diff options
Diffstat (limited to 'arch/x86/kernel')
26 files changed, 630 insertions, 598 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/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/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..8a25b1c0d480 100644 --- a/arch/x86/kernel/cc_platform.c +++ b/arch/x86/kernel/cc_platform.c @@ -50,6 +50,14 @@ 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; } 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..2a0f83678911 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -79,7 +79,7 @@ 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); 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/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/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..dd3777ac0443 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; } 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_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/process.c b/arch/x86/kernel/process.c index 04143a653a8a..5d481038fe0b 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); 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/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 a9fc2ac7a8bd..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); @@ -797,22 +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; @@ -860,76 +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 @@ -997,83 +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; @@ -1432,7 +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"); @@ -1480,7 +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); |