); - if (mce_intel_cmci_poll()) { - iv = mce_adjust_timer(iv); - goto done; - } - } - /* * Alert userspace if needed. If we logged an MCE, reduce the polling * interval, otherwise increase the polling interval. @@ -1655,23 +1683,29 @@ static void mce_timer_fn(struct timer_list *t) else iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); -done: - __this_cpu_write(mce_next_interval, iv); - __start_timer(t, iv); + if (mce_get_storm_mode()) { + __start_timer(t, HZ); + } else { + __this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); + } } /* - * Ensure that the timer is firing in @interval from now. + * When a storm starts on any bank on this CPU, switch to polling + * once per second. When the storm ends, revert to the default + * polling interval. */ -void mce_timer_kick(unsigned long interval) +void mce_timer_kick(bool storm) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned long iv = __this_cpu_read(mce_next_interval); - __start_timer(t, interval); + mce_set_storm_mode(storm); - if (interval < iv) - __this_cpu_write(mce_next_interval, interval); + if (storm) + __start_timer(t, HZ); + else + __this_cpu_write(mce_next_interval, check_interval * HZ); } /* Must not be called in IRQ context where del_timer_sync() can deadlock */ @@ -1995,7 +2029,6 @@ static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) intel_init_cmci(); intel_init_lmce(); - mce_adjust_timer = cmci_intel_adjust_timer; } static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c) @@ -2008,7 +2041,6 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); - mce_adjust_timer = cmci_intel_adjust_timer; break; case X86_VENDOR_AMD: { @@ -2568,9 +2600,6 @@ static int mce_device_create(unsigned int cpu) int err; int i, j; - if (!mce_available(&boot_cpu_data)) - return -EIO; - dev = per_cpu(mce_device, cpu); if (dev) return 0; @@ -2665,8 +2694,6 @@ static void mce_reenable_cpu(void) static int mce_cpu_dead(unsigned int cpu) { - mce_intel_hcpu_update(cpu); - /* intentionally ignoring frozen here */ if (!cpuhp_tasks_frozen) cmci_rediscover(); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 4d8d4bcf915d..72f0695c3dc1 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -746,6 +746,7 @@ static void check_hw_inj_possible(void) wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status); rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status); + wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0); if (!status) { hw_injection_possible = false; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 52bce533ddcc..399b62e223d2 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -42,15 +42,6 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); /* - * CMCI storm detection backoff counter - * - * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've - * encountered an error. If not, we decrement it by one. We signal the end of - * the CMCI storm when it reaches 0. - */ -static DEFINE_PER_CPU(int, cmci_backoff_cnt); - -/* * cmci_discover_lock protects against parallel discovery attempts * which could race against each other. */ @@ -63,22 +54,26 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); */ static DEFINE_SPINLOCK(cmci_poll_lock); +/* Linux non-storm CMCI threshold (may be overridden by BIOS) */ #define CMCI_THRESHOLD 1 -#define CMCI_POLL_INTERVAL (30 * HZ) -#define CMCI_STORM_INTERVAL (HZ) -#define CMCI_STORM_THRESHOLD 15 -static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); -static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); -static DEFINE_PER_CPU(unsigned int, cmci_storm_state); - -enum { - CMCI_STORM_NONE, - CMCI_STORM_ACTIVE, - CMCI_STORM_SUBSIDED, -}; +/* + * MCi_CTL2 threshold for each bank when there is no storm. + * Default value for each bank may have been set by BIOS. + */ +static u16 cmci_threshold[MAX_NR_BANKS]; -static atomic_t cmci_storm_on_cpus; +/* + * High threshold to limit CMCI rate during storms. Max supported is + * 0x7FFF. Use this slightly smaller value so it has a distinctive + * signature when some asks "Why am I not seeing all corrected errors?" + * A high threshold is used instead of just disabling CMCI for a + * bank because both corrected and uncorrected errors may be logged + * in the same bank and signalled with CMCI. The threshold only applies + * to corrected errors, so keeping CMCI enabled means that uncorrected + * errors will still be processed in a timely fashion. + */ +#define CMCI_STORM_THRESHOLD 32749 static int cmci_supported(int *banks) { @@ -134,204 +129,166 @@ static bool lmce_supported(void) return tmp & FEAT_CTL_LMCE_ENABLED; } -bool mce_intel_cmci_poll(void) +/* + * Set a new CMCI threshold value. Preserve the state of the + * MCI_CTL2_CMCI_EN bit in case this happens during a + * cmci_rediscover() operation. + */ +static void cmci_set_threshold(int bank, int thresh) { - if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) - return false; - - /* - * Reset the counter if we've logged an error in the last poll - * during the storm. - */ - if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned))) - this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); - else - this_cpu_dec(cmci_backoff_cnt); + unsigned long flags; + u64 val; - return true; + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } -void mce_intel_hcpu_update(unsigned long cpu) +void mce_intel_handle_storm(int bank, bool on) { - if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) - atomic_dec(&cmci_storm_on_cpus); + if (on) + cmci_set_threshold(bank, CMCI_STORM_THRESHOLD); + else + cmci_set_threshold(bank, cmci_threshold[bank]); +} - per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +/* + * The interrupt handler. This is called on every event. + * Just call the poller directly to log any events. + * This could in theory increase the threshold under high load, + * but doesn't for now. + */ +static void intel_threshold_interrupt(void) +{ + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); } -static void cmci_toggle_interrupt_mode(bool on) +/* + * Check all the reasons why current CPU cannot claim + * ownership of a bank. + * 1: CPU already owns this bank + * 2: BIOS owns this bank + * 3: Some other CPU owns this bank + */ +static bool cmci_skip_bank(int bank, u64 *val) { - unsigned long flags, *owned; - int bank; - u64 val; + unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); - raw_spin_lock_irqsave(&cmci_discover_lock, flags); - owned = this_cpu_ptr(mce_banks_owned); - for_each_set_bit(bank, owned, MAX_NR_BANKS) { - rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + if (test_bit(bank, owned)) + return true; - if (on) - val |= MCI_CTL2_CMCI_EN; - else - val &= ~MCI_CTL2_CMCI_EN; + /* Skip banks in firmware first mode */ + if (test_bit(bank, mce_banks_ce_disabled)) + return true; - wrmsrl(MSR_IA32_MCx_CTL2(bank), val); - } - raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); -} + rdmsrl(MSR_IA32_MCx_CTL2(bank), *val); -unsigned long cmci_intel_adjust_timer(unsigned long interval) -{ - if ((this_cpu_read(cmci_backoff_cnt) > 0) && - (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) { - mce_notify_irq(); - return CMCI_STORM_INTERVAL; + /* Already owned by someone else? */ + if (*val & MCI_CTL2_CMCI_EN) { + clear_bit(bank, owned); + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + return true; } - switch (__this_cpu_read(cmci_storm_state)) { - case CMCI_STORM_ACTIVE: - - /* - * We switch back to interrupt mode once the poll timer has - * silenced itself. That means no events recorded and the timer - * interval is back to our poll interval. - */ - __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); - if (!atomic_sub_return(1, &cmci_storm_on_cpus)) - pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + return false; +} - fallthrough; +/* + * Decide which CMCI interrupt threshold to use: + * 1: If this bank is in storm mode from whichever CPU was + * the previous owner, stay in storm mode. + * 2: If ignoring any threshold set by BIOS, set Linux default + * 3: Try to honor BIOS threshold (unless buggy BIOS set it at zero). + */ +static u64 cmci_pick_threshold(u64 val, int *bios_zero_thresh) +{ + if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) + return val; - case CMCI_STORM_SUBSIDED: + if (!mca_cfg.bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { /* - * We wait for all CPUs to go back to SUBSIDED state. When that - * happens we switch back to interrupt mode. + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. */ - if (!atomic_read(&cmci_storm_on_cpus)) { - __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); - cmci_toggle_interrupt_mode(true); - cmci_recheck(); - } - return CMCI_POLL_INTERVAL; - default: - - /* We have shiny weather. Let the poll do whatever it thinks. */ - return interval; + *bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; } + + return val; } -static bool cmci_storm_detect(void) +/* + * Try to claim ownership of a bank. + */ +static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_wrong_thresh) { - unsigned int cnt = __this_cpu_read(cmci_storm_cnt); - unsigned long ts = __this_cpu_read(cmci_time_stamp); - unsigned long now = jiffies; - int r; + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); - if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) - return true; + val |= MCI_CTL2_CMCI_EN; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); - if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { - cnt++; - } else { - cnt = 1; - __this_cpu_write(cmci_time_stamp, now); + /* If the enable bit did not stick, this bank should be polled. */ + if (!(val & MCI_CTL2_CMCI_EN)) { + WARN_ON(!test_bit(bank, this_cpu_ptr(mce_poll_banks))); + storm->banks[bank].poll_only = true; + return; } - __this_cpu_write(cmci_storm_cnt, cnt); - if (cnt <= CMCI_STORM_THRESHOLD) - return false; - - cmci_toggle_interrupt_mode(false); - __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); - r = atomic_add_return(1, &cmci_storm_on_cpus); - mce_timer_kick(CMCI_STORM_INTERVAL); - this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + /* This CPU successfully set the enable bit. */ + set_bit(bank, (void *)this_cpu_ptr(&mce_banks_owned)); - if (r == 1) - pr_notice("CMCI storm detected: switching to poll mode\n"); - return true; -} + if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) { + pr_notice("CPU%d BANK%d CMCI inherited storm\n", smp_processor_id(), bank); + mce_inherit_storm(bank); + cmci_storm_begin(bank); + } else { + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + } -/* - * The interrupt handler. This is called on every event. - * Just call the poller directly to log any events. - * This could in theory increase the threshold under high load, - * but doesn't for now. - */ -static void intel_threshold_interrupt(void) -{ - if (cmci_storm_detect()) - return; + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + *bios_wrong_thresh = 1; - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); + /* Save default threshold for each bank */ + if (cmci_threshold[bank] == 0) + cmci_threshold[bank] = val & MCI_CTL2_CMCI_THRESHOLD_MASK; } /* * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks * on this CPU. Use the algorithm recommended in the SDM to discover shared - * banks. + * banks. Called during initial bootstrap, and also for hotplug CPU operations + * to rediscover/reassign machine check banks. */ static void cmci_discover(int banks) { - unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); + int bios_wrong_thresh = 0; unsigned long flags; int i; - int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; int bios_zero_thresh = 0; - if (test_bit(i, owned)) + if (cmci_skip_bank(i, &val)) continue; - /* Skip banks in firmware first mode */ - if (test_bit(i, mce_banks_ce_disabled)) - continue; - - rdmsrl(MSR_IA32_MCx_CTL2(i), val); - - /* Already owned by someone else? */ - if (val & MCI_CTL2_CMCI_EN) { - clear_bit(i, owned); - __clear_bit(i, this_cpu_ptr(mce_poll_banks)); - continue; - } - - if (!mca_cfg.bios_cmci_threshold) { - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= CMCI_THRESHOLD; - } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { - /* - * If bios_cmci_threshold boot option was specified - * but the threshold is zero, we'll try to initialize - * it to 1. - */ - bios_zero_thresh = 1; - val |= CMCI_THRESHOLD; - } - - val |= MCI_CTL2_CMCI_EN; - wrmsrl(MSR_IA32_MCx_CTL2(i), val); - rdmsrl(MSR_IA32_MCx_CTL2(i), val); - - /* Did the enable bit stick? -- the bank supports CMCI */ - if (val & MCI_CTL2_CMCI_EN) { - set_bit(i, owned); - __clear_bit(i, this_cpu_ptr(mce_poll_banks)); - /* - * We are able to set thresholds for some banks that - * had a threshold of 0. This means the BIOS has not - * set the thresholds properly or does not work with - * this boot option. Note down now and report later. - */ - if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && - (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) - bios_wrong_thresh = 1; - } else { - WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks))); - } + val = cmci_pick_threshold(val, &bios_zero_thresh); + cmci_claim_bank(i, val, bios_zero_thresh, &bios_wrong_thresh); } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) { @@ -370,6 +327,9 @@ static void __cmci_disable_bank(int bank) val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(bank), val); __clear_bit(bank, this_cpu_ptr(mce_banks_owned)); + + if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) + cmci_storm_end(bank); } /* diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index e13a26c9c0ac..01f8f03969e6 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -41,9 +41,7 @@ struct dentry *mce_get_debugfs_dir(void); extern mce_banks_t mce_banks_ce_disabled; #ifdef CONFIG_X86_MCE_INTEL -unsigned long cmci_intel_adjust_timer(unsigned long interval); -bool mce_intel_cmci_poll(void); -void mce_intel_hcpu_update(unsigned long cpu); +void mce_intel_handle_storm(int bank, bool on); void cmci_disable_bank(int bank); void intel_init_cmci(void); void intel_init_lmce(void); @@ -51,9 +49,7 @@ void intel_clear_lmce(void); bool intel_filter_mce(struct mce *m); bool intel_mce_usable_address(struct mce *m); #else -# define cmci_intel_adjust_timer mce_adjust_timer_default -static inline bool mce_intel_cmci_poll(void) { return false; } -static inline void mce_intel_hcpu_update(unsigned long cpu) { } +static inline void mce_intel_handle_storm(int bank, bool on) { } static inline void cmci_disable_bank(int bank) { } static inline void intel_init_cmci(void) { } static inline void intel_init_lmce(void) { } @@ -62,7 +58,63 @@ static inline bool intel_filter_mce(struct mce *m) { return false; } static inline bool intel_mce_usable_address(struct mce *m) { return false; } #endif -void mce_timer_kick(unsigned long interval); +void mce_timer_kick(bool storm); + +#ifdef CONFIG_X86_MCE_THRESHOLD +void cmci_storm_begin(unsigned int bank); +void cmci_storm_end(unsigned int bank); +void mce_track_storm(struct mce *mce); +void mce_inherit_storm(unsigned int bank); +bool mce_get_storm_mode(void); +void mce_set_storm_mode(bool storm); +#else +static inline void cmci_storm_begin(unsigned int bank) {} +static inline void cmci_storm_end(unsigned int bank) {} +static inline void mce_track_storm(struct mce *mce) {} +static inline void mce_inherit_storm(unsigned int bank) {} +static inline bool mce_get_storm_mode(void) { return false; } +static inline void mce_set_storm_mode(bool storm) {} +#endif + +/* + * history: Bitmask tracking errors occurrence. Each set bit + * represents an error seen. + * + * timestamp: Last time (in jiffies) that the bank was polled. + * in_storm_mode: Is this bank in storm mode? + * poll_only: Bank does not support CMCI, skip storm tracking. + */ +struct storm_bank { + u64 history; + u64 timestamp; + bool in_storm_mode; + bool poll_only; +}; + +#define NUM_HISTORY_BITS (sizeof(u64) * BITS_PER_BYTE) + +/* How many errors within the history buffer mark the start of a storm. */ +#define STORM_BEGIN_THRESHOLD 5 + +/* + * How many polls of machine check bank without an error before declaring + * the storm is over. Since it is tracked by the bitmasks in the history + * field of struct storm_bank the mask is 30 bits [0 ... 29]. + */ +#define STORM_END_POLL_THRESHOLD 29 + +/* + * banks: per-cpu, per-bank details + * stormy_bank_count: count of MC banks in storm state + * poll_mode: CPU is in poll mode + */ +struct mca_storm_desc { + struct storm_bank banks[MAX_NR_BANKS]; + u8 stormy_bank_count; + bool poll_mode; +}; + +DECLARE_PER_CPU(struct mca_storm_desc, storm_desc); #ifdef CONFIG_ACPI_APEI int apei_write_mce(struct mce *m); diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index ef4e7bb5fd88..89e31e1e5c9c 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -29,3 +29,118 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_threshold) trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); apic_eoi(); } + +DEFINE_PER_CPU(struct mca_storm_desc, storm_desc); + +void mce_inherit_storm(unsigned int bank) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + + /* + * Previous CPU owning this bank had put it into storm mode, + * but the precise history of that storm is unknown. Assume + * the worst (all recent polls of the bank found a valid error + * logged). This will avoid the new owner prematurely declaring + * the storm has ended. + */ + storm->banks[bank].history = ~0ull; + storm->banks[bank].timestamp = jiffies; +} + +bool mce_get_storm_mode(void) +{ + return __this_cpu_read(storm_desc.poll_mode); +} + +void mce_set_storm_mode(bool storm) +{ + __this_cpu_write(storm_desc.poll_mode, storm); +} + +static void mce_handle_storm(unsigned int bank, bool on) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_handle_storm(bank, on); + break; + } +} + +void cmci_storm_begin(unsigned int bank) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + + __set_bit(bank, this_cpu_ptr(mce_poll_banks)); + storm->banks[bank].in_storm_mode = true; + + /* + * If this is the first bank on this CPU to enter storm mode + * start polling. + */ + if (++storm->stormy_bank_count == 1) + mce_timer_kick(true); +} + +void cmci_storm_end(unsigned int bank) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + storm->banks[bank].history = 0; + storm->banks[bank].in_storm_mode = false; + + /* If no banks left in storm mode, stop polling. */ + if (!this_cpu_dec_return(storm_desc.stormy_bank_count)) + mce_timer_kick(false); +} + +void mce_track_storm(struct mce *mce) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + unsigned long now = jiffies, delta; + unsigned int shift = 1; + u64 history = 0; + + /* No tracking needed for banks that do not support CMCI */ + if (storm->banks[mce->bank].poll_only) + return; + + /* + * When a bank is in storm mode it is polled once per second and + * the history mask will record about the last minute of poll results. + * If it is not in storm mode, then the bank is only checked when + * there is a CMCI interrupt. Check how long it has been since + * this bank was last checked, and adjust the amount of "shift" + * to apply to history. + */ + if (!storm->banks[mce->bank].in_storm_mode) { + delta = now - storm->banks[mce->bank].timestamp; + shift = (delta + HZ) / HZ; + } + + /* If it has been a long time since the last poll, clear history. */ + if (shift < NUM_HISTORY_BITS) + history = storm->banks[mce->bank].history << shift; + + storm->banks[mce->bank].timestamp = now; + + /* History keeps track of corrected errors. VAL=1 && UC=0 */ + if ((mce->status & MCI_STATUS_VAL) && mce_is_correctable(mce)) + history |= 1; + + storm->banks[mce->bank].history = history; + + if (storm->banks[mce->bank].in_storm_mode) { + if (history & GENMASK_ULL(STORM_END_POLL_THRESHOLD, 0)) + return; + printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm subsided\n", smp_processor_id(), mce->bank); + mce_handle_storm(mce->bank, false); + cmci_storm_end(mce->bank); + } else { + if (hweight64(history) < STORM_BEGIN_THRESHOLD) + return; + printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm detected\n", smp_processor_id(), mce->bank); + mce_handle_storm(mce->bank, true); + cmci_storm_begin(mce->bank); + } +} diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 070426b9895f..857e608af641 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -370,14 +370,14 @@ static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info * { struct cpio_data cp; + intel_collect_cpu_info(&uci->cpu_sig); + if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path); if (!(cp.data && cp.size)) return NULL; - intel_collect_cpu_info(&uci->cpu_sig); - return scan_microcode(cp.data, cp.size, uci, save); } @@ -410,13 +410,13 @@ void __init load_ucode_intel_bsp(struct early_load_data *ed) { struct ucode_cpu_info uci; - ed->old_rev = intel_get_microcode_revision(); - uci.mc = get_microcode_blob(&uci, false); - if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) - ucode_patch_va = UCODE_BSP_LOADED; + ed->old_rev = uci.cpu_sig.rev; - ed->new_rev = uci.cpu_sig.rev; + if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) { + ucode_patch_va = UCODE_BSP_LOADED; + ed->new_rev = uci.cpu_sig.rev; + } } void load_ucode_intel_ap(void) @@ -457,12 +457,6 @@ static enum ucode_state apply_microcode_late(int cpu) if (ret != UCODE_UPDATED && ret != UCODE_OK) return ret; - if (!cpu && uci->cpu_sig.rev != cur_rev) { - pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n", - uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, - (mc->hdr.date >> 16) & 0xff); - } - cpu_data(cpu).microcode = uci->cpu_sig.rev; if (!cpu) boot_cpu_data.microcode = uci->cpu_sig.rev; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 2d6aa5d2e3d7..d3524778a545 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -428,6 +428,10 @@ void __init mtrr_copy_map(void) * from the x86_init.hyper.init_platform() hook. It can be called only once. * The MTRR state can't be changed afterwards. To ensure that, X86_FEATURE_MTRR * is cleared. + * + * @var: MTRR variable range array to use + * @num_var: length of the @var array + * @def_type: default caching type */ void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, mtrr_type def_type) @@ -492,13 +496,15 @@ static u8 type_merge(u8 type, u8 new_type, u8 *uniform) /** * mtrr_type_lookup - look up memory type in MTRR * + * @start: Begin of the physical address range + * @end: End of the physical address range + * @uniform: output argument: + * - 1: the returned MTRR type is valid for the whole region + * - 0: otherwise + * * Return Values: * MTRR_TYPE_(type) - The effective MTRR type for the region * MTRR_TYPE_INVALID - MTRR is disabled - * - * Output Argument: - * uniform - Set to 1 when the returned MTRR type is valid for the whole - * region, set to 0 else. */ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 5d390df21440..b65ab214bdf5 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -581,7 +581,7 @@ err_out: * * Flush any outstanding enqueued EADD operations and perform EINIT. The * Launch Enclave Public Key Hash MSRs are rewritten as necessary to match - * the enclave's MRSIGNER, which is caculated from the provided sigstruct. + * the enclave's MRSIGNER, which is calculated from the provided sigstruct. * * Return: * - 0: Success. diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c92d88680dbf..b6b044356f1b 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -170,7 +170,7 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem) int ret = 0; /* Exclude the low 1M because it is always reserved */ - ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1); + ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); if (ret) return ret; @@ -198,8 +198,8 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) } /* Prepare elf headers. Return addr and size */ -static int prepare_elf_headers(struct kimage *image, void **addr, - unsigned long *sz, unsigned long *nr_mem_ranges) +static int prepare_elf_headers(void **addr, unsigned long *sz, + unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; @@ -221,7 +221,7 @@ static int prepare_elf_headers(struct kimage *image, void **addr, *nr_mem_ranges = cmem->nr_ranges; /* By default prepare 64bit headers */ - ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); + ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); @@ -349,7 +349,7 @@ int crash_load_segments(struct kimage *image) .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ - ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz, &pnum); + ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; @@ -386,8 +386,8 @@ int crash_load_segments(struct kimage *image) if (ret) return ret; image->elf_load_addr = kbuf.mem; - pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + kexec_dprintk("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } @@ -452,7 +452,7 @@ void arch_crash_handle_hotplug_event(struct kimage *image) * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ - if (prepare_elf_headers(image, &elfbuf, &elfsz, &nr_mem_ranges)) { + if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { pr_err("unable to create new elfcorehdr"); goto out; } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb8cf953380d..b66f540de054 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index a6c1867fc7aa..59f4aefc6bc1 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -779,13 +779,13 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); - if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + if ((type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) { sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); if (sec > num) early_pci_scan_bus(sec); } - if (!(type & 0x80)) + if (!(type & PCI_HEADER_TYPE_MFD)) return -1; return 0; diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index 794e70151203..a06b876bbf2d 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -2,6 +2,7 @@ /* * x86 FPU bug checks: */ +#include <asm/cpufeature.h> #include <asm/fpu/api.h> /* diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index a21a4d0ecc34..520deb411a70 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); * Must be invoked from KVM after a VMEXIT before enabling interrupts when * XFD write emulation is disabled. This is required because the guest can * freely modify XFD and the state at VMEXIT is not guaranteed to be the - * same as the state on VMENTER. So software state has to be udpated before + * same as the state on VMENTER. So software state has to be updated before * any operation which depends on it can take place. * * Note: It can be invoked unconditionally even when write emulation is diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 558076dbde5b..247f2225aa9f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -274,12 +274,13 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures, * Attempt to restore the FPU registers directly from user memory. * Pagefaults are handled and any errors returned are fatal. */ -static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, - bool fx_only, unsigned int size) +static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only) { struct fpu *fpu = ¤t->thread.fpu; int ret; + /* Restore enabled features only. */ + xrestore &= fpu->fpstate->user_xfeatures; retry: fpregs_lock(); /* Ensure that XFD is up to date */ @@ -309,7 +310,7 @@ retry: if (ret != X86_TRAP_PF) return false; - if (!fault_in_readable(buf, size)) + if (!fault_in_readable(buf, fpu->fpstate->user_size)) goto retry; return false; } @@ -339,7 +340,6 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, struct user_i387_ia32_struct env; bool success, fx_only = false; union fpregs_state *fpregs; - unsigned int state_size; u64 user_xfeatures = 0; if (use_xsave()) { @@ -349,17 +349,14 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, return false; fx_only = !fx_sw_user.magic1; - state_size = fx_sw_user.xstate_size; user_xfeatures = fx_sw_user.xfeatures; } else { user_xfeatures = XFEATURE_MASK_FPSSE; - state_size = fpu->fpstate->user_size; } if (likely(!ia32_fxstate)) { /* Restore the FPU registers directly from user memory. */ - return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only, - state_size); + return restore_fpregs_from_user(buf_fx, user_xfeatures, fx_only); } /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 05a110c97111..dc0956067944 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -71,9 +71,9 @@ EXPORT_SYMBOL(vmemmap_base); * GDT used on the boot CPU before switching to virtual addresses. */ static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = { - [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff), }; /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 0f8103240fda..d4918d03efb4 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -114,6 +114,28 @@ SYM_CODE_START_NOALIGN(startup_64) /* Form the CR3 value being sure to include the CR3 modifier */ addq $(early_top_pgt - __START_KERNEL_map), %rax + +#ifdef CONFIG_AMD_MEM_ENCRYPT + mov %rax, %rdi + mov %rax, %r14 + + addq phys_base(%rip), %rdi + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + */ + call sev_verify_cbit + + /* + * Restore CR3 value without the phys_base which will be added + * below, before writing %cr3. + */ + mov %r14, %rax +#endif + jmp 1f SYM_CODE_END(startup_64) @@ -182,7 +204,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Enable PAE mode, PSE, PGE and LA57 */ orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL - testl $1, __pgtable_l5_enabled(%rip) + testb $1, __pgtable_l5_enabled(%rip) jz 1f orl $X86_CR4_LA57, %ecx 1: @@ -193,21 +215,12 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) addq phys_base(%rip), %rax /* - * For SEV guests: Verify that the C-bit is correct. A malicious - * hypervisor could lie about the C-bit position to perform a ROP - * attack on the guest by writing to the unencrypted stack and wait for - * the next RET instruction. - */ - movq %rax, %rdi - call sev_verify_cbit - - /* * Switch to new page-table * * For the boot CPU this switches to early_top_pgt which still has the - * indentity mappings present. The secondary CPUs will switch to the + * identity mappings present. The secondary CPUs will switch to the * init_top_pgt here, away from the trampoline_pgd and unmap the - * indentity mapped ranges. + * identity mapped ranges. */ movq %rax, %cr3 diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 41eecf180b7f..a38d0c93a66e 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -707,7 +707,7 @@ static void __init hpet_select_clockevents(void) hpet_base.nr_clockevents = 0; - /* No point if MSI is disabled or CPU has an Always Runing APIC Timer */ + /* No point if MSI is disabled or CPU has an Always Running APIC Timer */ if (hpet_msi_disable || boot_cpu_has(X86_FEATURE_ARAT)) return; @@ -965,7 +965,7 @@ static bool __init mwait_pc10_supported(void) * and per CPU timer interrupts. * * The probability that this problem is going to be solved in the - * forseeable future is close to zero, so the kernel has to be cluttered + * foreseeable future is close to zero, so the kernel has to be cluttered * with heuristics to keep up with the ever growing amount of hardware and * firmware trainwrecks. Hopefully some day hardware people will understand * that the approach of "This can be fixed in software" is not sustainable. @@ -1438,7 +1438,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) { - if (unlikely(mc146818_get_time(&curr_time) < 0)) { + if (unlikely(mc146818_get_time(&curr_time, 10) < 0)) { pr_err_ratelimited("unable to read current time from RTC\n"); return IRQ_HANDLED; } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index a61c12c01270..2a422e00ed4b 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -82,7 +82,7 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, cmdline_ptr[cmdline_len - 1] = '\0'; - pr_debug("Final command line is: %s\n", cmdline_ptr); + kexec_dprintk("Final command line is: %s\n", cmdline_ptr); cmdline_ptr_phys = bootparams_load_addr + cmdline_offset; cmdline_low_32 = cmdline_ptr_phys & 0xffffffffUL; cmdline_ext_32 = cmdline_ptr_phys >> 32; @@ -272,7 +272,12 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, nr_e820_entries = params->e820_entries; + kexec_dprintk("E820 memmap:\n"); for (i = 0; i < nr_e820_entries; i++) { + kexec_dprintk("%016llx-%016llx (%d)\n", + params->e820_table[i].addr, + params->e820_table[i].addr + params->e820_table[i].size - 1, + params->e820_table[i].type); if (params->e820_table[i].type != E820_TYPE_RAM) continue; start = params->e820_table[i].addr; @@ -424,7 +429,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * command line. Make sure it does not overflow */ if (cmdline_len + MAX_ELFCOREHDR_STR_LEN > header->cmdline_size) { - pr_debug("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n"); + pr_err("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n"); return ERR_PTR(-EINVAL); } @@ -445,7 +450,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, return ERR_PTR(ret); } - pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); + kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem); /* @@ -490,8 +495,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, if (ret) goto out_free_params; bootparam_load_addr = kbuf.mem; - pr_debug("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - bootparam_load_addr, kbuf.bufsz, kbuf.bufsz); + kexec_dprintk("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + bootparam_load_addr, kbuf.bufsz, kbuf.memsz); /* Load kernel */ kbuf.buffer = kernel + kern16_size; @@ -505,8 +510,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, goto out_free_params; kernel_load_addr = kbuf.mem; - pr_debug("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - kernel_load_addr, kbuf.bufsz, kbuf.memsz); + kexec_dprintk("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_load_addr, kbuf.bufsz, kbuf.memsz); /* Load initrd high */ if (initrd) { @@ -520,8 +525,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, goto out_free_params; initrd_load_addr = kbuf.mem; - pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - initrd_load_addr, initrd_len, initrd_len); + kexec_dprintk("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, initrd_len, initrd_len); setup_initrd(params, initrd_load_addr, initrd_len); } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 0ddb3bd0f1aa..428ee74002e1 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void) { int cpu; - if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + if (cc_vendor != CC_VENDOR_AMD || + !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; for_each_possible_cpu(cpu) { @@ -803,8 +804,8 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \ "setne %al\n\t" -DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted, - PV_VCPU_PREEMPTED_ASM, .text); +DEFINE_ASM_FUNC(__raw_callee_save___kvm_vcpu_is_preempted, + PV_VCPU_PREEMPTED_ASM, .text); #endif static void __init kvm_guest_init(void) @@ -942,7 +943,7 @@ static void __init kvm_init_platform(void) * Reset the host's shared pages list related to kernel * specific page encryption status settings before we load a * new kernel by kexec. Reset the page encryption status - * during early boot intead of just before kexec to avoid SMP + * during early boot instead of just before kexec to avoid SMP * races during kvm_pv_guest_cpu_reboot(). * NOTE: We cannot reset the complete shared pages list * here as we need to retain the UEFI/OVMF firmware diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index fb8f52149be9..5bb395551c44 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -24,8 +24,8 @@ static int kvmclock __initdata = 1; static int kvmclock_vsyscall __initdata = 1; -static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME; -static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK; +static int msr_kvm_system_time __ro_after_init; +static int msr_kvm_wall_clock __ro_after_init; static u64 kvm_sched_clock_offset __ro_after_init; static int __init parse_no_kvmclock(char *arg) @@ -42,7 +42,7 @@ static int __init parse_no_kvmclock_vsyscall(char *arg) } early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); -/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */ +/* Aligned to page sizes to match what's mapped via vsyscalls to userspace */ #define HVC_BOOT_ARRAY_SIZE \ (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) @@ -195,7 +195,8 @@ static void kvm_setup_secondary_clock(void) void kvmclock_disable(void) { - native_write_msr(msr_kvm_system_time, 0, 0); + if (msr_kvm_system_time) + native_write_msr(msr_kvm_system_time, 0, 0); } static void __init kvmclock_init_mem(void) @@ -294,7 +295,10 @@ void __init kvmclock_init(void) if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) { msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW; msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW; - } else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + } else if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) { + msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; + msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; + } else { return; } diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index adc67f98819a..7a814b41402d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -7,7 +7,7 @@ * This handles calls from both 32bit and 64bit mode. * * Lock order: - * contex.ldt_usr_sem + * context.ldt_usr_sem * mmap_lock * context.lock */ @@ -49,7 +49,7 @@ void load_mm_ldt(struct mm_struct *mm) /* * Any change to mm->context.ldt is followed by an IPI to all * CPUs with the mm active. The LDT will not be freed until - * after the IPI is handled by all such CPUs. This means that, + * after the IPI is handled by all such CPUs. This means that * if the ldt_struct changes before we return, the values we see * will be safe, and the new values will be loaded before we run * any user code. @@ -685,7 +685,7 @@ SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , } /* * The SYSCALL_DEFINE() macros give us an 'unsigned long' - * return type, but tht ABI for sys_modify_ldt() expects + * return type, but the ABI for sys_modify_ldt() expects * 'int'. This cast gives us an int-sized value in %rax * for the return code. The 'unsigned' is necessary so * the compiler does not try to sign-extend the negative diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1a3e2c05a8a5..bc0a5348b4a6 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -42,12 +42,9 @@ struct init_pgtable_data { static int mem_region_callback(struct resource *res, void *arg) { struct init_pgtable_data *data = arg; - unsigned long mstart, mend; - - mstart = res->start; - mend = mstart + resource_size(res) - 1; - return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend); + return kernel_ident_mapping_init(data->info, data->level4p, + res->start, res->end + 1); } static int diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 5f71a0cf4399..e18914c0e38a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -276,7 +276,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *alt = NULL, *locks = NULL, - *para = NULL, *orc = NULL, *orc_ip = NULL, + *orc = NULL, *orc_ip = NULL, *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL, *calls = NULL, *cfi = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; @@ -286,8 +286,6 @@ int module_finalize(const Elf_Ehdr *hdr, alt = s; if (!strcmp(".smp_locks", secstrings + s->sh_name)) locks = s; - if (!strcmp(".parainstructions", secstrings + s->sh_name)) - para = s; if (!strcmp(".orc_unwind", secstrings + s->sh_name)) orc = s; if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) @@ -304,14 +302,6 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } - /* - * See alternative_instructions() for the ordering rules between the - * various patching types. - */ - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -341,7 +331,7 @@ int module_finalize(const Elf_Ehdr *hdr, void *aseg = (void *)alt->sh_addr; apply_alternatives(aseg, aseg + alt->sh_size); } - if (calls || para) { + if (calls || alt) { struct callthunk_sites cs = {}; if (calls) { @@ -349,9 +339,9 @@ int module_finalize(const Elf_Ehdr *hdr, cs.call_end = (void *)calls->sh_addr + calls->sh_size; } - if (para) { - cs.pv_start = (void *)para->sh_addr; - cs.pv_end = (void *)para->sh_addr + para->sh_size; + if (alt) { + cs.alt_start = (void *)alt->sh_addr; + cs.alt_end = (void *)alt->sh_addr + alt->sh_size; } callthunks_patch_module_calls(&cs, me); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 17e955ab69fe..3082cf24b69e 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -563,9 +563,6 @@ nmi_restart: } if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); } #if IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97f1436c1a20..5358d43886ad 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -34,14 +34,8 @@ #include <asm/io_bitmap.h> #include <asm/gsseg.h> -/* - * nop stub, which must not clobber anything *including the stack* to - * avoid confusing the entry prologues. - */ -DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text); - /* stub always returning 0. */ -DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text); +DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text); void __init default_banner(void) { @@ -49,26 +43,12 @@ void __init default_banner(void) pv_info.name); } -/* Undefined instruction for dealing with missing ops pointers. */ -noinstr void paravirt_BUG(void) -{ - BUG(); -} - -static unsigned paravirt_patch_call(void *insn_buff, const void *target, - unsigned long addr, unsigned len) -{ - __text_gen_insn(insn_buff, CALL_INSN_OPCODE, - (void *)addr, target, CALL_INSN_SIZE); - return CALL_INSN_SIZE; -} - #ifdef CONFIG_PARAVIRT_XXL -DEFINE_PARAVIRT_ASM(_paravirt_ident_64, "mov %rdi, %rax", .text); -DEFINE_PARAVIRT_ASM(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_irq_disable, "cli", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_irq_enable, "sti", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); +DEFINE_ASM_FUNC(_paravirt_ident_64, "mov %rdi, %rax", .text); +DEFINE_ASM_FUNC(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_irq_disable, "cli", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); #endif DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); @@ -85,28 +65,6 @@ static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) tlb_remove_page(tlb, table); } -unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, - unsigned int len) -{ - /* - * Neat trick to map patch type back to the call within the - * corresponding structure. - */ - void *opfunc = *((void **)&pv_ops + type); - unsigned ret; - - if (opfunc == NULL) - /* If there's no function, patch it with paravirt_BUG() */ - ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len); - else if (opfunc == _paravirt_nop) - ret = 0; - else - /* Otherwise call the function. */ - ret = paravirt_patch_call(insn_buff, opfunc, addr, len); - - return ret; -} - struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b6f4e8399fca..ab49ade31b0d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -477,7 +477,7 @@ void native_tss_update_io_bitmap(void) /* * Make sure that the TSS limit is covering the IO bitmap. It might have * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O - * access from user space to trigger a #GP because tbe bitmap is outside + * access from user space to trigger a #GP because the bitmap is outside * the TSS limit. */ refresh_tss_limit(); diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 1309b9b05338..2e7066980f3e 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -67,7 +67,7 @@ void mach_get_cmos_time(struct timespec64 *now) return; } - if (mc146818_get_time(&tm)) { + if (mc146818_get_time(&tm, 1000)) { pr_err("Unable to read current time from RTC\n"); now->tv_sec = now->tv_nsec = 0; return; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1526747bedf2..84201071dfac 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -226,8 +226,6 @@ static void __init reserve_brk(void) _brk_start = 0; } -u64 relocated_ramdisk; - #ifdef CONFIG_BLK_DEV_INITRD static u64 __init get_ramdisk_image(void) @@ -261,7 +259,7 @@ static void __init relocate_initrd(void) u64 area_size = PAGE_ALIGN(ramdisk_size); /* We need to move the initrd down into directly mapped mem */ - relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0, + u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0, PFN_PHYS(max_pfn_mapped)); if (!relocated_ramdisk) panic("Cannot find place for new RAMDISK of size %lld\n", @@ -1033,6 +1031,8 @@ void __init setup_arch(char **cmdline_p) * * Moreover, on machines with SandyBridge graphics or in setups that use * crashkernel the entire 1M is reserved anyway. + * + * Note the host kernel TDX also requires the first 1MB being reserved. */ x86_platform.realmode_reserve(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 2c97bf7b56ae..b30d6e180df7 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -106,8 +106,8 @@ void __init pcpu_populate_pte(unsigned long addr) static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 - struct desc_struct d = GDT_ENTRY_INIT(0x8092, per_cpu_offset(cpu), - 0xFFFFF); + struct desc_struct d = GDT_ENTRY_INIT(DESC_DATA32, + per_cpu_offset(cpu), 0xFFFFF); write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &d, DESCTYPE_S); #endif diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ccb0915e84e1..1d24ec679915 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -96,7 +96,7 @@ static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) /* Tell the hypervisor what went wrong. */ val |= GHCB_SEV_TERM_REASON(set, reason); - /* Request Guest Termination from Hypvervisor */ + /* Request Guest Termination from Hypervisor */ sev_es_wr_ghcb_msr(val); VMGEXIT(); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 65fe2094da59..31b6f5dddfc2 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -27,6 +27,7 @@ #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/syscalls.h> +#include <linux/rseq.h> #include <asm/processor.h> #include <asm/ucontext.h> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2cc2aa120b4b..3f57ce68a3f1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -757,6 +757,7 @@ const struct cpumask *cpu_clustergroup_mask(int cpu) { return cpu_l2c_shared_mask(cpu); } +EXPORT_SYMBOL_GPL(cpu_clustergroup_mask); static void impress_friends(void) { diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 0bab03130033..d42c28b8bfd8 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -35,38 +35,9 @@ #include <asm/io_apic.h> #include <asm/cpu.h> -static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); - #ifdef CONFIG_HOTPLUG_CPU -int arch_register_cpu(int cpu) +bool arch_cpu_is_hotpluggable(int cpu) { - struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu); - - xc->cpu.hotpluggable = cpu > 0; - return register_cpu(&xc->cpu, cpu); -} -EXPORT_SYMBOL(arch_register_cpu); - -void arch_unregister_cpu(int num) -{ - unregister_cpu(&per_cpu(cpu_devices, num).cpu); -} -EXPORT_SYMBOL(arch_unregister_cpu); -#else /* CONFIG_HOTPLUG_CPU */ - -int __init arch_register_cpu(int num) -{ - return register_cpu(&per_cpu(cpu_devices, num).cpu, num); + return cpu > 0; } #endif /* CONFIG_HOTPLUG_CPU */ - -static int __init topology_init(void) -{ - int i; - - for_each_present_cpu(i) - arch_register_cpu(i); - - return 0; -} -subsys_initcall(topology_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c876f1d36a81..c3b2f863acf0 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -37,6 +37,7 @@ #include <linux/nmi.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/io.h> #include <linux/hardirq.h> #include <linux/atomic.h> @@ -565,7 +566,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs) */ static bool try_fixup_enqcmd_gp(void) { -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID u32 pasid; /* @@ -591,7 +592,7 @@ static bool try_fixup_enqcmd_gp(void) if (!mm_valid_pasid(current->mm)) return false; - pasid = current->mm->pasid; + pasid = mm_get_enqcmd_pasid(current->mm); /* * Did this thread already have its PASID activated? diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 54a5596adaa6..a349dbfc6d5a 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -267,19 +267,6 @@ SECTIONS } #endif - /* - * start address and size of operations which during runtime - * can be patched with virtualization friendly instructions or - * baremetal native ones. Think page table operations. - * Details in paravirt_types.h - */ - . = ALIGN(8); - .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { - __parainstructions = .; - *(.parainstructions) - __parainstructions_end = .; - } - #ifdef CONFIG_RETPOLINE /* * List of instructions that call/jmp/jcc to retpoline thunks |