diff options
Diffstat (limited to 'arch/x86/kernel')
56 files changed, 1090 insertions, 798 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 2ff3e600f426..6aef9ee28a39 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -84,7 +84,7 @@ obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o obj-$(CONFIG_INTEL_TXT) += tboot.o obj-$(CONFIG_ISA_DMA_API) += i8237.o -obj-$(CONFIG_STACKTRACE) += stacktrace.o +obj-y += stacktrace.o obj-y += cpu/ obj-y += acpi/ obj-y += reboot.o diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 3f85fcae450c..1e97f944b47d 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -139,8 +139,10 @@ static int __init acpi_sleep_setup(char *str) if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; #ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_hwsig", 8) == 0) + acpi_check_s4_hw_signature(1); if (strncmp(str, "s4_nohwsig", 10) == 0) - acpi_no_s4_hw_signature(); + acpi_check_s4_hw_signature(0); #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index daf88f8143c5..cf69081073b5 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -60,7 +60,7 @@ save_registers: popl saved_context_eflags movl $ret_point, saved_eip - ret + RET restore_registers: @@ -70,7 +70,7 @@ restore_registers: movl saved_context_edi, %edi pushl saved_context_eflags popfl - ret + RET SYM_CODE_START(do_suspend_lowlevel) call save_processor_state @@ -86,7 +86,7 @@ SYM_CODE_START(do_suspend_lowlevel) ret_point: call restore_registers call restore_processor_state - ret + RET SYM_CODE_END(do_suspend_lowlevel) .data diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 23fb4d51a5da..5007c3ffe96f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -714,7 +714,7 @@ asm ( " .type int3_magic, @function\n" "int3_magic:\n" " movl $1, (%" _ASM_ARG1 ")\n" -" ret\n" + ASM_RET " .size int3_magic, .-int3_magic\n" " .popsection\n" ); @@ -1113,10 +1113,13 @@ void text_poke_sync(void) } struct text_poke_loc { - s32 rel_addr; /* addr := _stext + rel_addr */ - s32 rel32; + /* addr := _stext + rel_addr */ + s32 rel_addr; + s32 disp; + u8 len; u8 opcode; const u8 text[POKE_MAX_OPCODE_SIZE]; + /* see text_poke_bp_batch() */ u8 old; }; @@ -1131,7 +1134,8 @@ static struct bp_patching_desc *bp_desc; static __always_inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) { - struct bp_patching_desc *desc = __READ_ONCE(*descp); /* rcu_dereference */ + /* rcu_dereference */ + struct bp_patching_desc *desc = __READ_ONCE(*descp); if (!desc || !arch_atomic_inc_not_zero(&desc->refs)) return NULL; @@ -1165,7 +1169,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs) { struct bp_patching_desc *desc; struct text_poke_loc *tp; - int len, ret = 0; + int ret = 0; void *ip; if (user_mode(regs)) @@ -1205,8 +1209,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs) goto out_put; } - len = text_opcode_size(tp->opcode); - ip += len; + ip += tp->len; switch (tp->opcode) { case INT3_INSN_OPCODE: @@ -1221,12 +1224,12 @@ noinstr int poke_int3_handler(struct pt_regs *regs) break; case CALL_INSN_OPCODE: - int3_emulate_call(regs, (long)ip + tp->rel32); + int3_emulate_call(regs, (long)ip + tp->disp); break; case JMP32_INSN_OPCODE: case JMP8_INSN_OPCODE: - int3_emulate_jmp(regs, (long)ip + tp->rel32); + int3_emulate_jmp(regs, (long)ip + tp->disp); break; default: @@ -1301,7 +1304,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries */ for (do_sync = 0, i = 0; i < nr_entries; i++) { u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, }; - int len = text_opcode_size(tp[i].opcode); + int len = tp[i].len; if (len - INT3_INSN_SIZE > 0) { memcpy(old + INT3_INSN_SIZE, @@ -1378,21 +1381,37 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, const void *opcode, size_t len, const void *emulate) { struct insn insn; - int ret; + int ret, i; memcpy((void *)tp->text, opcode, len); if (!emulate) emulate = opcode; ret = insn_decode_kernel(&insn, emulate); - BUG_ON(ret < 0); - BUG_ON(len != insn.length); tp->rel_addr = addr - (void *)_stext; + tp->len = len; tp->opcode = insn.opcode.bytes[0]; switch (tp->opcode) { + case RET_INSN_OPCODE: + case JMP32_INSN_OPCODE: + case JMP8_INSN_OPCODE: + /* + * Control flow instructions without implied execution of the + * next instruction can be padded with INT3. + */ + for (i = insn.length; i < len; i++) + BUG_ON(tp->text[i] != INT3_INSN_OPCODE); + break; + + default: + BUG_ON(len != insn.length); + }; + + + switch (tp->opcode) { case INT3_INSN_OPCODE: case RET_INSN_OPCODE: break; @@ -1400,7 +1419,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: case JMP8_INSN_OPCODE: - tp->rel32 = insn.immediate.value; + tp->disp = insn.immediate.value; break; default: /* assume NOP */ @@ -1408,13 +1427,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, case 2: /* NOP2 -- emulate as JMP8+0 */ BUG_ON(memcmp(emulate, x86_nops[len], len)); tp->opcode = JMP8_INSN_OPCODE; - tp->rel32 = 0; + tp->disp = 0; break; case 5: /* NOP5 -- emulate as JMP32+0 */ BUG_ON(memcmp(emulate, x86_nops[len], len)); tp->opcode = JMP32_INSN_OPCODE; - tp->rel32 = 0; + tp->disp = 0; break; default: /* unknown instruction */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c92c9c774c0e..020c906f7934 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -19,17 +19,19 @@ #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 #define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 +#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT 0x14a4 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 #define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1 #define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 #define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e -/* Protect the PCI config register pairs used for SMN and DF indirect access. */ +/* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); static u32 *flush_words; @@ -39,6 +41,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, {} }; @@ -61,6 +64,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, {} @@ -78,6 +82,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, @@ -182,53 +187,6 @@ int amd_smn_write(u16 node, u32 address, u32 value) } EXPORT_SYMBOL_GPL(amd_smn_write); -/* - * Data Fabric Indirect Access uses FICAA/FICAD. - * - * Fabric Indirect Configuration Access Address (FICAA): Constructed based - * on the device's Instance Id and the PCI function and register offset of - * the desired register. - * - * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO - * and FICAD HI registers but so far we only need the LO register. - */ -int amd_df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) -{ - struct pci_dev *F4; - u32 ficaa; - int err = -ENODEV; - - if (node >= amd_northbridges.num) - goto out; - - F4 = node_to_amd_nb(node)->link; - if (!F4) - goto out; - - ficaa = 1; - ficaa |= reg & 0x3FC; - ficaa |= (func & 0x7) << 11; - ficaa |= instance_id << 16; - - mutex_lock(&smn_mutex); - - err = pci_write_config_dword(F4, 0x5C, ficaa); - if (err) { - pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa); - goto out_unlock; - } - - err = pci_read_config_dword(F4, 0x98, lo); - if (err) - pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa); - -out_unlock: - mutex_unlock(&smn_mutex); - -out: - return err; -} -EXPORT_SYMBOL_GPL(amd_df_indirect_read); int amd_cache_northbridges(void) { diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index dbacb9ec8843..7517eb05bdc1 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -19,6 +19,7 @@ #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/xen/hypervisor.h> struct irq_domain *x86_pci_msi_default_domain __ro_after_init; @@ -159,11 +160,8 @@ static struct irq_chip pci_msi_controller = { int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg) { - struct pci_dev *pdev = to_pci_dev(dev); - struct msi_desc *desc = first_pci_msi_entry(pdev); - init_irq_alloc_info(arg, NULL); - if (desc->msi_attrib.is_msix) { + if (to_pci_dev(dev)->msix_enabled) { arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; } else { arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; @@ -345,3 +343,8 @@ void dmar_free_hwirq(int irq) irq_domain_free_irqs(irq, 1); } #endif + +bool arch_restore_msi_irqs(struct pci_dev *dev) +{ + return xen_initdom_restore_msi(dev); +} diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index ecd3fd6993d1..9fb0a2f8b62a 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -38,9 +38,6 @@ static void __used common(void) #endif BLANK(); - OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx); - - BLANK(); OFFSET(pbe_address, pbe, address); OFFSET(pbe_orig_address, pbe, orig_address); OFFSET(pbe_next, pbe, next); diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c index 03bb2f343ddb..6a6ffcd978f6 100644 --- a/arch/x86/kernel/cc_platform.c +++ b/arch/x86/kernel/cc_platform.c @@ -11,6 +11,7 @@ #include <linux/cc_platform.h> #include <linux/mem_encrypt.h> +#include <asm/mshyperv.h> #include <asm/processor.h> static bool __maybe_unused intel_cc_platform_has(enum cc_attr attr) @@ -50,6 +51,14 @@ static bool amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_STATE_ENCRYPT: return sev_status & MSR_AMD64_SEV_ES_ENABLED; + /* + * With SEV, the rep string I/O instructions need to be unrolled + * but SEV-ES supports them through the #VC handler. + */ + case CC_ATTR_GUEST_UNROLL_STRING_IO: + return (sev_status & MSR_AMD64_SEV_ENABLED) && + !(sev_status & MSR_AMD64_SEV_ES_ENABLED); + default: return false; } @@ -58,12 +67,19 @@ static bool amd_cc_platform_has(enum cc_attr attr) #endif } +static bool hyperv_cc_platform_has(enum cc_attr attr) +{ + return attr == CC_ATTR_GUEST_MEM_ENCRYPT; +} bool cc_platform_has(enum cc_attr attr) { if (sme_me_mask) return amd_cc_platform_has(attr); + if (hv_is_isolation_supported()) + return hyperv_cc_platform_has(attr); + return false; } EXPORT_SYMBOL_GPL(cc_platform_has); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0083464de5e3..7b8382c11788 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -384,7 +384,7 @@ set_register: } EXPORT_SYMBOL(native_write_cr0); -void native_write_cr4(unsigned long val) +void __no_profile native_write_cr4(unsigned long val) { unsigned long bits_changed = 0; @@ -1787,6 +1787,17 @@ EXPORT_PER_CPU_SYMBOL(__preempt_count); DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK; +static void wrmsrl_cstar(unsigned long val) +{ + /* + * Intel CPUs do not support 32-bit SYSCALL. Writing to MSR_CSTAR + * is so far ignored by the CPU, but raises a #VE trap in a TDX + * guest. Avoid the pointless write on all Intel CPUs. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + wrmsrl(MSR_CSTAR, val); +} + /* May not be marked __init: used by software suspend */ void syscall_init(void) { @@ -1794,7 +1805,7 @@ void syscall_init(void) wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION - wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); + wrmsrl_cstar((unsigned long)entry_SYSCALL_compat); /* * This only works on Intel CPUs. * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. @@ -1806,7 +1817,7 @@ void syscall_init(void) (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else - wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); + wrmsrl_cstar((unsigned long)ignore_sysret); wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index f4dd73396f28..fbaf12e43f41 100644 --- a/arch/x86/kernel/cpu/intel_epb.c +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -16,6 +16,7 @@ #include <linux/syscore_ops.h> #include <linux/pm.h> +#include <asm/cpu_device_id.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -58,6 +59,22 @@ static DEFINE_PER_CPU(u8, saved_epb); #define EPB_SAVED 0x10ULL #define MAX_EPB EPB_MASK +enum energy_perf_value_index { + EPB_INDEX_PERFORMANCE, + EPB_INDEX_BALANCE_PERFORMANCE, + EPB_INDEX_NORMAL, + EPB_INDEX_BALANCE_POWERSAVE, + EPB_INDEX_POWERSAVE, +}; + +static u8 energ_perf_values[] = { + [EPB_INDEX_PERFORMANCE] = ENERGY_PERF_BIAS_PERFORMANCE, + [EPB_INDEX_BALANCE_PERFORMANCE] = ENERGY_PERF_BIAS_BALANCE_PERFORMANCE, + [EPB_INDEX_NORMAL] = ENERGY_PERF_BIAS_NORMAL, + [EPB_INDEX_BALANCE_POWERSAVE] = ENERGY_PERF_BIAS_BALANCE_POWERSAVE, + [EPB_INDEX_POWERSAVE] = ENERGY_PERF_BIAS_POWERSAVE, +}; + static int intel_epb_save(void) { u64 epb; @@ -90,7 +107,7 @@ static void intel_epb_restore(void) */ val = epb & EPB_MASK; if (val == ENERGY_PERF_BIAS_PERFORMANCE) { - val = ENERGY_PERF_BIAS_NORMAL; + val = energ_perf_values[EPB_INDEX_NORMAL]; pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); } } @@ -103,18 +120,11 @@ static struct syscore_ops intel_epb_syscore_ops = { }; static const char * const energy_perf_strings[] = { - "performance", - "balance-performance", - "normal", - "balance-power", - "power" -}; -static const u8 energ_perf_values[] = { - ENERGY_PERF_BIAS_PERFORMANCE, - ENERGY_PERF_BIAS_BALANCE_PERFORMANCE, - ENERGY_PERF_BIAS_NORMAL, - ENERGY_PERF_BIAS_BALANCE_POWERSAVE, - ENERGY_PERF_BIAS_POWERSAVE + [EPB_INDEX_PERFORMANCE] = "performance", + [EPB_INDEX_BALANCE_PERFORMANCE] = "balance-performance", + [EPB_INDEX_NORMAL] = "normal", + [EPB_INDEX_BALANCE_POWERSAVE] = "balance-power", + [EPB_INDEX_POWERSAVE] = "power", }; static ssize_t energy_perf_bias_show(struct device *dev, @@ -193,13 +203,22 @@ static int intel_epb_offline(unsigned int cpu) return 0; } +static const struct x86_cpu_id intel_epb_normal[] = { + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 7), + {} +}; + static __init int intel_epb_init(void) { + const struct x86_cpu_id *id = x86_match_cpu(intel_epb_normal); int ret; if (!boot_cpu_has(X86_FEATURE_EPB)) return -ENODEV; + if (id) + energ_perf_values[EPB_INDEX_NORMAL] = id->driver_data; + ret = cpuhp_setup_state(CPUHP_AP_X86_INTEL_EPB_ONLINE, "x86/intel/epb:online", intel_epb_online, intel_epb_offline); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index fc85eb17cb6d..a1e2f41796dc 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -71,6 +71,22 @@ static const char * const smca_umc_block_names[] = { "misc_umc" }; +#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype)) + +struct smca_hwid { + unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ + u32 hwid_mcatype; /* (hwid,mcatype) tuple */ +}; + +struct smca_bank { + const struct smca_hwid *hwid; + u32 id; /* Value of MCA_IPID[InstanceId]. */ + u8 sysfs_id; /* Value used for sysfs name. */ +}; + +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 */ @@ -95,11 +111,18 @@ static struct smca_bank_name smca_names[] = { [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" }, }; static const char *smca_get_name(enum smca_bank_types t) @@ -119,14 +142,14 @@ const char *smca_get_long_name(enum smca_bank_types t) } EXPORT_SYMBOL_GPL(smca_get_long_name); -enum smca_bank_types smca_get_bank_type(unsigned int bank) +enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank) { struct smca_bank *b; if (bank >= MAX_NR_BANKS) return N_SMCA_BANK_TYPES; - b = &smca_banks[bank]; + b = &per_cpu(smca_banks, cpu)[bank]; if (!b->hwid) return N_SMCA_BANK_TYPES; @@ -134,7 +157,7 @@ enum smca_bank_types smca_get_bank_type(unsigned int bank) } EXPORT_SYMBOL_GPL(smca_get_bank_type); -static struct smca_hwid smca_hwid_mcatypes[] = { +static const struct smca_hwid smca_hwid_mcatypes[] = { /* { bank_type, hwid_mcatype } */ /* Reserved type */ @@ -174,6 +197,9 @@ static struct smca_hwid smca_hwid_mcatypes[] = { /* Microprocessor 5 Unit MCA type */ { SMCA_MP5, HWID_MCATYPE(0x01, 0x2) }, + /* MPDMA MCA type */ + { SMCA_MPDMA, HWID_MCATYPE(0x01, 0x3) }, + /* Northbridge IO Unit MCA type */ { SMCA_NBIO, HWID_MCATYPE(0x18, 0x0) }, @@ -181,19 +207,17 @@ static struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_PCIE, HWID_MCATYPE(0x46, 0x0) }, { SMCA_PCIE_V2, HWID_MCATYPE(0x46, 0x1) }, - /* xGMI PCS MCA type */ { SMCA_XGMI_PCS, HWID_MCATYPE(0x50, 0x0) }, - - /* xGMI PHY MCA type */ + { SMCA_NBIF, HWID_MCATYPE(0x6C, 0x0) }, + { SMCA_SHUB, HWID_MCATYPE(0x80, 0x0) }, + { SMCA_SATA, HWID_MCATYPE(0xA8, 0x0) }, + { SMCA_USB, HWID_MCATYPE(0xAA, 0x0) }, + { SMCA_GMI_PCS, HWID_MCATYPE(0x241, 0x0) }, { SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0) }, - - /* WAFL PHY MCA type */ { SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0) }, + { SMCA_GMI_PHY, HWID_MCATYPE(0x269, 0x0) }, }; -struct smca_bank smca_banks[MAX_NR_BANKS]; -EXPORT_SYMBOL_GPL(smca_banks); - /* * In SMCA enabled processors, we can have multiple banks for a given IP type. * So to define a unique name for each bank, we use a temp c-string to append @@ -249,8 +273,9 @@ static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu) static void smca_configure(unsigned int bank, unsigned int cpu) { + u8 *bank_counts = this_cpu_ptr(smca_bank_counts); + const struct smca_hwid *s_hwid; unsigned int i, hwid_mcatype; - struct smca_hwid *s_hwid; u32 high, low; u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank); @@ -286,10 +311,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) smca_set_misc_banks_map(bank, cpu); - /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) - return; - if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; @@ -300,10 +321,11 @@ static void smca_configure(unsigned int bank, unsigned int cpu) for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) { s_hwid = &smca_hwid_mcatypes[i]; + if (hwid_mcatype == s_hwid->hwid_mcatype) { - smca_banks[bank].hwid = s_hwid; - smca_banks[bank].id = low; - smca_banks[bank].sysfs_id = s_hwid->count++; + this_cpu_ptr(smca_banks)[bank].hwid = s_hwid; + this_cpu_ptr(smca_banks)[bank].id = low; + this_cpu_ptr(smca_banks)[bank].sysfs_id = bank_counts[s_hwid->bank_type]++; break; } } @@ -589,7 +611,7 @@ out: bool amd_filter_mce(struct mce *m) { - enum smca_bank_types bank_type = smca_get_bank_type(m->bank); + enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank); struct cpuinfo_x86 *c = &boot_cpu_data; /* See Family 17h Models 10h-2Fh Erratum #1114. */ @@ -627,7 +649,7 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank) } else if (c->x86 == 0x17 && (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) { - if (smca_get_bank_type(bank) != SMCA_IF) + if (smca_get_bank_type(smp_processor_id(), bank) != SMCA_IF) return; msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank); @@ -689,213 +711,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) -{ - u64 dram_base_addr, dram_limit_addr, dram_hole_base; - /* We start from the normalized address */ - u64 ret_addr = norm_addr; - - u32 tmp; - - u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask; - u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets; - u8 intlv_addr_sel, intlv_addr_bit; - u8 num_intlv_bits, hashed_bit; - u8 lgcy_mmio_hole_en, base = 0; - u8 cs_mask, cs_id = 0; - bool hash_enabled = false; - - /* Read D18F0x1B4 (DramOffset), check if base 1 is used. */ - if (amd_df_indirect_read(nid, 0, 0x1B4, umc, &tmp)) - goto out_err; - - /* Remove HiAddrOffset from normalized address, if enabled: */ - if (tmp & BIT(0)) { - u64 hi_addr_offset = (tmp & GENMASK_ULL(31, 20)) << 8; - - if (norm_addr >= hi_addr_offset) { - ret_addr -= hi_addr_offset; - base = 1; - } - } - - /* Read D18F0x110 (DramBaseAddress). */ - if (amd_df_indirect_read(nid, 0, 0x110 + (8 * base), umc, &tmp)) - goto out_err; - - /* Check if address range is valid. */ - if (!(tmp & BIT(0))) { - pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n", - __func__, tmp); - goto out_err; - } - - lgcy_mmio_hole_en = tmp & BIT(1); - intlv_num_chan = (tmp >> 4) & 0xF; - intlv_addr_sel = (tmp >> 8) & 0x7; - dram_base_addr = (tmp & GENMASK_ULL(31, 12)) << 16; - - /* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */ - if (intlv_addr_sel > 3) { - pr_err("%s: Invalid interleave address select %d.\n", - __func__, intlv_addr_sel); - goto out_err; - } - - /* Read D18F0x114 (DramLimitAddress). */ - if (amd_df_indirect_read(nid, 0, 0x114 + (8 * base), umc, &tmp)) - goto out_err; - - intlv_num_sockets = (tmp >> 8) & 0x1; - intlv_num_dies = (tmp >> 10) & 0x3; - dram_limit_addr = ((tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0); - - intlv_addr_bit = intlv_addr_sel + 8; - - /* Re-use intlv_num_chan by setting it equal to log2(#channels) */ - switch (intlv_num_chan) { - case 0: intlv_num_chan = 0; break; - case 1: intlv_num_chan = 1; break; - case 3: intlv_num_chan = 2; break; - case 5: intlv_num_chan = 3; break; - case 7: intlv_num_chan = 4; break; - - case 8: intlv_num_chan = 1; - hash_enabled = true; - break; - default: - pr_err("%s: Invalid number of interleaved channels %d.\n", - __func__, intlv_num_chan); - goto out_err; - } - - num_intlv_bits = intlv_num_chan; - - if (intlv_num_dies > 2) { - pr_err("%s: Invalid number of interleaved nodes/dies %d.\n", - __func__, intlv_num_dies); - goto out_err; - } - - num_intlv_bits += intlv_num_dies; - - /* Add a bit if sockets are interleaved. */ - num_intlv_bits += intlv_num_sockets; - - /* Assert num_intlv_bits <= 4 */ - if (num_intlv_bits > 4) { - pr_err("%s: Invalid interleave bits %d.\n", - __func__, num_intlv_bits); - goto out_err; - } - - if (num_intlv_bits > 0) { - u64 temp_addr_x, temp_addr_i, temp_addr_y; - u8 die_id_bit, sock_id_bit, cs_fabric_id; - - /* - * Read FabricBlockInstanceInformation3_CS[BlockFabricID]. - * This is the fabric id for this coherent slave. Use - * umc/channel# as instance id of the coherent slave - * for FICAA. - */ - if (amd_df_indirect_read(nid, 0, 0x50, umc, &tmp)) - goto out_err; - - cs_fabric_id = (tmp >> 8) & 0xFF; - die_id_bit = 0; - - /* If interleaved over more than 1 channel: */ - if (intlv_num_chan) { - die_id_bit = intlv_num_chan; - cs_mask = (1 << die_id_bit) - 1; - cs_id = cs_fabric_id & cs_mask; - } - - sock_id_bit = die_id_bit; - - /* Read D18F1x208 (SystemFabricIdMask). */ - if (intlv_num_dies || intlv_num_sockets) - if (amd_df_indirect_read(nid, 1, 0x208, umc, &tmp)) - goto out_err; - - /* If interleaved over more than 1 die. */ - if (intlv_num_dies) { - sock_id_bit = die_id_bit + intlv_num_dies; - die_id_shift = (tmp >> 24) & 0xF; - die_id_mask = (tmp >> 8) & 0xFF; - - cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit; - } - - /* If interleaved over more than 1 socket. */ - if (intlv_num_sockets) { - socket_id_shift = (tmp >> 28) & 0xF; - socket_id_mask = (tmp >> 16) & 0xFF; - - cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit; - } - - /* - * The pre-interleaved address consists of XXXXXXIIIYYYYY - * where III is the ID for this CS, and XXXXXXYYYYY are the - * address bits from the post-interleaved address. - * "num_intlv_bits" has been calculated to tell us how many "I" - * bits there are. "intlv_addr_bit" tells us how many "Y" bits - * there are (where "I" starts). - */ - temp_addr_y = ret_addr & GENMASK_ULL(intlv_addr_bit-1, 0); - temp_addr_i = (cs_id << intlv_addr_bit); - temp_addr_x = (ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits; - ret_addr = temp_addr_x | temp_addr_i | temp_addr_y; - } - - /* Add dram base address */ - ret_addr += dram_base_addr; - - /* If legacy MMIO hole enabled */ - if (lgcy_mmio_hole_en) { - if (amd_df_indirect_read(nid, 0, 0x104, umc, &tmp)) - goto out_err; - - dram_hole_base = tmp & GENMASK(31, 24); - if (ret_addr >= dram_hole_base) - ret_addr += (BIT_ULL(32) - dram_hole_base); - } - - if (hash_enabled) { - /* Save some parentheses and grab ls-bit at the end. */ - hashed_bit = (ret_addr >> 12) ^ - (ret_addr >> 18) ^ - (ret_addr >> 21) ^ - (ret_addr >> 30) ^ - cs_id; - - hashed_bit &= BIT(0); - - if (hashed_bit != ((ret_addr >> intlv_addr_bit) & BIT(0))) - ret_addr ^= BIT(intlv_addr_bit); - } - - /* Is calculated system address is above DRAM limit address? */ - if (ret_addr > dram_limit_addr) - goto out_err; - - *sys_addr = ret_addr; - return 0; - -out_err: - return -EINVAL; -} -EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr); - bool amd_mce_is_memory_error(struct mce *m) { /* ErrCodeExt[20:16] */ u8 xec = (m->status >> 16) & 0x1f; if (mce_flags.smca) - return smca_get_bank_type(m->bank) == SMCA_UMC && xec == 0x0; + return smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC && xec == 0x0; return m->bank == 4 && xec == 0x8; } @@ -1211,7 +1033,7 @@ static struct kobj_type threshold_ktype = { .release = threshold_block_release, }; -static const char *get_name(unsigned int bank, struct threshold_block *b) +static const char *get_name(unsigned int cpu, unsigned int bank, struct threshold_block *b) { enum smca_bank_types bank_type; @@ -1222,7 +1044,7 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return th_names[bank]; } - bank_type = smca_get_bank_type(bank); + bank_type = smca_get_bank_type(cpu, bank); if (bank_type >= N_SMCA_BANK_TYPES) return NULL; @@ -1232,12 +1054,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return NULL; } - if (smca_banks[bank].hwid->count == 1) + if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1) return smca_get_name(bank_type); snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, - "%s_%x", smca_get_name(bank_type), - smca_banks[bank].sysfs_id); + "%s_%u", smca_get_name(bank_type), + per_cpu(smca_banks, cpu)[bank].sysfs_id); return buf_mcatype; } @@ -1293,7 +1115,7 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb else tb->blocks = b; - err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b)); + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(cpu, bank, b)); if (err) goto out_free; recurse: @@ -1348,7 +1170,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, struct device *dev = this_cpu_read(mce_device); struct amd_northbridge *nb = NULL; struct threshold_bank *b = NULL; - const char *name = get_name(bank, NULL); + const char *name = get_name(cpu, bank, NULL); int err = 0; if (!dev) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6ed365337a3b..5818b837fd4d 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -99,7 +99,6 @@ struct mca_config mca_cfg __read_mostly = { static DEFINE_PER_CPU(struct mce, mces_seen); static unsigned long mce_need_notify; -static int cpu_missing; /* * MCA banks polled by the period polling timer for corrected events. @@ -128,7 +127,7 @@ static struct irq_work mce_irq_work; BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ -noinstr void mce_setup(struct mce *m) +void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); @@ -267,11 +266,17 @@ static void wait_for_panic(void) panic("Panicing machine check CPU died"); } -static void mce_panic(const char *msg, struct mce *final, char *exp) +static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) { - int apei_err = 0; struct llist_node *pending; struct mce_evt_llist *l; + int apei_err = 0; + + /* + * Allow instrumentation around external facilities usage. Not that it + * matters a whole lot since the machine is going to panic anyway. + */ + instrumentation_begin(); if (!fake_panic) { /* @@ -286,7 +291,7 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) } else { /* Don't log too much for fake panic */ if (atomic_inc_return(&mce_fake_panicked) > 1) - return; + goto out; } pending = mce_gen_pool_prepare_records(); /* First print corrected ones that are still unlogged */ @@ -314,8 +319,6 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) if (!apei_err) apei_err = apei_write_mce(final); } - if (cpu_missing) - pr_emerg(HW_ERR "Some CPUs didn't answer in synchronization\n"); if (exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); if (!fake_panic) { @@ -324,6 +327,9 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); + +out: + instrumentation_end(); } /* Support code for software error injection */ @@ -365,7 +371,7 @@ void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) } /* MSR access wrappers used for error injection */ -static noinstr u64 mce_rdmsrl(u32 msr) +noinstr u64 mce_rdmsrl(u32 msr) { DECLARE_ARGS(val, low, high); @@ -433,9 +439,15 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v) * check into our "mce" struct so that we can use it later to assess * the severity of the problem as we read per-bank specific details. */ -static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) +static noinstr void mce_gather_info(struct mce *m, struct pt_regs *regs) { + /* + * Enable instrumentation around mce_setup() which calls external + * facilities. + */ + instrumentation_begin(); mce_setup(m); + instrumentation_end(); m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); if (regs) { @@ -636,7 +648,7 @@ static struct notifier_block mce_default_nb = { /* * Read ADDR and MISC registers. */ -static void mce_read_aux(struct mce *m, int i) +static noinstr void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC)); @@ -871,8 +883,13 @@ static cpumask_t mce_missing_cpus = CPU_MASK_ALL; /* * Check if a timeout waiting for other CPUs happened. */ -static int mce_timed_out(u64 *t, const char *msg) +static noinstr int mce_timed_out(u64 *t, const char *msg) { + int ret = 0; + + /* Enable instrumentation around calls to external facilities */ + instrumentation_begin(); + /* * The others already did panic for some reason. * Bail out like in a timeout. @@ -891,13 +908,17 @@ static int mce_timed_out(u64 *t, const char *msg) cpumask_pr_args(&mce_missing_cpus)); mce_panic(msg, NULL, NULL); } - cpu_missing = 1; - return 1; + ret = 1; + goto out; } *t -= SPINUNIT; + out: touch_nmi_watchdog(); - return 0; + + instrumentation_end(); + + return ret; } /* @@ -986,14 +1007,13 @@ static atomic_t global_nwo; * in the entry order. * TBD double check parallel CPU hotunplug */ -static int mce_start(int *no_way_out) +static noinstr int mce_start(int *no_way_out) { - int order; - int cpus = num_online_cpus(); u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; + int order, ret = -1; if (!timeout) - return -1; + return ret; atomic_add(*no_way_out, &global_nwo); /* @@ -1003,14 +1023,17 @@ static int mce_start(int *no_way_out) order = atomic_inc_return(&mce_callin); cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); + /* Enable instrumentation around calls to external facilities */ + instrumentation_begin(); + /* * Wait for everyone. */ - while (atomic_read(&mce_callin) != cpus) { + while (atomic_read(&mce_callin) != num_online_cpus()) { if (mce_timed_out(&timeout, "Timeout: Not all CPUs entered broadcast exception handler")) { atomic_set(&global_nwo, 0); - return -1; + goto out; } ndelay(SPINUNIT); } @@ -1036,7 +1059,7 @@ static int mce_start(int *no_way_out) if (mce_timed_out(&timeout, "Timeout: Subject CPUs unable to finish machine check processing")) { atomic_set(&global_nwo, 0); - return -1; + goto out; } ndelay(SPINUNIT); } @@ -1047,17 +1070,25 @@ static int mce_start(int *no_way_out) */ *no_way_out = atomic_read(&global_nwo); - return order; + ret = order; + +out: + instrumentation_end(); + + return ret; } /* * Synchronize between CPUs after main scanning loop. * This invokes the bulk of the Monarch processing. */ -static int mce_end(int order) +static noinstr int mce_end(int order) { - int ret = -1; u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; + int ret = -1; + + /* Allow instrumentation around external facilities. */ + instrumentation_begin(); if (!timeout) goto reset; @@ -1070,14 +1101,11 @@ static int mce_end(int order) atomic_inc(&mce_executing); if (order == 1) { - /* CHECKME: Can this race with a parallel hotplug? */ - int cpus = num_online_cpus(); - /* * Monarch: Wait for everyone to go through their scanning * loops. */ - while (atomic_read(&mce_executing) <= cpus) { + while (atomic_read(&mce_executing) <= num_online_cpus()) { if (mce_timed_out(&timeout, "Timeout: Monarch CPU unable to finish machine check processing")) goto reset; @@ -1101,7 +1129,8 @@ static int mce_end(int order) /* * Don't reset anything. That's done by the Monarch. */ - return 0; + ret = 0; + goto out; } /* @@ -1117,6 +1146,10 @@ reset: * Let others run again. */ atomic_set(&mce_executing, 0); + +out: + instrumentation_end(); + return ret; } @@ -1165,13 +1198,14 @@ static noinstr bool mce_check_crashing_cpu(void) return false; } -static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, - unsigned long *toclear, unsigned long *valid_banks, - int no_way_out, int *worst) +static __always_inline int +__mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, + unsigned long *toclear, unsigned long *valid_banks, int no_way_out, + int *worst) { struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); struct mca_config *cfg = &mca_cfg; - int severity, i; + int severity, i, taint = 0; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { __clear_bit(i, toclear); @@ -1198,7 +1232,7 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin continue; /* Set taint even when machine check was not enabled. */ - add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + taint++; severity = mce_severity(m, regs, cfg->tolerant, NULL, true); @@ -1221,7 +1255,13 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin /* assuming valid severity level != 0 */ m->severity = severity; + /* + * Enable instrumentation around the mce_log() call which is + * done in #MC context, where instrumentation is disabled. + */ + instrumentation_begin(); mce_log(m); + instrumentation_end(); if (severity > *worst) { *final = *m; @@ -1231,6 +1271,8 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin /* mce_clear_state will clear *final, save locally for use later */ *m = *final; + + return taint; } static void kill_me_now(struct callback_head *ch) @@ -1320,11 +1362,11 @@ static noinstr void unexpected_machine_check(struct pt_regs *regs) } /* - * The actual machine check handler. This only handles real - * exceptions when something got corrupted coming in through int 18. + * The actual machine check handler. This only handles real exceptions when + * something got corrupted coming in through int 18. * - * This is executed in NMI context not subject to normal locking rules. This - * implies that most kernel services cannot be safely used. Don't even + * This is executed in #MC context not subject to normal locking rules. + * This implies that most kernel services cannot be safely used. Don't even * think about putting a printk in there! * * On Intel systems this is entered on all CPUs in parallel through @@ -1336,12 +1378,20 @@ static noinstr void unexpected_machine_check(struct pt_regs *regs) * issues: if the machine check was due to a failure of the memory * backing the user stack, tracing that reads the user stack will cause * potentially infinite recursion. + * + * Currently, the #MC handler calls out to a number of external facilities + * and, therefore, allows instrumentation around them. The optimal thing to + * have would be to do the absolutely minimal work required in #MC context + * and have instrumentation disabled only around that. Further processing can + * then happen in process context where instrumentation is allowed. Achieving + * that requires careful auditing and modifications. Until then, the code + * allows instrumentation temporarily, where required. * */ noinstr void do_machine_check(struct pt_regs *regs) { - int worst = 0, order, no_way_out, kill_current_task, lmce; - DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); - DECLARE_BITMAP(toclear, MAX_NR_BANKS); + int worst = 0, order, no_way_out, kill_current_task, lmce, taint = 0; + DECLARE_BITMAP(valid_banks, MAX_NR_BANKS) = { 0 }; + DECLARE_BITMAP(toclear, MAX_NR_BANKS) = { 0 }; struct mca_config *cfg = &mca_cfg; struct mce m, *final; char *msg = NULL; @@ -1385,7 +1435,6 @@ noinstr void do_machine_check(struct pt_regs *regs) final = this_cpu_ptr(&mces_seen); *final = m; - memset(valid_banks, 0, sizeof(valid_banks)); no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs); barrier(); @@ -1419,7 +1468,7 @@ noinstr void do_machine_check(struct pt_regs *regs) order = mce_start(&no_way_out); } - __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst); + taint = __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1451,6 +1500,16 @@ noinstr void do_machine_check(struct pt_regs *regs) } } + /* + * Enable instrumentation around the external facilities like task_work_add() + * (via queue_task_work()), fixup_exception() etc. For now, that is. Fixing this + * properly would need a lot more involved reorganization. + */ + instrumentation_begin(); + + if (taint) + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + if (worst != MCE_AR_SEVERITY && !kill_current_task) goto out; @@ -1482,7 +1541,10 @@ noinstr void do_machine_check(struct pt_regs *regs) if (m.kflags & MCE_IN_KERNEL_COPYIN) queue_task_work(&m, msg, kill_me_never); } + out: + instrumentation_end(); + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -2702,7 +2764,6 @@ struct dentry *mce_get_debugfs_dir(void) static void mce_reset(void) { - cpu_missing = 0; atomic_set(&mce_fake_panicked, 0); atomic_set(&mce_executing, 0); atomic_set(&mce_callin, 0); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 0bfc14041bbb..5fbd7ffb3233 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -74,7 +74,6 @@ MCE_INJECT_SET(status); MCE_INJECT_SET(misc); MCE_INJECT_SET(addr); MCE_INJECT_SET(synd); -MCE_INJECT_SET(ipid); #define MCE_INJECT_GET(reg) \ static int inj_##reg##_get(void *data, u64 *val) \ @@ -95,6 +94,20 @@ DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); + +/* Use the user provided IPID value on a sw injection. */ +static int inj_ipid_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (cpu_feature_enabled(X86_FEATURE_SMCA)) { + if (inj_type == SW_INJ) + m->ipid = val; + } + + return 0; +} + DEFINE_SIMPLE_ATTRIBUTE(ipid_fops, inj_ipid_get, inj_ipid_set, "%llx\n"); static void setup_inj_struct(struct mce *m) @@ -350,7 +363,7 @@ static ssize_t flags_write(struct file *filp, const char __user *ubuf, char buf[MAX_FLAG_OPT_SIZE], *__buf; int err; - if (cnt > MAX_FLAG_OPT_SIZE) + if (!cnt || cnt > MAX_FLAG_OPT_SIZE) return -EINVAL; if (copy_from_user(&buf, ubuf, cnt)) @@ -490,6 +503,8 @@ static void do_inject(void) i_mce.tsc = rdtsc_ordered(); + i_mce.status |= MCI_STATUS_VAL; + if (i_mce.misc) i_mce.status |= MCI_STATUS_MISCV; @@ -577,6 +592,33 @@ static int inj_bank_set(void *data, u64 val) } m->bank = val; + + /* + * sw-only injection allows to write arbitrary values into the MCA + * registers because it tests only the decoding paths. + */ + if (inj_type == SW_INJ) + goto inject; + + /* + * Read IPID value to determine if a bank is populated on the target + * CPU. + */ + if (cpu_feature_enabled(X86_FEATURE_SMCA)) { + u64 ipid; + + if (rdmsrl_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) { + pr_err("Error reading IPID on CPU%d\n", m->extcpu); + return -EINVAL; + } + + if (!ipid) { + pr_err("Cannot inject into unpopulated bank %llu\n", val); + return -ENODEV; + } + } + +inject: do_inject(); /* Reset injection struct */ diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index acd61c41846c..52c633950b38 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -207,4 +207,6 @@ static inline void pentium_machine_check(struct pt_regs *regs) {} static inline void winchip_machine_check(struct pt_regs *regs) {} #endif +noinstr u64 mce_rdmsrl(u32 msr); + #endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index bb019a594a2c..7aa2bda93cbb 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -222,6 +222,9 @@ static bool is_copy_from_user(struct pt_regs *regs) struct insn insn; int ret; + if (!regs) + return false; + if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) return false; @@ -263,24 +266,36 @@ static bool is_copy_from_user(struct pt_regs *regs) * distinguish an exception taken in user from from one * taken in the kernel. */ -static int error_context(struct mce *m, struct pt_regs *regs) +static noinstr int error_context(struct mce *m, struct pt_regs *regs) { + int fixup_type; + bool copy_user; + if ((m->cs & 3) == 3) return IN_USER; + if (!mc_recoverable(m->mcgstatus)) return IN_KERNEL; - switch (ex_get_fixup_type(m->ip)) { + /* Allow instrumentation around external facilities usage. */ + instrumentation_begin(); + fixup_type = ex_get_fixup_type(m->ip); + copy_user = is_copy_from_user(regs); + instrumentation_end(); + + switch (fixup_type) { case EX_TYPE_UACCESS: case EX_TYPE_COPY: - if (!regs || !is_copy_from_user(regs)) + if (!copy_user) return IN_KERNEL; m->kflags |= MCE_IN_KERNEL_COPYIN; fallthrough; + case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV; return IN_KERNEL_RECOV; + default: return IN_KERNEL; } @@ -288,8 +303,7 @@ static int error_context(struct mce *m, struct pt_regs *regs) static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) { - u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); - u32 low, high; + u64 mcx_cfg; /* * We need to look at the following bits: @@ -300,11 +314,10 @@ static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) if (!mce_flags.succor) return MCE_PANIC_SEVERITY; - if (rdmsr_safe(addr, &low, &high)) - return MCE_PANIC_SEVERITY; + mcx_cfg = mce_rdmsrl(MSR_AMD64_SMCA_MCx_CONFIG(m->bank)); /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ - if ((low & MCI_CONFIG_MCAX) && + if ((mcx_cfg & MCI_CONFIG_MCAX) && (m->status & MCI_STATUS_TCC) && (err_ctx == IN_KERNEL)) return MCE_PANIC_SEVERITY; @@ -317,8 +330,8 @@ static int mce_severity_amd_smca(struct mce *m, enum context err_ctx) * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" */ -static int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant, - char **msg, bool is_excp) +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant, + char **msg, bool is_excp) { enum context ctx = error_context(m, regs); @@ -370,8 +383,8 @@ static int mce_severity_amd(struct mce *m, struct pt_regs *regs, int tolerant, return MCE_KEEP_SEVERITY; } -static int mce_severity_intel(struct mce *m, struct pt_regs *regs, - int tolerant, char **msg, bool is_excp) +static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, + int tolerant, char **msg, bool is_excp) { enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m, regs); @@ -407,8 +420,8 @@ static int mce_severity_intel(struct mce *m, struct pt_regs *regs, } } -int mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, - bool is_excp) +int noinstr mce_severity(struct mce *m, struct pt_regs *regs, int tolerant, char **msg, + bool is_excp) { if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index ff55df60228f..5a99f993e639 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -18,6 +18,7 @@ #include <linux/kexec.h> #include <linux/i8253.h> #include <linux/random.h> +#include <linux/swiotlb.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> @@ -79,7 +80,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0) inc_irq_stat(hyperv_stimer0_count); if (hv_stimer0_handler) hv_stimer0_handler(); - add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0); + add_interrupt_randomness(HYPERV_STIMER0_VECTOR); ack_APIC_irq(); set_irq_regs(old_regs); @@ -329,8 +330,20 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); - if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) + if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) { static_branch_enable(&isolation_type_snp); +#ifdef CONFIG_SWIOTLB + swiotlb_unencrypted_base = ms_hyperv.shared_gpa_boundary; +#endif + } + +#ifdef CONFIG_SWIOTLB + /* + * Enable swiotlb force mode in Isolation VM to + * use swiotlb bounce buffer for dma transaction. + */ + swiotlb_force = SWIOTLB_FORCE; +#endif } if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) { diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index c9f0f3d63f75..eaf25a234ff5 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -282,7 +282,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) u64 shift = 64 - width, chunks; chunks = (cur_msr << shift) - (prev_msr << shift); - return chunks >>= shift; + return chunks >> shift; } static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h index 9b204843b78d..fa04a73daf9c 100644 --- a/arch/x86/kernel/cpu/sgx/encls.h +++ b/arch/x86/kernel/cpu/sgx/encls.h @@ -11,26 +11,8 @@ #include <asm/traps.h> #include "sgx.h" -/** - * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr - * - * ENCLS has its own (positive value) error codes and also generates - * ENCLS specific #GP and #PF faults. And the ENCLS values get munged - * with system error codes as everything percolates back up the stack. - * Unfortunately (for us), we need to precisely identify each unique - * error code, e.g. the action taken if EWB fails varies based on the - * type of fault and on the exact SGX error code, i.e. we can't simply - * convert all faults to -EFAULT. - * - * To make all three error types coexist, we set bit 30 to identify an - * ENCLS fault. Bit 31 (technically bits N:31) is used to differentiate - * between positive (faults and SGX error codes) and negative (system - * error codes) values. - */ -#define ENCLS_FAULT_FLAG 0x40000000 - /* Retrieve the encoded trapnr from the specified return code. */ -#define ENCLS_TRAPNR(r) ((r) & ~ENCLS_FAULT_FLAG) +#define ENCLS_TRAPNR(r) ((r) & ~SGX_ENCLS_FAULT_FLAG) /* Issue a WARN() about an ENCLS function. */ #define ENCLS_WARN(r, name) { \ @@ -50,7 +32,7 @@ */ static inline bool encls_faulted(int ret) { - return ret & ENCLS_FAULT_FLAG; + return ret & SGX_ENCLS_FAULT_FLAG; } /** @@ -88,11 +70,7 @@ static inline bool encls_failed(int ret) asm volatile( \ "1: .byte 0x0f, 0x01, 0xcf;\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE_FAULT(1b, 3b) \ + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX) \ : "=a"(ret) \ : "a"(rax), inputs \ : "memory", "cc"); \ @@ -127,7 +105,7 @@ static inline bool encls_failed(int ret) * * Return: * 0 on success, - * trapnr with ENCLS_FAULT_FLAG set on fault + * trapnr with SGX_ENCLS_FAULT_FLAG set on fault */ #define __encls_N(rax, rbx_out, inputs...) \ ({ \ @@ -136,11 +114,7 @@ static inline bool encls_failed(int ret) "1: .byte 0x0f, 0x01, 0xcf;\n\t" \ " xor %%eax,%%eax;\n" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: orl $"__stringify(ENCLS_FAULT_FLAG)",%%eax\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE_FAULT(1b, 3b) \ + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_SGX) \ : "=a"(ret), "=b"(rbx_out) \ : "a"(rax), inputs \ : "memory"); \ diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 8471a8b9b48e..4b41efc9e367 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -6,11 +6,13 @@ #include <linux/highmem.h> #include <linux/kthread.h> #include <linux/miscdevice.h> +#include <linux/node.h> #include <linux/pagemap.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> +#include <linux/sysfs.h> #include <asm/sgx.h> #include "driver.h" #include "encl.h" @@ -20,6 +22,7 @@ struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS]; static int sgx_nr_epc_sections; static struct task_struct *ksgxd_tsk; static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); +static DEFINE_XARRAY(sgx_epc_address_space); /* * These variables are part of the state of the reclaimer, and must be accessed @@ -60,6 +63,24 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list) page = list_first_entry(dirty_page_list, struct sgx_epc_page, list); + /* + * Checking page->poison without holding the node->lock + * is racy, but losing the race (i.e. poison is set just + * after the check) just means __eremove() will be uselessly + * called for a page that sgx_free_epc_page() will put onto + * the node->sgx_poison_page_list later. + */ + if (page->poison) { + struct sgx_epc_section *section = &sgx_epc_sections[page->section]; + struct sgx_numa_node *node = section->node; + + spin_lock(&node->lock); + list_move(&page->list, &node->sgx_poison_page_list); + spin_unlock(&node->lock); + + continue; + } + ret = __eremove(sgx_get_epc_virt_addr(page)); if (!ret) { /* @@ -471,6 +492,7 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); + page->flags = 0; spin_unlock(&node->lock); atomic_long_dec(&sgx_nr_free_pages); @@ -624,7 +646,12 @@ void sgx_free_epc_page(struct sgx_epc_page *page) spin_lock(&node->lock); - list_add_tail(&page->list, &node->free_page_list); + page->owner = NULL; + if (page->poison) + list_add(&page->list, &node->sgx_poison_page_list); + else + list_add_tail(&page->list, &node->free_page_list); + page->flags = SGX_EPC_PAGE_IS_FREE; spin_unlock(&node->lock); atomic_long_inc(&sgx_nr_free_pages); @@ -648,17 +675,102 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, } section->phys_addr = phys_addr; + xa_store_range(&sgx_epc_address_space, section->phys_addr, + phys_addr + size - 1, section, GFP_KERNEL); for (i = 0; i < nr_pages; i++) { section->pages[i].section = index; section->pages[i].flags = 0; section->pages[i].owner = NULL; + section->pages[i].poison = 0; list_add_tail(§ion->pages[i].list, &sgx_dirty_page_list); } return true; } +bool arch_is_platform_page(u64 paddr) +{ + return !!xa_load(&sgx_epc_address_space, paddr); +} +EXPORT_SYMBOL_GPL(arch_is_platform_page); + +static struct sgx_epc_page *sgx_paddr_to_page(u64 paddr) +{ + struct sgx_epc_section *section; + + section = xa_load(&sgx_epc_address_space, paddr); + if (!section) + return NULL; + + return §ion->pages[PFN_DOWN(paddr - section->phys_addr)]; +} + +/* + * Called in process context to handle a hardware reported + * error in an SGX EPC page. + * If the MF_ACTION_REQUIRED bit is set in flags, then the + * context is the task that consumed the poison data. Otherwise + * this is called from a kernel thread unrelated to the page. + */ +int arch_memory_failure(unsigned long pfn, int flags) +{ + struct sgx_epc_page *page = sgx_paddr_to_page(pfn << PAGE_SHIFT); + struct sgx_epc_section *section; + struct sgx_numa_node *node; + + /* + * mm/memory-failure.c calls this routine for all errors + * where there isn't a "struct page" for the address. But that + * includes other address ranges besides SGX. + */ + if (!page) + return -ENXIO; + + /* + * If poison was consumed synchronously. Send a SIGBUS to + * the task. Hardware has already exited the SGX enclave and + * will not allow re-entry to an enclave that has a memory + * error. The signal may help the task understand why the + * enclave is broken. + */ + if (flags & MF_ACTION_REQUIRED) + force_sig(SIGBUS); + + section = &sgx_epc_sections[page->section]; + node = section->node; + + spin_lock(&node->lock); + + /* Already poisoned? Nothing more to do */ + if (page->poison) + goto out; + + page->poison = 1; + + /* + * If the page is on a free list, move it to the per-node + * poison page list. + */ + if (page->flags & SGX_EPC_PAGE_IS_FREE) { + list_move(&page->list, &node->sgx_poison_page_list); + goto out; + } + + /* + * TBD: Add additional plumbing to enable pre-emptive + * action for asynchronous poison notification. Until + * then just hope that the poison: + * a) is not accessed - sgx_free_epc_page() will deal with it + * when the user gives it back + * b) results in a recoverable machine check rather than + * a fatal one + */ +out: + spin_unlock(&node->lock); + return 0; +} + /** * A section metric is concatenated in a way that @low bits 12-31 define the * bits 12-31 of the metric and @high bits 0-19 define the bits 32-51 of the @@ -670,6 +782,48 @@ static inline u64 __init sgx_calc_section_metric(u64 low, u64 high) ((high & GENMASK_ULL(19, 0)) << 32); } +#ifdef CONFIG_NUMA +static ssize_t sgx_total_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", sgx_numa_nodes[dev->id].size); +} +static DEVICE_ATTR_RO(sgx_total_bytes); + +static umode_t arch_node_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int idx) +{ + /* Make all x86/ attributes invisible when SGX is not initialized: */ + if (nodes_empty(sgx_numa_mask)) + return 0; + + return attr->mode; +} + +static struct attribute *arch_node_dev_attrs[] = { + &dev_attr_sgx_total_bytes.attr, + NULL, +}; + +const struct attribute_group arch_node_dev_group = { + .name = "x86", + .attrs = arch_node_dev_attrs, + .is_visible = arch_node_attr_is_visible, +}; + +static void __init arch_update_sysfs_visibility(int nid) +{ + struct node *node = node_devices[nid]; + int ret; + + ret = sysfs_update_group(&node->dev.kobj, &arch_node_dev_group); + + if (ret) + pr_err("sysfs update failed (%d), files may be invisible", ret); +} +#else /* !CONFIG_NUMA */ +static void __init arch_update_sysfs_visibility(int nid) {} +#endif + static bool __init sgx_page_cache_init(void) { u32 eax, ebx, ecx, edx, type; @@ -713,10 +867,16 @@ static bool __init sgx_page_cache_init(void) if (!node_isset(nid, sgx_numa_mask)) { spin_lock_init(&sgx_numa_nodes[nid].lock); INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list); + INIT_LIST_HEAD(&sgx_numa_nodes[nid].sgx_poison_page_list); node_set(nid, sgx_numa_mask); + sgx_numa_nodes[nid].size = 0; + + /* Make SGX-specific node sysfs files visible: */ + arch_update_sysfs_visibility(nid); } sgx_epc_sections[i].node = &sgx_numa_nodes[nid]; + sgx_numa_nodes[nid].size += size; sgx_nr_epc_sections++; } diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index 4628acec0009..0f17def9fe6f 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -26,9 +26,13 @@ /* Pages, which are being tracked by the page reclaimer. */ #define SGX_EPC_PAGE_RECLAIMER_TRACKED BIT(0) +/* Pages on free list */ +#define SGX_EPC_PAGE_IS_FREE BIT(1) + struct sgx_epc_page { unsigned int section; - unsigned int flags; + u16 flags; + u16 poison; struct sgx_encl_page *owner; struct list_head list; }; @@ -39,6 +43,8 @@ struct sgx_epc_page { */ struct sgx_numa_node { struct list_head free_page_list; + struct list_head sgx_poison_page_list; + unsigned long size; spinlock_t lock; }; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index ea4fe192189d..53de044e5654 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -351,7 +351,7 @@ unsigned long oops_begin(void) } NOKPROBE_SYMBOL(oops_begin); -void __noreturn rewind_stack_do_exit(int signr); +void __noreturn rewind_stack_and_make_dead(int signr); void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { @@ -386,7 +386,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * reuse the task stack and that existing poisons are invalid. */ kasan_unpoison_task_stack(current); - rewind_stack_do_exit(signr); + rewind_stack_and_make_dead(signr); } NOKPROBE_SYMBOL(oops_end); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 391a4e2b8604..fd2d3ab38ebb 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -554,6 +554,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = { INTEL_RKL_IDS(&gen11_early_ops), INTEL_ADLS_IDS(&gen11_early_ops), INTEL_ADLP_IDS(&gen11_early_ops), + INTEL_RPLS_IDS(&gen11_early_ops), }; struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 8ea306b1bf8e..8dea01ffc5c1 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -99,6 +99,19 @@ bool irq_fpu_usable(void) EXPORT_SYMBOL(irq_fpu_usable); /* + * Track AVX512 state use because it is known to slow the max clock + * speed of the core. + */ +static void update_avx_timestamp(struct fpu *fpu) +{ + +#define AVX512_TRACKING_MASK (XFEATURE_MASK_ZMM_Hi256 | XFEATURE_MASK_Hi16_ZMM) + + if (fpu->fpstate->regs.xsave.header.xfeatures & AVX512_TRACKING_MASK) + fpu->avx512_timestamp = jiffies; +} + +/* * Save the FPU register state in fpu->fpstate->regs. The register state is * preserved. * @@ -116,13 +129,7 @@ void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(fpu->fpstate); - - /* - * AVX512 state is tracked here because its use is - * known to slow the max clock speed of the core. - */ - if (fpu->fpstate->regs.xsave.header.xfeatures & XFEATURE_MASK_AVX512) - fpu->avx512_timestamp = jiffies; + update_avx_timestamp(fpu); return; } @@ -199,7 +206,27 @@ void fpu_reset_from_exception_fixup(void) } #if IS_ENABLED(CONFIG_KVM) -static void __fpstate_reset(struct fpstate *fpstate); +static void __fpstate_reset(struct fpstate *fpstate, u64 xfd); + +static void fpu_init_guest_permissions(struct fpu_guest *gfpu) +{ + struct fpu_state_perm *fpuperm; + u64 perm; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + spin_lock_irq(¤t->sighand->siglock); + fpuperm = ¤t->group_leader->thread.fpu.guest_perm; + perm = fpuperm->__state_perm; + + /* First fpstate allocation locks down permissions. */ + WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED); + + spin_unlock_irq(¤t->sighand->siglock); + + gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED; +} bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) { @@ -211,12 +238,18 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) if (!fpstate) return false; - __fpstate_reset(fpstate); + /* Leave xfd to 0 (the reset value defined by spec) */ + __fpstate_reset(fpstate, 0); fpstate_init_user(fpstate); fpstate->is_valloc = true; fpstate->is_guest = true; - gfpu->fpstate = fpstate; + gfpu->fpstate = fpstate; + gfpu->xfeatures = fpu_user_cfg.default_features; + gfpu->perm = fpu_user_cfg.default_features; + gfpu->uabi_size = fpu_user_cfg.default_size; + fpu_init_guest_permissions(gfpu); + return true; } EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate); @@ -236,6 +269,64 @@ void fpu_free_guest_fpstate(struct fpu_guest *gfpu) } EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate); +/* + * fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable + * @guest_fpu: Pointer to the guest FPU container + * @xfeatures: Features requested by guest CPUID + * + * Enable all dynamic xfeatures according to guest perm and requested CPUID. + * + * Return: 0 on success, error code otherwise + */ +int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures) +{ + lockdep_assert_preemption_enabled(); + + /* Nothing to do if all requested features are already enabled. */ + xfeatures &= ~guest_fpu->xfeatures; + if (!xfeatures) + return 0; + + return __xfd_enable_feature(xfeatures, guest_fpu); +} +EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features); + +#ifdef CONFIG_X86_64 +void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) +{ + fpregs_lock(); + guest_fpu->fpstate->xfd = xfd; + if (guest_fpu->fpstate->in_use) + xfd_update_state(guest_fpu->fpstate); + fpregs_unlock(); +} +EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); + +/** + * fpu_sync_guest_vmexit_xfd_state - Synchronize XFD MSR and software state + * + * 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 + * any operation which depends on it can take place. + * + * Note: It can be invoked unconditionally even when write emulation is + * enabled for the price of a then pointless MSR read. + */ +void fpu_sync_guest_vmexit_xfd_state(void) +{ + struct fpstate *fps = current->thread.fpu.fpstate; + + lockdep_assert_irqs_disabled(); + if (fpu_state_size_dynamic()) { + rdmsrl(MSR_IA32_XFD, fps->xfd); + __this_cpu_write(xfd_state, fps->xfd); + } +} +EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state); +#endif /* CONFIG_X86_64 */ + int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) { struct fpstate *guest_fps = guest_fpu->fpstate; @@ -430,26 +521,28 @@ void fpstate_init_user(struct fpstate *fpstate) fpstate_init_fstate(fpstate); } -static void __fpstate_reset(struct fpstate *fpstate) +static void __fpstate_reset(struct fpstate *fpstate, u64 xfd) { /* Initialize sizes and feature masks */ fpstate->size = fpu_kernel_cfg.default_size; fpstate->user_size = fpu_user_cfg.default_size; fpstate->xfeatures = fpu_kernel_cfg.default_features; fpstate->user_xfeatures = fpu_user_cfg.default_features; - fpstate->xfd = init_fpstate.xfd; + fpstate->xfd = xfd; } void fpstate_reset(struct fpu *fpu) { /* Set the fpstate pointer to the default fpstate */ fpu->fpstate = &fpu->__fpstate; - __fpstate_reset(fpu->fpstate); + __fpstate_reset(fpu->fpstate, init_fpstate.xfd); /* Initialize the permission related info in fpu */ fpu->perm.__state_perm = fpu_kernel_cfg.default_features; fpu->perm.__state_size = fpu_kernel_cfg.default_size; fpu->perm.__user_state_size = fpu_user_cfg.default_size; + /* Same defaults for guests */ + fpu->guest_perm = fpu->perm; } static inline void fpu_inherit_perms(struct fpu *dst_fpu) @@ -460,6 +553,7 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu) spin_lock_irq(¤t->sighand->siglock); /* Fork also inherits the permissions of the parent */ dst_fpu->perm = src_fpu->perm; + dst_fpu->guest_perm = src_fpu->guest_perm; spin_unlock_irq(¤t->sighand->siglock); } } diff --git a/arch/x86/kernel/fpu/legacy.h b/arch/x86/kernel/fpu/legacy.h index 17c26b164c63..098f367bb8a7 100644 --- a/arch/x86/kernel/fpu/legacy.h +++ b/arch/x86/kernel/fpu/legacy.h @@ -35,11 +35,7 @@ static inline void ldmxcsr(u32 mxcsr) int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d5958278eba6..91d4b6de58ab 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, struct fpstate *fpstate) { struct xregs_state __user *x = buf; - struct _fpx_sw_bytes sw_bytes; + struct _fpx_sw_bytes sw_bytes = {}; u32 xfeatures; int err; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index d28829403ed0..02b3ddaf4f75 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1500,35 +1500,13 @@ void fpstate_free(struct fpu *fpu) } /** - * fpu_install_fpstate - Update the active fpstate in the FPU - * - * @fpu: A struct fpu * pointer - * @newfps: A struct fpstate * pointer - * - * Returns: A null pointer if the last active fpstate is the embedded - * one or the new fpstate is already installed; - * otherwise, a pointer to the old fpstate which has to - * be freed by the caller. - */ -static struct fpstate *fpu_install_fpstate(struct fpu *fpu, - struct fpstate *newfps) -{ - struct fpstate *oldfps = fpu->fpstate; - - if (fpu->fpstate == newfps) - return NULL; - - fpu->fpstate = newfps; - return oldfps != &fpu->__fpstate ? oldfps : NULL; -} - -/** * fpstate_realloc - Reallocate struct fpstate for the requested new features * * @xfeatures: A bitmap of xstate features which extend the enabled features * of that task * @ksize: The required size for the kernel buffer * @usize: The required size for user space buffers + * @guest_fpu: Pointer to a guest FPU container. NULL for host allocations * * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer * terminates quickly, vfree()-induced IPIs may be a concern, but tasks @@ -1537,13 +1515,13 @@ static struct fpstate *fpu_install_fpstate(struct fpu *fpu, * Returns: 0 on success, -ENOMEM on allocation error. */ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, - unsigned int usize) + unsigned int usize, struct fpu_guest *guest_fpu) { struct fpu *fpu = ¤t->thread.fpu; struct fpstate *curfps, *newfps = NULL; unsigned int fpsize; + bool in_use; - curfps = fpu->fpstate; fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64); newfps = vzalloc(fpsize); @@ -1553,28 +1531,56 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, newfps->user_size = usize; newfps->is_valloc = true; + /* + * When a guest FPU is supplied, use @guest_fpu->fpstate + * as reference independent whether it is in use or not. + */ + curfps = guest_fpu ? guest_fpu->fpstate : fpu->fpstate; + + /* Determine whether @curfps is the active fpstate */ + in_use = fpu->fpstate == curfps; + + if (guest_fpu) { + newfps->is_guest = true; + newfps->is_confidential = curfps->is_confidential; + newfps->in_use = curfps->in_use; + guest_fpu->xfeatures |= xfeatures; + guest_fpu->uabi_size = usize; + } + fpregs_lock(); /* - * Ensure that the current state is in the registers before - * swapping fpstate as that might invalidate it due to layout - * changes. + * If @curfps is in use, ensure that the current state is in the + * registers before swapping fpstate as that might invalidate it + * due to layout changes. */ - if (test_thread_flag(TIF_NEED_FPU_LOAD)) + if (in_use && test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; - curfps = fpu_install_fpstate(fpu, newfps); - /* Do the final updates within the locked region */ xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures); - xfd_update_state(newfps); + if (guest_fpu) { + guest_fpu->fpstate = newfps; + /* If curfps is active, update the FPU fpstate pointer */ + if (in_use) + fpu->fpstate = newfps; + } else { + fpu->fpstate = newfps; + } + + if (in_use) + xfd_update_state(fpu->fpstate); fpregs_unlock(); - vfree(curfps); + /* Only free valloc'ed state */ + if (curfps && curfps->is_valloc) + vfree(curfps); + return 0; } @@ -1595,7 +1601,7 @@ static int validate_sigaltstack(unsigned int usize) return 0; } -static int __xstate_request_perm(u64 permitted, u64 requested) +static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) { /* * This deliberately does not exclude !XSAVES as we still might @@ -1605,9 +1611,10 @@ static int __xstate_request_perm(u64 permitted, u64 requested) */ bool compacted = cpu_feature_enabled(X86_FEATURE_XSAVES); struct fpu *fpu = ¤t->group_leader->thread.fpu; + struct fpu_state_perm *perm; unsigned int ksize, usize; u64 mask; - int ret; + int ret = 0; /* Check whether fully enabled */ if ((permitted & requested) == requested) @@ -1621,15 +1628,18 @@ static int __xstate_request_perm(u64 permitted, u64 requested) mask &= XFEATURE_MASK_USER_SUPPORTED; usize = xstate_calculate_size(mask, false); - ret = validate_sigaltstack(usize); - if (ret) - return ret; + if (!guest) { + ret = validate_sigaltstack(usize); + if (ret) + return ret; + } + perm = guest ? &fpu->guest_perm : &fpu->perm; /* Pairs with the READ_ONCE() in xstate_get_group_perm() */ - WRITE_ONCE(fpu->perm.__state_perm, requested); + WRITE_ONCE(perm->__state_perm, requested); /* Protected by sighand lock */ - fpu->perm.__state_size = ksize; - fpu->perm.__user_state_size = usize; + perm->__state_size = ksize; + perm->__user_state_size = usize; return ret; } @@ -1640,7 +1650,7 @@ static const u64 xstate_prctl_req[XFEATURE_MAX] = { [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA, }; -static int xstate_request_perm(unsigned long idx) +static int xstate_request_perm(unsigned long idx, bool guest) { u64 permitted, requested; int ret; @@ -1661,26 +1671,33 @@ static int xstate_request_perm(unsigned long idx) return -EOPNOTSUPP; /* Lockless quick check */ - permitted = xstate_get_host_group_perm(); + permitted = xstate_get_group_perm(guest); if ((permitted & requested) == requested) return 0; /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); - permitted = xstate_get_host_group_perm(); - ret = __xstate_request_perm(permitted, requested); + permitted = xstate_get_group_perm(guest); + + /* First vCPU allocation locks the permissions. */ + if (guest && (permitted & FPU_GUEST_PERM_LOCKED)) + ret = -EBUSY; + else + ret = __xstate_request_perm(permitted, requested, guest); spin_unlock_irq(¤t->sighand->siglock); return ret; } -int xfd_enable_feature(u64 xfd_err) +int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu) { u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC; + struct fpu_state_perm *perm; unsigned int ksize, usize; struct fpu *fpu; if (!xfd_event) { - pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err); + if (!guest_fpu) + pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err); return 0; } @@ -1688,14 +1705,16 @@ int xfd_enable_feature(u64 xfd_err) spin_lock_irq(¤t->sighand->siglock); /* If not permitted let it die */ - if ((xstate_get_host_group_perm() & xfd_event) != xfd_event) { + if ((xstate_get_group_perm(!!guest_fpu) & xfd_event) != xfd_event) { spin_unlock_irq(¤t->sighand->siglock); return -EPERM; } fpu = ¤t->group_leader->thread.fpu; - ksize = fpu->perm.__state_size; - usize = fpu->perm.__user_state_size; + perm = guest_fpu ? &fpu->guest_perm : &fpu->perm; + ksize = perm->__state_size; + usize = perm->__user_state_size; + /* * The feature is permitted. State size is sufficient. Dropping * the lock is safe here even if more features are added from @@ -1708,17 +1727,29 @@ int xfd_enable_feature(u64 xfd_err) * Try to allocate a new fpstate. If that fails there is no way * out. */ - if (fpstate_realloc(xfd_event, ksize, usize)) + if (fpstate_realloc(xfd_event, ksize, usize, guest_fpu)) return -EFAULT; return 0; } + +int xfd_enable_feature(u64 xfd_err) +{ + return __xfd_enable_feature(xfd_err, NULL); +} + #else /* CONFIG_X86_64 */ -static inline int xstate_request_perm(unsigned long idx) +static inline int xstate_request_perm(unsigned long idx, bool guest) { return -EPERM; } #endif /* !CONFIG_X86_64 */ +u64 xstate_get_guest_group_perm(void) +{ + return xstate_get_group_perm(true); +} +EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); + /** * fpu_xstate_prctl - xstate permission operations * @tsk: Redundant pointer to current @@ -1742,6 +1773,7 @@ long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2) u64 __user *uptr = (u64 __user *)arg2; u64 permitted, supported; unsigned long idx = arg2; + bool guest = false; if (tsk != current) return -EPERM; @@ -1760,11 +1792,20 @@ long fpu_xstate_prctl(struct task_struct *tsk, int option, unsigned long arg2) permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); + case ARCH_GET_XCOMP_GUEST_PERM: + permitted = xstate_get_guest_group_perm(); + permitted &= XFEATURE_MASK_USER_SUPPORTED; + return put_user(permitted, uptr); + + case ARCH_REQ_XCOMP_GUEST_PERM: + guest = true; + fallthrough; + case ARCH_REQ_XCOMP_PERM: if (!IS_ENABLED(CONFIG_X86_64)) return -EOPNOTSUPP; - return xstate_request_perm(idx); + return xstate_request_perm(idx, guest); default: return -EINVAL; diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 86ea7c0fa2f6..d22ace092ca2 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -20,10 +20,19 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; } -static inline u64 xstate_get_host_group_perm(void) +static inline u64 xstate_get_group_perm(bool guest) { + struct fpu *fpu = ¤t->group_leader->thread.fpu; + struct fpu_state_perm *perm; + /* Pairs with WRITE_ONCE() in xstate_request_perm() */ - return READ_ONCE(current->group_leader->thread.fpu.perm.__state_perm); + perm = guest ? &fpu->guest_perm : &fpu->perm; + return READ_ONCE(perm->__state_perm); +} + +static inline u64 xstate_get_host_group_perm(void) +{ + return xstate_get_group_perm(false); } enum xstate_copy_mode { @@ -108,11 +117,7 @@ static inline u64 xfeatures_mask_independent(void) "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ - ".pushsection .fixup,\"ax\"\n" \ - "4: movl $-2, %[err]\n" \ - "jmp 3b\n" \ - ".popsection\n" \ - _ASM_EXTABLE(661b, 4b) \ + _ASM_EXTABLE_TYPE_REG(661b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") @@ -149,8 +154,14 @@ static inline void xfd_update_state(struct fpstate *fpstate) } } } + +extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else static inline void xfd_update_state(struct fpstate *fpstate) { } + +static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { + return -EPERM; +} #endif /* diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c39f906cdc4e..7cc540e6de0c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -303,7 +303,7 @@ union ftrace_op_code_union { } __attribute__((packed)); }; -#define RET_SIZE 1 +#define RET_SIZE 1 + IS_ENABLED(CONFIG_SLS) static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index e405fe1a8bf4..a0ed0e4a2c0c 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -19,7 +19,7 @@ #endif SYM_FUNC_START(__fentry__) - ret + RET SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) @@ -84,7 +84,7 @@ ftrace_graph_call: /* This is weak to keep gas from relaxing the jumps */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) - ret + RET SYM_CODE_END(ftrace_caller) SYM_CODE_START(ftrace_regs_caller) @@ -177,7 +177,7 @@ SYM_CODE_START(ftrace_graph_caller) popl %edx popl %ecx popl %eax - ret + RET SYM_CODE_END(ftrace_graph_caller) .globl return_to_handler diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 7a879901f103..11ac028e30e4 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -132,7 +132,7 @@ #ifdef CONFIG_DYNAMIC_FTRACE SYM_FUNC_START(__fentry__) - retq + RET SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) @@ -176,11 +176,11 @@ SYM_FUNC_END(ftrace_caller); SYM_FUNC_START(ftrace_epilogue) /* * This is weak to keep gas from relaxing the jumps. - * It is also used to copy the retq for trampolines. + * It is also used to copy the RET for trampolines. */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) UNWIND_HINT_FUNC - retq + RET SYM_FUNC_END(ftrace_epilogue) SYM_FUNC_START(ftrace_regs_caller) @@ -284,7 +284,7 @@ SYM_FUNC_START(__fentry__) jnz trace SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) - retq + RET trace: /* save_mcount_regs fills in first two parameters */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index fc5371a7e9d1..de563db9cdcd 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -126,6 +126,36 @@ static bool __head check_la57_support(unsigned long physaddr) } #endif +static unsigned long sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd) +{ + unsigned long vaddr, vaddr_end; + int i; + + /* Encrypt the kernel and related (if SME is active) */ + sme_encrypt_kernel(bp); + + /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (sme_get_me_mask()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* + * Return the SME encryption mask (if SME is active) to be used as a + * modifier for the initial pgdir entry programmed into CR3. + */ + return sme_get_me_mask(); +} + /* Code in __startup_64() can be relocated during execution, but the compiler * doesn't have to generate PC-relative relocations when accessing globals from * that function. Clang actually does not generate them, which leads to @@ -135,7 +165,6 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { - unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -276,34 +305,7 @@ unsigned long __head __startup_64(unsigned long physaddr, */ *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask(); - /* Encrypt the kernel and related (if SME is active) */ - sme_encrypt_kernel(bp); - - /* - * Clear the memory encryption mask from the .bss..decrypted section. - * The bss section will be memset to zero later in the initialization so - * there is no need to zero it after changing the memory encryption - * attribute. - * - * This is early code, use an open coded check for SME instead of - * using cc_platform_has(). This eliminates worries about removing - * instrumentation or checking boot_cpu_data in the cc_platform_has() - * function. - */ - if (sme_get_me_mask()) { - vaddr = (unsigned long)__start_bss_decrypted; - vaddr_end = (unsigned long)__end_bss_decrypted; - for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { - i = pmd_index(vaddr); - pmd[i] -= sme_get_me_mask(); - } - } - - /* - * Return the SME encryption mask (if SME is active) to be used as a - * modifier for the initial pgdir entry programmed into CR3. - */ - return sme_get_me_mask(); + return sme_postprocess_startup(bp, pmd); } unsigned long __startup_secondary_64(void) @@ -485,6 +487,10 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); + /* + * This needs to happen *before* kasan_early_init() because latter maps stuff + * into that page. + */ clear_page(init_top_pgt); /* @@ -496,6 +502,16 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) kasan_early_init(); + /* + * Flush global TLB entries which could be left over from the trampoline page + * table. + * + * This needs to happen *after* kasan_early_init() as KASAN-enabled .configs + * instrument native_write_cr4() so KASAN must be initialized for that + * instrumentation to work. + */ + __native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4)); + idt_setup_early_handler(); copy_bootdata(__va(real_mode_data)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index d8c64dab0efe..eb8656bac99b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -340,7 +340,7 @@ SYM_FUNC_END(startup_32_smp) __INIT setup_once: andl $0,setup_once_ref /* Once is enough, thanks */ - ret + RET SYM_FUNC_START(early_idt_handler_array) # 36(%esp) %eflags diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d8b3ebd2bb85..9c63fc5988cd 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -166,9 +166,26 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) call sev_verify_cbit popq %rsi - /* Switch to new page-table */ + /* + * 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 + * init_top_pgt here, away from the trampoline_pgd and unmap the + * indentity mapped ranges. + */ movq %rax, %cr3 + /* + * Do a global TLB flush after the CR3 switch to make sure the TLB + * entries from the identity mapping are flushed. + */ + movq %cr4, %rcx + movq %rcx, %rax + xorq $X86_CR4_PGE, %rcx + movq %rcx, %cr4 + movq %rax, %cr4 + /* Ensure I am executing from virtual addresses */ movq $1f, %rax ANNOTATE_RETPOLINE_SAFE diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index 760e1f293093..aaf9e776f323 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -11,7 +11,7 @@ SYM_FUNC_START(native_save_fl) pushf pop %_ASM_AX - ret + RET SYM_FUNC_END(native_save_fl) .popsection EXPORT_SYMBOL(native_save_fl) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index fce99e249d61..6290712cb36d 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1051,7 +1051,7 @@ asm( " addl $4, %esp\n" " popfl\n" #endif - " ret\n" + ASM_RET ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n" ); NOKPROBE_SYMBOL(__kretprobe_trampoline); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 59abbdad7729..a438217cbfac 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -313,7 +313,7 @@ static void kvm_register_steal_time(void) return; wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED)); - pr_info("stealtime: cpu %d, msr %llx\n", cpu, + pr_debug("stealtime: cpu %d, msr %llx\n", cpu, (unsigned long long) slow_virt_to_phys(st)); } @@ -350,7 +350,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); - pr_info("setup async PF for cpu %d\n", smp_processor_id()); + pr_debug("setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { @@ -376,7 +376,7 @@ static void kvm_pv_disable_apf(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(apf_reason.enabled, 0); - pr_info("disable async PF for cpu %d\n", smp_processor_id()); + pr_debug("disable async PF for cpu %d\n", smp_processor_id()); } static void kvm_disable_steal_time(void) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 462dd8e9b03d..a35cbf9107af 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -174,7 +174,7 @@ static void kvm_register_clock(char *txt) pa = slow_virt_to_phys(&src->pvti) | 0x01ULL; wrmsrl(msr_kvm_system_time, pa); - pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt); + pr_debug("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt); } static void kvm_save_sched_clock_state(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 169fb6f4cd2e..95fa745e310a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -67,6 +67,7 @@ static unsigned long int get_module_load_offset(void) void *module_alloc(unsigned long size) { + gfp_t gfp_mask = GFP_KERNEL; void *p; if (PAGE_ALIGN(size) > MODULES_LEN) @@ -74,10 +75,10 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), - MODULES_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, + MODULES_END, gfp_mask, + PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7f7636aac620..4420499f7bb4 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -41,7 +41,7 @@ extern void _paravirt_nop(void); asm (".pushsection .entry.text, \"ax\"\n" ".global _paravirt_nop\n" "_paravirt_nop:\n\t" - "ret\n\t" + ASM_RET ".size _paravirt_nop, . - _paravirt_nop\n\t" ".type _paravirt_nop, @function\n\t" ".popsection"); @@ -51,7 +51,7 @@ asm (".pushsection .entry.text, \"ax\"\n" ".global paravirt_ret0\n" "paravirt_ret0:\n\t" "xor %" _ASM_AX ", %" _ASM_AX ";\n\t" - "ret\n\t" + ASM_RET ".size paravirt_ret0, . - paravirt_ret0\n\t" ".type paravirt_ret0, @function\n\t" ".popsection"); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 04143a653a8a..81d8ef036637 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -365,7 +365,7 @@ void arch_setup_new_exec(void) clear_thread_flag(TIF_SSBD); task_clear_spec_ssb_disable(current); task_clear_spec_ssb_noexec(current); - speculation_ctrl_update(task_thread_info(current)->flags); + speculation_ctrl_update(read_thread_flags()); } } @@ -617,7 +617,7 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) clear_tsk_thread_flag(tsk, TIF_SPEC_IB); } /* Return the updated threadinfo flags*/ - return task_thread_info(tsk)->flags; + return read_task_thread_flags(tsk); } void speculation_ctrl_update(unsigned long tif) @@ -653,8 +653,8 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) { unsigned long tifp, tifn; - tifn = READ_ONCE(task_thread_info(next_p)->flags); - tifp = READ_ONCE(task_thread_info(prev_p)->flags); + tifn = read_task_thread_flags(next_p); + tifp = read_task_thread_flags(prev_p); switch_to_bitmap(tifp); @@ -993,6 +993,8 @@ long do_arch_prctl_common(struct task_struct *task, int option, case ARCH_GET_XCOMP_SUPP: case ARCH_GET_XCOMP_PERM: case ARCH_REQ_XCOMP_PERM: + case ARCH_GET_XCOMP_GUEST_PERM: + case ARCH_REQ_XCOMP_GUEST_PERM: return fpu_xstate_prctl(task, option, arg2); } diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h index 1d0797b2338a..76b547b83232 100644 --- a/arch/x86/kernel/process.h +++ b/arch/x86/kernel/process.h @@ -13,8 +13,8 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p); static inline void switch_to_extra(struct task_struct *prev, struct task_struct *next) { - unsigned long next_tif = task_thread_info(next)->flags; - unsigned long prev_tif = task_thread_info(prev)->flags; + unsigned long next_tif = read_task_thread_flags(next); + unsigned long prev_tif = read_task_thread_flags(prev); if (IS_ENABLED(CONFIG_SMP)) { /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0a40df66a40d..fa700b46588e 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -113,17 +113,9 @@ void __noreturn machine_real_restart(unsigned int type) spin_unlock(&rtc_lock); /* - * Switch back to the initial page table. + * Switch to the trampoline page table. */ -#ifdef CONFIG_X86_32 - load_cr3(initial_page_table); -#else - write_cr3(real_mode_header->trampoline_pgd); - - /* Exiting long mode will fail if CR4.PCIDE is set. */ - if (boot_cpu_has(X86_FEATURE_PCID)) - cr4_clear_bits(X86_CR4_PCIDE); -#endif + load_trampoline_pgtable(); /* Jump to the identity-mapped low memory code */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index f469153eca8a..fcc8a7699103 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -91,7 +91,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) movl %edi, %eax addl $(identity_mapped - relocate_kernel), %eax pushl %eax - ret + RET SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -159,7 +159,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %edx, %edx xorl %esi, %esi xorl %ebp, %ebp - ret + RET 1: popl %edx movl CP_PA_SWAP_PAGE(%edi), %esp @@ -190,7 +190,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movl %edi, %eax addl $(virtual_mapped - relocate_kernel), %eax pushl %eax - ret + RET SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -208,7 +208,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popl %edi popl %esi popl %ebx - ret + RET SYM_CODE_END(virtual_mapped) /* Do the copies */ @@ -271,7 +271,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) popl %edi popl %ebx popl %ebp - ret + RET SYM_CODE_END(swap_pages) .globl kexec_control_code_size diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index c8fe74a28143..399f075ccdc4 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -104,7 +104,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) /* jump to identity mapped page */ addq $(identity_mapped - relocate_kernel), %r8 pushq %r8 - ret + RET SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -191,7 +191,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %r14d, %r14d xorl %r15d, %r15d - ret + RET 1: popq %rdx @@ -210,7 +210,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) call swap_pages movq $virtual_mapped, %rax pushq %rax - ret + RET SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -231,7 +231,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popq %r12 popq %rbp popq %rbx - ret + RET SYM_CODE_END(virtual_mapped) /* Do the copies */ @@ -288,7 +288,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) lea PAGE_SIZE(%rax), %rsi jmp 0b 3: - ret + RET SYM_CODE_END(swap_pages) .globl kexec_control_code_size diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 9b9fb7882c20..9ae64f9af956 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/dmi.h> #include <linux/ioport.h> #include <asm/e820/api.h> @@ -23,11 +24,31 @@ static void resource_clip(struct resource *res, resource_size_t start, res->start = end + 1; } +/* + * Some BIOS-es contain a bug where they add addresses which map to + * system RAM in the PCI host bridge window returned by the ACPI _CRS + * method, see commit 4dc2287c1805 ("x86: avoid E820 regions when + * allocating address space"). To avoid this Linux by default excludes + * E820 reservations when allocating addresses since 2010. + * In 2019 some systems have shown-up with E820 reservations which cover + * the entire _CRS returned PCI host bridge window, causing all attempts + * to assign memory to PCI BARs to fail if Linux uses E820 reservations. + * + * Ideally Linux would fully stop using E820 reservations, but then + * the old systems this was added for will regress. + * Instead keep the old behavior for old systems, while ignoring the + * E820 reservations for any systems from now on. + */ static void remove_e820_regions(struct resource *avail) { - int i; + int i, year = dmi_get_bios_year(); struct e820_entry *entry; + if (year >= 2018) + return; + + pr_info_once("PCI: Removing E820 reservations from host bridge windows\n"); + for (i = 0; i < e820_table->nr_entries; i++) { entry = &e820_table->entries[i]; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6a190c7f4d71..f7a132eb794d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -40,6 +40,7 @@ #include <asm/kasan.h> #include <asm/kaslr.h> #include <asm/mce.h> +#include <asm/memtype.h> #include <asm/mtrr.h> #include <asm/realmode.h> #include <asm/olpc_ofw.h> @@ -713,9 +714,6 @@ static void __init early_reserve_memory(void) early_reserve_initrd(); - if (efi_enabled(EFI_BOOT)) - efi_memblock_x86_reserve_range(); - memblock_x86_reserve_range_setup_data(); reserve_ibft_region(); @@ -742,28 +740,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } -static char * __init prepare_command_line(void) -{ -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0]) { - /* append boot loader cmdline to builtin */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - - parse_early_param(); - - return command_line; -} - /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -853,23 +829,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); /* - * x86_configure_nx() is called before parse_early_param() (called by - * prepare_command_line()) to detect whether hardware doesn't support - * NX (so that the early EHCI debug console setup can safely call - * set_fixmap()). It may then be called again from within noexec_setup() - * during parsing early parameters to honor the respective command line - * option. - */ - x86_configure_nx(); - - /* - * This parses early params and it needs to run before - * early_reserve_memory() because latter relies on such settings - * supplied as early params. - */ - *cmdline_p = prepare_command_line(); - - /* * Do some memory reservations *before* memory is added to memblock, so * memblock allocations won't overwrite it. * @@ -902,6 +861,36 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = __pa_symbol(__bss_start); bss_resource.end = __pa_symbol(__bss_stop)-1; +#ifdef CONFIG_CMDLINE_BOOL +#ifdef CONFIG_CMDLINE_OVERRIDE + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); +#else + if (builtin_cmdline[0]) { + /* append boot loader cmdline to builtin */ + strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); + strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + } +#endif +#endif + + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + *cmdline_p = command_line; + + /* + * x86_configure_nx() is called before parse_early_param() to detect + * whether hardware doesn't support NX (so that the early EHCI debug + * console setup can safely call set_fixmap()). It may then be called + * again from within noexec_setup() during parsing early parameters + * to honor the respective command line option. + */ + x86_configure_nx(); + + parse_early_param(); + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); + #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux @@ -979,7 +968,11 @@ void __init setup_arch(char **cmdline_p) max_pfn = e820__end_of_ram_pfn(); /* update e820 for memory not covered by WB MTRRs */ - mtrr_bp_init(); + if (IS_ENABLED(CONFIG_MTRR)) + mtrr_bp_init(); + else + pat_disable("PAT support disabled because CONFIG_MTRR is disabled in the kernel."); + if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820__end_of_ram_pfn(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 787dc5f568b5..ce987688bbc0 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -221,7 +221,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) fail: /* Terminate the guest */ - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); } static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 74f0ec955384..e6d316a01fdd 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -26,6 +26,7 @@ #include <asm/fpu/xcr.h> #include <asm/processor.h> #include <asm/realmode.h> +#include <asm/setup.h> #include <asm/traps.h> #include <asm/svm.h> #include <asm/smp.h> @@ -86,9 +87,6 @@ struct ghcb_state { static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data); DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); -/* Needed in vc_early_forward_exception */ -void do_early_exception(struct pt_regs *regs, int trapnr); - static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -209,9 +207,6 @@ static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state) return ghcb; } -/* Needed in vc_early_forward_exception */ -void do_early_exception(struct pt_regs *regs, int trapnr); - static inline u64 sev_es_rd_ghcb_msr(void) { return __rdmsr(MSR_AMD64_SEV_ES_GHCB); @@ -294,11 +289,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, char *dst, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; - char __user *target = (char __user *)dst; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __put_user() independent of whether kernel or user @@ -320,26 +310,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *target = (u8 __user *)dst; + memcpy(&d1, buf, 1); if (__put_user(d1, target)) goto fault; break; - case 2: + } + case 2: { + u16 d2; + u16 __user *target = (u16 __user *)dst; + memcpy(&d2, buf, 2); if (__put_user(d2, target)) goto fault; break; - case 4: + } + case 4: { + u32 d4; + u32 __user *target = (u32 __user *)dst; + memcpy(&d4, buf, 4); if (__put_user(d4, target)) goto fault; break; - case 8: + } + case 8: { + u64 d8; + u64 __user *target = (u64 __user *)dst; + memcpy(&d8, buf, 8); if (__put_user(d8, target)) goto fault; break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -362,11 +368,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, char *src, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT; - char __user *s = (char __user *)src; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __get_user() independent of whether kernel or user @@ -388,26 +389,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *s = (u8 __user *)src; + if (__get_user(d1, s)) goto fault; memcpy(buf, &d1, 1); break; - case 2: + } + case 2: { + u16 d2; + u16 __user *s = (u16 __user *)src; + if (__get_user(d2, s)) goto fault; memcpy(buf, &d2, 2); break; - case 4: + } + case 4: { + u32 d4; + u32 __user *s = (u32 __user *)src; + if (__get_user(d4, s)) goto fault; memcpy(buf, &d4, 4); break; - case 8: + } + case 8: { + u64 d8; + u64 __user *s = (u64 __user *)src; if (__get_user(d8, s)) goto fault; memcpy(buf, &d8, 8); break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -776,22 +792,6 @@ static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt) do_early_exception(ctxt->regs, trapnr); } -static long *vc_insn_get_reg(struct es_em_ctxt *ctxt) -{ - long *reg_array; - int offset; - - reg_array = (long *)ctxt->regs; - offset = insn_get_modrm_reg_off(&ctxt->insn, ctxt->regs); - - if (offset < 0) - return NULL; - - offset /= sizeof(long); - - return reg_array + offset; -} - static long *vc_insn_get_rm(struct es_em_ctxt *ctxt) { long *reg_array; @@ -839,76 +839,6 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, return sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, exit_info_1, exit_info_2); } -static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb, - struct es_em_ctxt *ctxt) -{ - struct insn *insn = &ctxt->insn; - unsigned int bytes = 0; - enum es_result ret; - int sign_byte; - long *reg_data; - - switch (insn->opcode.bytes[1]) { - /* MMIO Read w/ zero-extension */ - case 0xb6: - bytes = 1; - fallthrough; - case 0xb7: - if (!bytes) - bytes = 2; - - ret = vc_do_mmio(ghcb, ctxt, bytes, true); - if (ret) - break; - - /* Zero extend based on operand size */ - reg_data = vc_insn_get_reg(ctxt); - if (!reg_data) - return ES_DECODE_FAILED; - - memset(reg_data, 0, insn->opnd_bytes); - - memcpy(reg_data, ghcb->shared_buffer, bytes); - break; - - /* MMIO Read w/ sign-extension */ - case 0xbe: - bytes = 1; - fallthrough; - case 0xbf: - if (!bytes) - bytes = 2; - - ret = vc_do_mmio(ghcb, ctxt, bytes, true); - if (ret) - break; - - /* Sign extend based on operand size */ - reg_data = vc_insn_get_reg(ctxt); - if (!reg_data) - return ES_DECODE_FAILED; - - if (bytes == 1) { - u8 *val = (u8 *)ghcb->shared_buffer; - - sign_byte = (*val & 0x80) ? 0xff : 0x00; - } else { - u16 *val = (u16 *)ghcb->shared_buffer; - - sign_byte = (*val & 0x8000) ? 0xff : 0x00; - } - memset(reg_data, sign_byte, insn->opnd_bytes); - - memcpy(reg_data, ghcb->shared_buffer, bytes); - break; - - default: - ret = ES_UNSUPPORTED; - } - - return ret; -} - /* * The MOVS instruction has two memory operands, which raises the * problem that it is not known whether the access to the source or the @@ -976,83 +906,79 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt, return ES_RETRY; } -static enum es_result vc_handle_mmio(struct ghcb *ghcb, - struct es_em_ctxt *ctxt) +static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct insn *insn = &ctxt->insn; unsigned int bytes = 0; + enum mmio_type mmio; enum es_result ret; + u8 sign_byte; long *reg_data; - switch (insn->opcode.bytes[0]) { - /* MMIO Write */ - case 0x88: - bytes = 1; - fallthrough; - case 0x89: - if (!bytes) - bytes = insn->opnd_bytes; + mmio = insn_decode_mmio(insn, &bytes); + if (mmio == MMIO_DECODE_FAILED) + return ES_DECODE_FAILED; - reg_data = vc_insn_get_reg(ctxt); + if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) { + reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs); if (!reg_data) return ES_DECODE_FAILED; + } + switch (mmio) { + case MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); - ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - - case 0xc6: - bytes = 1; - fallthrough; - case 0xc7: - if (!bytes) - bytes = insn->opnd_bytes; - + case MMIO_WRITE_IMM: memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes); - ret = vc_do_mmio(ghcb, ctxt, bytes, false); break; - - /* MMIO Read */ - case 0x8a: - bytes = 1; - fallthrough; - case 0x8b: - if (!bytes) - bytes = insn->opnd_bytes; - + case MMIO_READ: ret = vc_do_mmio(ghcb, ctxt, bytes, true); if (ret) break; - reg_data = vc_insn_get_reg(ctxt); - if (!reg_data) - return ES_DECODE_FAILED; - /* Zero-extend for 32-bit operation */ if (bytes == 4) *reg_data = 0; memcpy(reg_data, ghcb->shared_buffer, bytes); break; + case MMIO_READ_ZERO_EXTEND: + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; - /* MOVS instruction */ - case 0xa4: - bytes = 1; - fallthrough; - case 0xa5: - if (!bytes) - bytes = insn->opnd_bytes; + /* Zero extend based on operand size */ + memset(reg_data, 0, insn->opnd_bytes); + memcpy(reg_data, ghcb->shared_buffer, bytes); + break; + case MMIO_READ_SIGN_EXTEND: + ret = vc_do_mmio(ghcb, ctxt, bytes, true); + if (ret) + break; - ret = vc_handle_mmio_movs(ctxt, bytes); + if (bytes == 1) { + u8 *val = (u8 *)ghcb->shared_buffer; + + sign_byte = (*val & 0x80) ? 0xff : 0x00; + } else { + u16 *val = (u16 *)ghcb->shared_buffer; + + sign_byte = (*val & 0x8000) ? 0xff : 0x00; + } + + /* Sign extend based on operand size */ + memset(reg_data, sign_byte, insn->opnd_bytes); + memcpy(reg_data, ghcb->shared_buffer, bytes); break; - /* Two-Byte Opcodes */ - case 0x0f: - ret = vc_handle_mmio_twobyte_ops(ghcb, ctxt); + case MMIO_MOVS: + ret = vc_handle_mmio_movs(ctxt, bytes); break; default: ret = ES_UNSUPPORTED; + break; } return ret; @@ -1411,7 +1337,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication) show_regs(regs); /* Ask hypervisor to sev_es_terminate */ - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); /* If that fails and we get here - just panic */ panic("Returned from Terminate-Request to Hypervisor\n"); @@ -1459,7 +1385,7 @@ bool __init handle_vc_boot_ghcb(struct pt_regs *regs) /* Do initial setup or terminate the guest */ if (unlikely(boot_ghcb == NULL && !sev_es_setup_ghcb())) - sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + sev_es_terminate(GHCB_SEV_ES_GEN_REQ); vc_ghcb_invalidate(boot_ghcb); diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S index ee04941a6546..3355e27c69eb 100644 --- a/arch/x86/kernel/sev_verify_cbit.S +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -85,5 +85,5 @@ SYM_FUNC_START(sev_verify_cbit) #endif /* Return page-table pointer */ movq %rdi, %rax - ret + RET SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ac2909f0cab3..617012f4619f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -579,6 +579,17 @@ static struct sched_domain_topology_level x86_numa_in_package_topology[] = { { NULL, }, }; +static struct sched_domain_topology_level x86_hybrid_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static struct sched_domain_topology_level x86_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, @@ -1469,8 +1480,11 @@ void __init native_smp_cpus_done(unsigned int max_cpus) calculate_max_logical_packages(); + /* XXX for now assume numa-in-package and hybrid don't overlap */ if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); + if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) + set_sched_topology(x86_hybrid_topology); nmi_selftest(); impress_friends(); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 9c407a33a774..531fb4cbb63f 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -17,6 +17,8 @@ enum insn_type { */ static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; + static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) { const void *emulate = NULL; @@ -42,8 +44,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void break; case RET: - code = text_gen_insn(RET_INSN_OPCODE, insn, func); - size = RET_INSN_SIZE; + code = &retinsn; break; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2e076a459a0c..a698196377be 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason) EXPORT_SYMBOL_GPL(mark_tsc_unstable); +static void __init tsc_disable_clocksource_watchdog(void) +{ + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; +} + static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) @@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void) #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; + + /* + * Disable the clocksource watchdog when the system has: + * - TSC running at constant frequency + * - TSC which does not stop in C-States + * - the TSC_ADJUST register which allows to detect even minimal + * modifications + * - not more than two sockets. As the number of sockets cannot be + * evaluated at the early boot stage where this has to be + * invoked, check the number of online memory nodes as a + * fallback solution which is an reasonable estimate. + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + boot_cpu_has(X86_FEATURE_TSC_ADJUST) && + nr_online_nodes <= 2) + tsc_disable_clocksource_watchdog(); } /* @@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void) if (tsc_unstable) goto unreg; - if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; - if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; @@ -1527,7 +1547,7 @@ void __init tsc_init(void) } if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 50a4515fe0ad..9452dc9664b5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -30,6 +30,7 @@ struct tsc_adjust { }; static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +static struct timer_list tsc_sync_check_timer; /* * TSC's on different sockets may be reset asynchronously. @@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume) } } +/* + * Normally the tsc_sync will be checked every time system enters idle + * state, but there is still caveat that a system won't enter idle, + * either because it's too busy or configured purposely to not enter + * idle. + * + * So setup a periodic timer (every 10 minutes) to make sure the check + * is always on. + */ + +#define SYNC_CHECK_INTERVAL (HZ * 600) + +static void tsc_sync_check_timer_fn(struct timer_list *unused) +{ + int next_cpu; + + tsc_verify_tsc_adjust(false); + + /* Run the check for all onlined CPUs in turn */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + + tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL; + add_timer_on(&tsc_sync_check_timer, next_cpu); +} + +static int __init start_sync_check_timer(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable) + return 0; + + timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0); + tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL; + add_timer(&tsc_sync_check_timer); + + return 0; +} +late_initcall(start_sync_check_timer); + static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, unsigned int cpu, bool bootcpu) { diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 641f0fe1e5b4..1258a5872d12 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -132,9 +132,9 @@ SYM_FUNC_START_LOCAL(verify_cpu) .Lverify_cpu_no_longmode: popf # Restore caller passed flags movl $1,%eax - ret + RET .Lverify_cpu_sse_ok: popf # Restore caller passed flags xorl %eax, %eax - ret + RET SYM_FUNC_END(verify_cpu) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3d6dc12d198f..27f830345b6f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -137,7 +137,6 @@ SECTIONS ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT STATIC_CALL_TEXT - *(.fixup) *(.gnu.warning) #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8b395821cb8d..7d20c1d34a3c 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -145,18 +145,6 @@ struct x86_platform_ops x86_platform __ro_after_init = { EXPORT_SYMBOL_GPL(x86_platform); -#if defined(CONFIG_PCI_MSI) -struct x86_msi_ops x86_msi __ro_after_init = { - .restore_msi_irqs = default_restore_msi_irqs, -}; - -/* MSI arch specific hooks */ -void arch_restore_msi_irqs(struct pci_dev *dev) -{ - x86_msi.restore_msi_irqs(dev); -} -#endif - struct x86_apic_ops x86_apic_ops __ro_after_init = { .io_apic_read = native_io_apic_read, .restore = native_restore_boot_irq_mode, |