diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1852953fea3837ee6bebfae943ed383af9ebf9cb..580f1b413c118fdaee637426a57c137656afaaf2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -401,7 +401,8 @@ struct kvm_mmu { u32 pkru_mask; u64 *pae_root; - u64 *lm_root; + u64 *pml4_root; + u64 *pml5_root; /* * check zero bits on shadow page table entries, these diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index a99be921a2ea5756ad016bed9495f9cdabe0ccfb..7780496ff3e3641f4b5ff7d66192fb90b75434ba 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -301,7 +301,7 @@ extern void apei_mce_report_mem_error(int corrected, /* These may be used by multiple smca_hwid_mcatypes */ enum smca_bank_types { SMCA_LS = 0, /* Load Store */ - SMCA_LS_V2, /* Load Store */ + SMCA_LS_V2, SMCA_IF, /* Instruction Fetch */ SMCA_L2_CACHE, /* L2 Cache */ SMCA_DE, /* Decoder Unit */ @@ -310,36 +310,32 @@ enum smca_bank_types { SMCA_FP, /* Floating Point */ SMCA_L3_CACHE, /* L3 Cache */ SMCA_CS, /* Coherent Slave */ - SMCA_CS_V2, /* Coherent Slave */ + SMCA_CS_V2, SMCA_PIE, /* Power, Interrupts, etc. */ SMCA_UMC, /* Unified Memory Controller */ + SMCA_UMC_V2, SMCA_PB, /* Parameter Block */ SMCA_PSP, /* Platform Security Processor */ - SMCA_PSP_V2, /* Platform Security Processor */ + SMCA_PSP_V2, SMCA_SMU, /* System Management Unit */ - SMCA_SMU_V2, /* System Management Unit */ + SMCA_SMU_V2, SMCA_MP5, /* Microprocessor 5 Unit */ + SMCA_MPDMA, /* MPDMA Unit */ SMCA_NBIO, /* Northbridge IO Unit */ SMCA_PCIE, /* PCI Express Unit */ + SMCA_PCIE_V2, + SMCA_XGMI_PCS, /* xGMI PCS Unit */ + SMCA_NBIF, /* NBIF Unit */ + SMCA_SHUB, /* System HUB Unit */ + SMCA_SATA, /* SATA Unit */ + SMCA_USB, /* USB Unit */ + SMCA_GMI_PCS, /* GMI PCS Unit */ + SMCA_XGMI_PHY, /* xGMI PHY Unit */ + SMCA_WAFL_PHY, /* WAFL PHY Unit */ + SMCA_GMI_PHY, /* GMI PHY Unit */ N_SMCA_BANK_TYPES }; -#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 */ - u8 count; /* Number of instances. */ -}; - -struct smca_bank { - struct smca_hwid *hwid; - u32 id; /* Value of MCA_IPID[InstanceId]. */ - u8 sysfs_id; /* Value used for sysfs name. */ -}; - -extern struct smca_bank smca_banks[MAX_NR_BANKS]; - extern const char *smca_get_long_name(enum smca_bank_types t); extern bool amd_mce_is_memory_error(struct mce *m); @@ -347,16 +343,13 @@ extern int mce_threshold_create_device(unsigned int cpu); extern int mce_threshold_remove_device(unsigned int cpu); void mce_amd_feature_init(struct cpuinfo_x86 *c); -int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr); - +enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank); #else static inline int mce_threshold_create_device(unsigned int cpu) { return 0; }; static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; }; static inline bool amd_mce_is_memory_error(struct mce *m) { return false; }; static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } -static inline int -umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; }; #endif static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3995770d723acbdad84abc338546d659e2d6bb39..28c17a336d19c8feb9f796ef5d488647451f4337 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -511,6 +511,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f8fad50502ad6d7d0a71f6c82b37af3d041afaf4..d73058fb83a07550e0bd90dc1a588d7b9c5fdfcd 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -200,6 +200,42 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_NP_ENABLE BIT(0) #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) + +/* AVIC */ +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) +#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFF) + +#define AVIC_DOORBELL_PHYSICAL_ID_MASK (0xFF) + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + +enum avic_ipi_failure_cause { + AVIC_IPI_FAILURE_INVALID_INT_TYPE, + AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, + AVIC_IPI_FAILURE_INVALID_TARGET, + AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, +}; + + +/* + * 0xff is broadcast, so the max index allowed for physical APIC ID + * table is 0xfe. APIC IDs above 0xff are reserved. + */ +#define AVIC_MAX_PHYSICAL_ID_COUNT 0xff + +#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + + struct vmcb_seg { u16 selector; u16 attrib; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 18f6b7c4bd79fad9b64dca2a69b27cd38be72176..832ce4251a2f7162e80d198cc495ba96e547f678 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -19,12 +19,17 @@ #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. */ static DEFINE_MUTEX(smn_mutex); @@ -36,6 +41,8 @@ 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) }, {} }; @@ -57,6 +64,9 @@ 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) }, {} }; @@ -72,6 +82,9 @@ 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) }, {} }; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 09f7c652346a9847fd0095dfb0ff7f7e3e3307d3..3269139719c0c71cb6bd460bfa3e40ce111648b4 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -71,33 +71,58 @@ 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 */ }; static struct smca_bank_name smca_names[] = { - [SMCA_LS] = { "load_store", "Load Store Unit" }, - [SMCA_LS_V2] = { "load_store", "Load Store Unit" }, - [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, - [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, - [SMCA_DE] = { "decode_unit", "Decode Unit" }, - [SMCA_RESERVED] = { "reserved", "Reserved" }, - [SMCA_EX] = { "execution_unit", "Execution Unit" }, - [SMCA_FP] = { "floating_point", "Floating Point Unit" }, - [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, - [SMCA_CS] = { "coherent_slave", "Coherent Slave" }, - [SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, - [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, - [SMCA_UMC] = { "umc", "Unified Memory Controller" }, - [SMCA_PB] = { "param_block", "Parameter Block" }, - [SMCA_PSP] = { "psp", "Platform Security Processor" }, - [SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, - [SMCA_SMU] = { "smu", "System Management Unit" }, - [SMCA_SMU_V2] = { "smu", "System Management Unit" }, - [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, - [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, - [SMCA_PCIE] = { "pcie", "PCI Express Unit" }, + [SMCA_LS ... SMCA_LS_V2] = { "load_store", "Load Store Unit" }, + [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, + [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, + [SMCA_DE] = { "decode_unit", "Decode Unit" }, + [SMCA_RESERVED] = { "reserved", "Reserved" }, + [SMCA_EX] = { "execution_unit", "Execution Unit" }, + [SMCA_FP] = { "floating_point", "Floating Point Unit" }, + [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, + [SMCA_CS ... SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, + [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, + + /* UMC v2 is separate because both of them can exist in a single system. */ + [SMCA_UMC] = { "umc", "Unified Memory Controller" }, + [SMCA_UMC_V2] = { "umc_v2", "Unified Memory Controller v2" }, + [SMCA_PB] = { "param_block", "Parameter Block" }, + [SMCA_PSP ... SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, + [SMCA_SMU ... SMCA_SMU_V2] = { "smu", "System Management Unit" }, + [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, + [SMCA_MPDMA] = { "mpdma", "MPDMA Unit" }, + [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, + [SMCA_PCIE ... SMCA_PCIE_V2] = { "pcie", "PCI Express Unit" }, + [SMCA_XGMI_PCS] = { "xgmi_pcs", "Ext Global Memory Interconnect PCS Unit" }, + [SMCA_NBIF] = { "nbif", "NBIF Unit" }, + [SMCA_SHUB] = { "shub", "System Hub Unit" }, + [SMCA_SATA] = { "sata", "SATA Unit" }, + [SMCA_USB] = { "usb", "USB Unit" }, + [SMCA_GMI_PCS] = { "gmi_pcs", "Global Memory Interconnect PCS Unit" }, + [SMCA_XGMI_PHY] = { "xgmi_phy", "Ext Global Memory Interconnect PHY Unit" }, + [SMCA_WAFL_PHY] = { "wafl_phy", "WAFL PHY Unit" }, + [SMCA_GMI_PHY] = { "gmi_phy", "Global Memory Interconnect PHY Unit" }, }; static const char *smca_get_name(enum smca_bank_types t) @@ -117,21 +142,22 @@ const char *smca_get_long_name(enum smca_bank_types t) } EXPORT_SYMBOL_GPL(smca_get_long_name); -static 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; return b->hwid->bank_type; } +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 */ @@ -155,6 +181,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = { /* Unified Memory Controller MCA type */ { SMCA_UMC, HWID_MCATYPE(0x96, 0x0) }, + { SMCA_UMC_V2, HWID_MCATYPE(0x96, 0x1) }, /* Parameter Block MCA type */ { SMCA_PB, HWID_MCATYPE(0x05, 0x0) }, @@ -170,16 +197,27 @@ 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) }, /* PCI Express Unit MCA type */ { SMCA_PCIE, HWID_MCATYPE(0x46, 0x0) }, + { SMCA_PCIE_V2, HWID_MCATYPE(0x46, 0x1) }, + + { SMCA_XGMI_PCS, HWID_MCATYPE(0x50, 0x0) }, + { 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) }, + { 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 @@ -235,8 +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); @@ -272,10 +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; @@ -286,10 +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; } } @@ -575,7 +611,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, 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. */ @@ -613,7 +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); @@ -675,213 +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; } @@ -1197,7 +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; @@ -1208,7 +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; @@ -1218,12 +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; } @@ -1279,7 +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: @@ -1334,7 +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/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6096d0f1a62af06b7c16d9fb73a1f5acfc3dec52..8a887a557b9347ed950393cc00157e9dde96aa09 100755 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3305,13 +3305,13 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) * the shadow page table may be a PAE or a long mode page table. */ pm_mask = PT_PRESENT_MASK; - if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) { + if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) { pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; /* * Allocate the page for the PDPTEs when shadowing 32-bit NPT * with 64-bit only when needed. Unlike 32-bit NPT, it doesn't - * need to be in low mem. See also lm_root below. + * need to be in low mem. See also pml4_root below. */ if (!vcpu->arch.mmu->pae_root) { WARN_ON_ONCE(!tdp_enabled); @@ -3351,20 +3351,47 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) * handled above (to share logic with PAE), deal with the PML4 here. */ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) { - if (vcpu->arch.mmu->lm_root == NULL) { - u64 *lm_root; + if (vcpu->arch.mmu->pml4_root == NULL) { + u64 *pml4_root; + + pml4_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml4_root) + return -ENOMEM; + + pml4_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask; + + vcpu->arch.mmu->pml4_root = pml4_root; + } + + vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pml4_root); + } +#ifdef CONFIG_X86_64 + if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_5LEVEL) { + if (vcpu->arch.mmu->pml4_root == NULL) { + u64 *pml4_root; - lm_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!lm_root) + pml4_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml4_root) return -ENOMEM; - lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask; + pml4_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask; - vcpu->arch.mmu->lm_root = lm_root; + vcpu->arch.mmu->pml4_root = pml4_root; } + if (vcpu->arch.mmu->pml5_root == NULL) { + u64 *pml5_root; + + pml5_root = (void*)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml5_root) + return -ENOMEM; + + pml5_root[0] = __pa(vcpu->arch.mmu->pml4_root) | pm_mask; - vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root); + vcpu->arch.mmu->pml5_root = pml5_root; + } + vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pml5_root); } +#endif set_root_pgd: vcpu->arch.mmu->root_pgd = root_pgd; @@ -5302,7 +5329,10 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, static void free_mmu_pages(struct kvm_mmu *mmu) { free_page((unsigned long)mmu->pae_root); - free_page((unsigned long)mmu->lm_root); + free_page((unsigned long)mmu->pml4_root); +#ifdef CONFIG_X86_64 + free_page((unsigned long)mmu->pml5_root); +#endif } static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 3e5cb74c0b5386f4b81a3e7845d1353d1e92dbbc..1401d168165b0a8309c60bd193a9a4c57c88812e 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -33,20 +33,6 @@ int avic; module_param(avic, int, S_IRUGO); #endif -#define SVM_AVIC_DOORBELL 0xc001011b - -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - /* AVIC GATAG is encoded using VM and VCPU IDs */ #define AVIC_VCPU_ID_BITS 8 #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) @@ -79,12 +65,6 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; /* Note: * This function is called from IOMMU driver to notify @@ -683,7 +663,7 @@ int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) int cpuid = vcpu->cpu; if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); + wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); put_cpu(); } else kvm_vcpu_wake_up(vcpu); @@ -958,18 +938,13 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; - /* ID = 0xff (broadcast), ID > 0xff (reserved) */ int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) return; - /* - * Since the host physical APIC id is 8 bits, - * we can support host APIC ID upto 255. - */ - if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) + if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e2677e38ea42799bbb7108175faf8231d5f6e1c1..f52668cef207a84f078a8011c66d7e418827c23e 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -257,7 +257,7 @@ static inline void invlpga(unsigned long addr, u32 asid) static int get_max_npt_level(void) { #ifdef CONFIG_X86_64 - return PT64_ROOT_4LEVEL; + return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; #else return PT32E_ROOT_LEVEL; #endif diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index c707d689b60ee264741e04ad2800a5c8225ab517..032ac5cf0201802d7c8fa5ba76783492e9ab790a 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -410,17 +410,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - extern int avic; static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) @@ -440,6 +429,17 @@ static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu) return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); } +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) + +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c index c319e7e3917dc3212de362c5e8471800bd76eb21..c13181431d9d0814e32528a7b3da94825328d219 100644 --- a/drivers/crypto/ccp/sp-pci.c +++ b/drivers/crypto/ccp/sp-pci.c @@ -360,6 +360,12 @@ static const struct sp_dev_vdata dev_vdata[] = { #endif #ifdef CONFIG_CRYPTO_DEV_SP_PSP .psp_vdata = &pspv3, +#endif + }, + { /* 5 */ + .bar = 2, +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + .psp_vdata = &pspv2, #endif }, }; @@ -369,6 +375,7 @@ static const struct pci_device_id sp_pci_table[] = { { PCI_VDEVICE(AMD, 0x1468), (kernel_ulong_t)&dev_vdata[2] }, { PCI_VDEVICE(AMD, 0x1486), (kernel_ulong_t)&dev_vdata[3] }, { PCI_VDEVICE(AMD, 0x15DF), (kernel_ulong_t)&dev_vdata[4] }, + { PCI_VDEVICE(AMD, 0x14CA), (kernel_ulong_t)&dev_vdata[5] }, /* Last entry must be zero */ { 0, } }; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index f5635dfa9acf6024b0d6f4ab2a8d39ec9744e240..7f018fc111c0d3694e8403255cb0720c2ef7adee 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -15,6 +15,21 @@ static struct msr __percpu *msrs; static struct amd64_family_type *fam_type; +static inline u32 get_umc_reg(u32 reg) +{ + if (!fam_type->flags.zn_regs_v2) + return reg; + + switch (reg) { + case UMCCH_ADDR_CFG: return UMCCH_ADDR_CFG_DDR5; + case UMCCH_ADDR_MASK_SEC: return UMCCH_ADDR_MASK_SEC_DDR5; + case UMCCH_DIMM_CFG: return UMCCH_DIMM_CFG_DDR5; + } + + WARN_ONCE(1, "%s: unknown register 0x%x", __func__, reg); + return 0; +} + /* Per-node stuff */ static struct ecc_settings **ecc_stngs; @@ -709,6 +724,205 @@ static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr) return csrow; } +static 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; +} + static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16); /* @@ -875,8 +1089,10 @@ static void __dump_misc_regs_df(struct amd64_pvt *pvt) edac_dbg(1, "UMC%d x16 DIMMs present: %s\n", i, (umc->dimm_cfg & BIT(7)) ? "yes" : "no"); - if (pvt->dram_type == MEM_LRDDR4) { - amd_smn_read(pvt->mc_node_id, umc_base + UMCCH_ADDR_CFG, &tmp); + if (umc->dram_type == MEM_LRDDR4 || umc->dram_type == MEM_LRDDR5) { + amd_smn_read(pvt->mc_node_id, + umc_base + get_umc_reg(UMCCH_ADDR_CFG), + &tmp); edac_dbg(1, "UMC%d LRDIMM %dx rank multiply\n", i, 1 << ((tmp >> 4) & 0x3)); } @@ -951,7 +1167,7 @@ static void prep_chip_selects(struct amd64_pvt *pvt) for_each_umc(umc) { pvt->csels[umc].b_cnt = 4; - pvt->csels[umc].m_cnt = 2; + pvt->csels[umc].m_cnt = fam_type->flags.zn_regs_v2 ? 4 : 2; } } else { @@ -991,7 +1207,7 @@ static void read_umc_base_mask(struct amd64_pvt *pvt) } umc_mask_reg = get_umc_base(umc) + UMCCH_ADDR_MASK; - umc_mask_reg_sec = get_umc_base(umc) + UMCCH_ADDR_MASK_SEC; + umc_mask_reg_sec = get_umc_base(umc) + get_umc_reg(UMCCH_ADDR_MASK_SEC); for_each_chip_select_mask(cs, umc, pvt) { mask = &pvt->csels[umc].csmasks[cs]; @@ -1062,19 +1278,49 @@ static void read_dct_base_mask(struct amd64_pvt *pvt) } } +static void determine_memory_type_df(struct amd64_pvt *pvt) +{ + struct amd64_umc *umc; + u32 i; + + for_each_umc(i) { + umc = &pvt->umc[i]; + + if (!(umc->sdp_ctrl & UMC_SDP_INIT)) { + umc->dram_type = MEM_EMPTY; + continue; + } + + /* + * Check if the system supports the "DDR Type" field in UMC Config + * and has DDR5 DIMMs in use. + */ + if (fam_type->flags.zn_regs_v2 && ((umc->umc_cfg & GENMASK(2, 0)) == 0x1)) { + if (umc->dimm_cfg & BIT(5)) + umc->dram_type = MEM_LRDDR5; + else if (umc->dimm_cfg & BIT(4)) + umc->dram_type = MEM_RDDR5; + else + umc->dram_type = MEM_DDR5; + } else { + if (umc->dimm_cfg & BIT(5)) + umc->dram_type = MEM_LRDDR4; + else if (umc->dimm_cfg & BIT(4)) + umc->dram_type = MEM_RDDR4; + else + umc->dram_type = MEM_DDR4; + } + + edac_dbg(1, " UMC%d DIMM type: %s\n", i, edac_mem_types[umc->dram_type]); + } +} + static void determine_memory_type(struct amd64_pvt *pvt) { u32 dram_ctrl, dcsm; - if (pvt->umc) { - if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(5)) - pvt->dram_type = MEM_LRDDR4; - else if ((pvt->umc[0].dimm_cfg | pvt->umc[1].dimm_cfg) & BIT(4)) - pvt->dram_type = MEM_RDDR4; - else - pvt->dram_type = MEM_DDR4; - return; - } + if (pvt->umc) + return determine_memory_type_df(pvt); switch (pvt->fam) { case 0xf: @@ -1595,6 +1841,7 @@ static int f17_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, { u32 addr_mask_orig, addr_mask_deinterleaved; u32 msb, weight, num_zero_bits; + int cs_mask_nr = csrow_nr; int dimm, size = 0; /* No Chip Selects are enabled. */ @@ -1610,17 +1857,33 @@ static int f17_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc, return size; /* - * There is one mask per DIMM, and two Chip Selects per DIMM. - * CS0 and CS1 -> DIMM0 - * CS2 and CS3 -> DIMM1 + * Family 17h introduced systems with one mask per DIMM, + * and two Chip Selects per DIMM. + * + * CS0 and CS1 -> MASK0 / DIMM0 + * CS2 and CS3 -> MASK1 / DIMM1 + * + * Family 19h Model 10h introduced systems with one mask per Chip Select, + * and two Chip Selects per DIMM. + * + * CS0 -> MASK0 -> DIMM0 + * CS1 -> MASK1 -> DIMM0 + * CS2 -> MASK2 -> DIMM1 + * CS3 -> MASK3 -> DIMM1 + * + * Keep the mask number equal to the Chip Select number for newer systems, + * and shift the mask number for older systems. */ dimm = csrow_nr >> 1; + if (!fam_type->flags.zn_regs_v2) + cs_mask_nr >>= 1; + /* Asymmetric dual-rank DIMM support. */ if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY)) - addr_mask_orig = pvt->csels[umc].csmasks_sec[dimm]; + addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr]; else - addr_mask_orig = pvt->csels[umc].csmasks[dimm]; + addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr]; /* * The number of zero bits in the mask is equal to the number of bits @@ -2371,6 +2634,17 @@ static struct amd64_family_type family_types[] = { .dbam_to_cs = f17_addr_mask_to_cs_size, } }, + [F19_M10H_CPUS] = { + .ctl_name = "F19h_M10h", + .f0_id = PCI_DEVICE_ID_AMD_19H_M10H_DF_F0, + .f6_id = PCI_DEVICE_ID_AMD_19H_M10H_DF_F6, + .max_mcs = 12, + .flags.zn_regs_v2 = 1, + .ops = { + .early_channel_count = f17_early_channel_count, + .dbam_to_cs = f17_addr_mask_to_cs_size, + } + }, }; /* @@ -2802,7 +3076,7 @@ static void __read_mc_regs_df(struct amd64_pvt *pvt) umc_base = get_umc_base(i); umc = &pvt->umc[i]; - amd_smn_read(nid, umc_base + UMCCH_DIMM_CFG, &umc->dimm_cfg); + amd_smn_read(nid, umc_base + get_umc_reg(UMCCH_DIMM_CFG), &umc->dimm_cfg); amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg); amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl); amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl); @@ -2886,7 +3160,9 @@ static void read_mc_regs(struct amd64_pvt *pvt) read_dct_base_mask(pvt); determine_memory_type(pvt); - edac_dbg(1, " DIMM type: %s\n", edac_mem_types[pvt->dram_type]); + + if (!pvt->umc) + edac_dbg(1, " DIMM type: %s\n", edac_mem_types[pvt->dram_type]); determine_ecc_sym_sz(pvt); } @@ -2982,7 +3258,7 @@ static int init_csrows_df(struct mem_ctl_info *mci) pvt->mc_node_id, cs); dimm->nr_pages = get_csrow_nr_pages(pvt, umc, cs); - dimm->mtype = pvt->dram_type; + dimm->mtype = pvt->umc[umc].dram_type; dimm->edac_mode = edac_mode; dimm->dtype = dev_type; dimm->grain = 64; @@ -3417,11 +3693,20 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) break; case 0x19: - if (pvt->model >= 0x20 && pvt->model <= 0x2f) { + if (pvt->model >= 0x10 && pvt->model <= 0x1f) { + fam_type = &family_types[F19_M10H_CPUS]; + pvt->ops = &family_types[F19_M10H_CPUS].ops; + break; + } else if (pvt->model >= 0x20 && pvt->model <= 0x2f) { fam_type = &family_types[F17_M70H_CPUS]; pvt->ops = &family_types[F17_M70H_CPUS].ops; fam_type->ctl_name = "F19h_M20h"; break; + } else if (pvt->model >= 0xa0 && pvt->model <= 0xaf) { + fam_type = &family_types[F19_M10H_CPUS]; + pvt->ops = &family_types[F19_M10H_CPUS].ops; + fam_type->ctl_name = "F19h_MA0h"; + break; } fam_type = &family_types[F19_CPUS]; pvt->ops = &family_types[F19_CPUS].ops; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index 52b5d03eeba007559943eb50558ad5cfce036570..5a273d589e3042806f26d522ceaead52ef74785b 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -96,7 +96,7 @@ /* Hardware limit on ChipSelect rows per MC and processors per system */ #define NUM_CHIPSELECTS 8 #define DRAM_RANGES 8 -#define NUM_CONTROLLERS 8 +#define NUM_CONTROLLERS 12 #define ON true #define OFF false @@ -126,6 +126,8 @@ #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F6 0x1446 #define PCI_DEVICE_ID_AMD_19H_DF_F0 0x1650 #define PCI_DEVICE_ID_AMD_19H_DF_F6 0x1656 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F0 0x14ad +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F6 0x14b3 /* * Function 1 - Address Map @@ -269,8 +271,11 @@ #define UMCCH_BASE_ADDR_SEC 0x10 #define UMCCH_ADDR_MASK 0x20 #define UMCCH_ADDR_MASK_SEC 0x28 +#define UMCCH_ADDR_MASK_SEC_DDR5 0x30 #define UMCCH_ADDR_CFG 0x30 +#define UMCCH_ADDR_CFG_DDR5 0x40 #define UMCCH_DIMM_CFG 0x80 +#define UMCCH_DIMM_CFG_DDR5 0x90 #define UMCCH_UMC_CFG 0x100 #define UMCCH_SDP_CTRL 0x104 #define UMCCH_ECC_CTRL 0x14C @@ -298,6 +303,7 @@ enum amd_families { F17_M60H_CPUS, F17_M70H_CPUS, F19_CPUS, + F19_M10H_CPUS, NUM_FAMILIES, }; @@ -338,6 +344,9 @@ struct amd64_umc { u32 sdp_ctrl; /* SDP Control reg */ u32 ecc_ctrl; /* DRAM ECC Control reg */ u32 umc_cap_hi; /* Capabilities High reg */ + + /* cache the dram_type */ + enum mem_type dram_type; }; struct amd64_pvt { @@ -385,7 +394,12 @@ struct amd64_pvt { /* place to store error injection parameters prior to issue */ struct error_injection injection; - /* cache the dram_type */ + /* + * cache the dram_type + * + * NOTE: Don't use this for Family 17h and later. + * Use dram_type in struct amd64_umc instead. + */ enum mem_type dram_type; struct amd64_umc *umc; /* UMC registers */ @@ -482,11 +496,22 @@ struct low_ops { unsigned cs_mode, int cs_mask_nr); }; +struct amd64_family_flags { + /* + * Indicates that the system supports the new register offsets, etc. + * first introduced with Family 19h Model 10h. + */ + __u64 zn_regs_v2 : 1, + + __reserved : 63; +}; + struct amd64_family_type { const char *ctl_name; u16 f0_id, f1_id, f2_id, f6_id; /* Maximum number of memory controllers per die/node. */ u8 max_mcs; + struct amd64_family_flags flags; struct low_ops ops; }; diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index bf4297075c229a5fbb572f4e64befc2c02da253f..3c3bef0162c8124eb182c09983f837fe707268e6 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -162,6 +162,8 @@ const char * const edac_mem_types[] = { [MEM_RDDR4] = "Registered-DDR4", [MEM_LRDDR4] = "Load-Reduced-DDR4-RAM", [MEM_DDR5] = "Unbuffered-DDR5", + [MEM_RDDR5] = "Registered-DDR5", + [MEM_LRDDR5] = "Load-Reduced-DDR5-RAM", [MEM_NVDIMM] = "Non-volatile-RAM", [MEM_HBM2] = "High-bandwidth-memory-Gen2", }; diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c index b6d4ae84a9a5bf4483ef1b6984bc74e91c075bb1..414dcab737156366be47af09ce4a66b8fc284b33 100644 --- a/drivers/edac/mce_amd.c +++ b/drivers/edac/mce_amd.c @@ -323,6 +323,21 @@ static const char * const smca_umc_mce_desc[] = { "AES SRAM ECC error", }; +static const char * const smca_umc2_mce_desc[] = { + "DRAM ECC error", + "Data poison error", + "SDP parity error", + "Reserved", + "Address/Command parity error", + "Write data parity error", + "DCQ SRAM ECC error", + "Reserved", + "Read data parity error", + "Rdb SRAM ECC error", + "RdRsp SRAM ECC error", + "LM32 MP errors", +}; + static const char * const smca_pb_mce_desc[] = { "An ECC error in the Parameter Block RAM array", }; @@ -384,6 +399,63 @@ static const char * const smca_mp5_mce_desc[] = { "Instruction Tag Cache Bank B ECC or parity error", }; +static const char * const smca_mpdma_mce_desc[] = { + "Main SRAM [31:0] bank ECC or parity error", + "Main SRAM [63:32] bank ECC or parity error", + "Main SRAM [95:64] bank ECC or parity error", + "Main SRAM [127:96] bank ECC or parity error", + "Data Cache Bank A ECC or parity error", + "Data Cache Bank B ECC or parity error", + "Data Tag Cache Bank A ECC or parity error", + "Data Tag Cache Bank B ECC or parity error", + "Instruction Cache Bank A ECC or parity error", + "Instruction Cache Bank B ECC or parity error", + "Instruction Tag Cache Bank A ECC or parity error", + "Instruction Tag Cache Bank B ECC or parity error", + "Data Cache Bank A ECC or parity error", + "Data Cache Bank B ECC or parity error", + "Data Tag Cache Bank A ECC or parity error", + "Data Tag Cache Bank B ECC or parity error", + "Instruction Cache Bank A ECC or parity error", + "Instruction Cache Bank B ECC or parity error", + "Instruction Tag Cache Bank A ECC or parity error", + "Instruction Tag Cache Bank B ECC or parity error", + "Data Cache Bank A ECC or parity error", + "Data Cache Bank B ECC or parity error", + "Data Tag Cache Bank A ECC or parity error", + "Data Tag Cache Bank B ECC or parity error", + "Instruction Cache Bank A ECC or parity error", + "Instruction Cache Bank B ECC or parity error", + "Instruction Tag Cache Bank A ECC or parity error", + "Instruction Tag Cache Bank B ECC or parity error", + "System Hub Read Buffer ECC or parity error", + "MPDMA TVF DVSEC Memory ECC or parity error", + "MPDMA TVF MMIO Mailbox0 ECC or parity error", + "MPDMA TVF MMIO Mailbox1 ECC or parity error", + "MPDMA TVF Doorbell Memory ECC or parity error", + "MPDMA TVF SDP Slave Memory 0 ECC or parity error", + "MPDMA TVF SDP Slave Memory 1 ECC or parity error", + "MPDMA TVF SDP Slave Memory 2 ECC or parity error", + "MPDMA TVF SDP Master Memory 0 ECC or parity error", + "MPDMA TVF SDP Master Memory 1 ECC or parity error", + "MPDMA TVF SDP Master Memory 2 ECC or parity error", + "MPDMA TVF SDP Master Memory 3 ECC or parity error", + "MPDMA TVF SDP Master Memory 4 ECC or parity error", + "MPDMA TVF SDP Master Memory 5 ECC or parity error", + "MPDMA TVF SDP Master Memory 6 ECC or parity error", + "MPDMA PTE Command FIFO ECC or parity error", + "MPDMA PTE Hub Data FIFO ECC or parity error", + "MPDMA PTE Internal Data FIFO ECC or parity error", + "MPDMA PTE Command Memory DMA ECC or parity error", + "MPDMA PTE Command Memory Internal ECC or parity error", + "MPDMA PTE DMA Completion FIFO ECC or parity error", + "MPDMA PTE Tablewalk Completion FIFO ECC or parity error", + "MPDMA PTE Descriptor Completion FIFO ECC or parity error", + "MPDMA PTE ReadOnly Completion FIFO ECC or parity error", + "MPDMA PTE DirectWrite Completion FIFO ECC or parity error", + "SDP Watchdog Timer expired", +}; + static const char * const smca_nbio_mce_desc[] = { "ECC or Parity error", "PCIE error", @@ -400,6 +472,111 @@ static const char * const smca_pcie_mce_desc[] = { "CCIX Non-okay write response with data error", }; +static const char * const smca_pcie2_mce_desc[] = { + "SDP Parity Error logging", +}; + +static const char * const smca_xgmipcs_mce_desc[] = { + "Data Loss Error", + "Training Error", + "Flow Control Acknowledge Error", + "Rx Fifo Underflow Error", + "Rx Fifo Overflow Error", + "CRC Error", + "BER Exceeded Error", + "Tx Vcid Data Error", + "Replay Buffer Parity Error", + "Data Parity Error", + "Replay Fifo Overflow Error", + "Replay FIfo Underflow Error", + "Elastic Fifo Overflow Error", + "Deskew Error", + "Flow Control CRC Error", + "Data Startup Limit Error", + "FC Init Timeout Error", + "Recovery Timeout Error", + "Ready Serial Timeout Error", + "Ready Serial Attempt Error", + "Recovery Attempt Error", + "Recovery Relock Attempt Error", + "Replay Attempt Error", + "Sync Header Error", + "Tx Replay Timeout Error", + "Rx Replay Timeout Error", + "LinkSub Tx Timeout Error", + "LinkSub Rx Timeout Error", + "Rx CMD Packet Error", +}; + +static const char * const smca_xgmiphy_mce_desc[] = { + "RAM ECC Error", + "ARC instruction buffer parity error", + "ARC data buffer parity error", + "PHY APB error", +}; + +static const char * const smca_nbif_mce_desc[] = { + "Timeout error from GMI", + "SRAM ECC error", + "NTB Error Event", + "SDP Parity error", +}; + +static const char * const smca_sata_mce_desc[] = { + "Parity error for port 0", + "Parity error for port 1", + "Parity error for port 2", + "Parity error for port 3", + "Parity error for port 4", + "Parity error for port 5", + "Parity error for port 6", + "Parity error for port 7", +}; + +static const char * const smca_usb_mce_desc[] = { + "Parity error or ECC error for S0 RAM0", + "Parity error or ECC error for S0 RAM1", + "Parity error or ECC error for S0 RAM2", + "Parity error for PHY RAM0", + "Parity error for PHY RAM1", + "AXI Slave Response error", +}; + +static const char * const smca_gmipcs_mce_desc[] = { + "Data Loss Error", + "Training Error", + "Replay Parity Error", + "Rx Fifo Underflow Error", + "Rx Fifo Overflow Error", + "CRC Error", + "BER Exceeded Error", + "Tx Fifo Underflow Error", + "Replay Buffer Parity Error", + "Tx Overflow Error", + "Replay Fifo Overflow Error", + "Replay Fifo Underflow Error", + "Elastic Fifo Overflow Error", + "Deskew Error", + "Offline Error", + "Data Startup Limit Error", + "FC Init Timeout Error", + "Recovery Timeout Error", + "Ready Serial Timeout Error", + "Ready Serial Attempt Error", + "Recovery Attempt Error", + "Recovery Relock Attempt Error", + "Deskew Abort Error", + "Rx Buffer Error", + "Rx LFDS Fifo Overflow Error", + "Rx LFDS Fifo Underflow Error", + "LinkSub Tx Timeout Error", + "LinkSub Rx Timeout Error", + "Rx CMD Packet Error", + "LFDS Training Timeout Error", + "LFDS FC Init Timeout Error", + "Data Loss Error", +}; + struct smca_mce_desc { const char * const *descs; unsigned int num_descs; @@ -418,14 +595,28 @@ static struct smca_mce_desc smca_mce_descs[] = { [SMCA_CS_V2] = { smca_cs2_mce_desc, ARRAY_SIZE(smca_cs2_mce_desc) }, [SMCA_PIE] = { smca_pie_mce_desc, ARRAY_SIZE(smca_pie_mce_desc) }, [SMCA_UMC] = { smca_umc_mce_desc, ARRAY_SIZE(smca_umc_mce_desc) }, + [SMCA_UMC_V2] = { smca_umc2_mce_desc, ARRAY_SIZE(smca_umc2_mce_desc) }, [SMCA_PB] = { smca_pb_mce_desc, ARRAY_SIZE(smca_pb_mce_desc) }, [SMCA_PSP] = { smca_psp_mce_desc, ARRAY_SIZE(smca_psp_mce_desc) }, [SMCA_PSP_V2] = { smca_psp2_mce_desc, ARRAY_SIZE(smca_psp2_mce_desc) }, [SMCA_SMU] = { smca_smu_mce_desc, ARRAY_SIZE(smca_smu_mce_desc) }, [SMCA_SMU_V2] = { smca_smu2_mce_desc, ARRAY_SIZE(smca_smu2_mce_desc) }, [SMCA_MP5] = { smca_mp5_mce_desc, ARRAY_SIZE(smca_mp5_mce_desc) }, + [SMCA_MPDMA] = { smca_mpdma_mce_desc, ARRAY_SIZE(smca_mpdma_mce_desc) }, [SMCA_NBIO] = { smca_nbio_mce_desc, ARRAY_SIZE(smca_nbio_mce_desc) }, [SMCA_PCIE] = { smca_pcie_mce_desc, ARRAY_SIZE(smca_pcie_mce_desc) }, + [SMCA_PCIE_V2] = { smca_pcie2_mce_desc, ARRAY_SIZE(smca_pcie2_mce_desc) }, + [SMCA_XGMI_PCS] = { smca_xgmipcs_mce_desc, ARRAY_SIZE(smca_xgmipcs_mce_desc) }, + /* NBIF and SHUB have the same error descriptions, for now. */ + [SMCA_NBIF] = { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc) }, + [SMCA_SHUB] = { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc) }, + [SMCA_SATA] = { smca_sata_mce_desc, ARRAY_SIZE(smca_sata_mce_desc) }, + [SMCA_USB] = { smca_usb_mce_desc, ARRAY_SIZE(smca_usb_mce_desc) }, + [SMCA_GMI_PCS] = { smca_gmipcs_mce_desc, ARRAY_SIZE(smca_gmipcs_mce_desc) }, + /* All the PHY bank types have the same error descriptions, for now. */ + [SMCA_XGMI_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) }, + [SMCA_WAFL_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) }, + [SMCA_GMI_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) }, }; static bool f12h_mc0_mce(u16 ec, u8 xec) @@ -975,20 +1166,13 @@ static void decode_mc6_mce(struct mce *m) /* Decode errors according to Scalable MCA specification */ static void decode_smca_error(struct mce *m) { - struct smca_hwid *hwid; - enum smca_bank_types bank_type; + enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank); const char *ip_name; u8 xec = XEC(m->status, xec_mask); - if (m->bank >= ARRAY_SIZE(smca_banks)) + if (bank_type >= N_SMCA_BANK_TYPES) return; - hwid = smca_banks[m->bank].hwid; - if (!hwid) - return; - - bank_type = hwid->bank_type; - if (bank_type == SMCA_RESERVED) { pr_emerg(HW_ERR "Bank %d is reserved.\n", m->bank); return; diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 3bc2551577a30f5b432b8d63f66cb607f288f2dc..4e239bd75b1dae2cf8f3108b0cdefbba78d4afad 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -65,36 +65,17 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); #define F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET 0xd8200c64 #define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET 0xd8200ca4 -/* Common for Zen CPU families (Family 17h and 18h) */ -#define ZEN_REPORTED_TEMP_CTRL_OFFSET 0x00059800 +/* Common for Zen CPU families (Family 17h and 18h and 19h) */ +#define ZEN_REPORTED_TEMP_CTRL_BASE 0x00059800 -#define ZEN_CCD_TEMP(x) (0x00059954 + ((x) * 4)) +#define ZEN_CCD_TEMP(offset, x) (ZEN_REPORTED_TEMP_CTRL_BASE + \ + (offset) + ((x) * 4)) #define ZEN_CCD_TEMP_VALID BIT(11) #define ZEN_CCD_TEMP_MASK GENMASK(10, 0) #define ZEN_CUR_TEMP_SHIFT 21 #define ZEN_CUR_TEMP_RANGE_SEL_MASK BIT(19) -#define ZEN_SVI_BASE 0x0005A000 - -/* F17h thermal registers through SMN */ -#define F17H_M01H_SVI_TEL_PLANE0 (ZEN_SVI_BASE + 0xc) -#define F17H_M01H_SVI_TEL_PLANE1 (ZEN_SVI_BASE + 0x10) -#define F17H_M31H_SVI_TEL_PLANE0 (ZEN_SVI_BASE + 0x14) -#define F17H_M31H_SVI_TEL_PLANE1 (ZEN_SVI_BASE + 0x10) - -#define F17H_M01H_CFACTOR_ICORE 1000000 /* 1A / LSB */ -#define F17H_M01H_CFACTOR_ISOC 250000 /* 0.25A / LSB */ -#define F17H_M31H_CFACTOR_ICORE 1000000 /* 1A / LSB */ -#define F17H_M31H_CFACTOR_ISOC 310000 /* 0.31A / LSB */ - -/* F19h thermal registers through SMN */ -#define F19H_M01_SVI_TEL_PLANE0 (ZEN_SVI_BASE + 0x14) -#define F19H_M01_SVI_TEL_PLANE1 (ZEN_SVI_BASE + 0x10) - -#define F19H_M01H_CFACTOR_ICORE 1000000 /* 1A / LSB */ -#define F19H_M01H_CFACTOR_ISOC 310000 /* 0.31A / LSB */ - struct k10temp_data { struct pci_dev *pdev; void (*read_htcreg)(struct pci_dev *pdev, u32 *regval); @@ -103,6 +84,7 @@ struct k10temp_data { u32 temp_adjust_mask; u32 show_temp; bool is_zen; + u32 ccd_offset; }; #define TCTL_BIT 0 @@ -163,7 +145,7 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) static void read_tempreg_nb_zen(struct pci_dev *pdev, u32 *regval) { amd_smn_read(amd_pci_dev_to_node_id(pdev), - ZEN_REPORTED_TEMP_CTRL_OFFSET, regval); + ZEN_REPORTED_TEMP_CTRL_BASE, regval); } static long get_raw_temp(struct k10temp_data *data) @@ -189,6 +171,10 @@ static const char *k10temp_temp_label[] = { "Tccd6", "Tccd7", "Tccd8", + "Tccd9", + "Tccd10", + "Tccd11", + "Tccd12", }; static int k10temp_read_labels(struct device *dev, @@ -224,9 +210,10 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel, if (*val < 0) *val = 0; break; - case 2 ... 9: /* Tccd{1-8} */ + case 2 ... 13: /* Tccd{1-12} */ amd_smn_read(amd_pci_dev_to_node_id(data->pdev), - ZEN_CCD_TEMP(channel - 2), ®val); + ZEN_CCD_TEMP(data->ccd_offset, channel - 2), + ®val); *val = (regval & ZEN_CCD_TEMP_MASK) * 125 - 49000; break; default: @@ -358,13 +345,11 @@ static const struct hwmon_channel_info *k10temp_info[] = { HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL), - HWMON_CHANNEL_INFO(in, - HWMON_I_INPUT | HWMON_I_LABEL, - HWMON_I_INPUT | HWMON_I_LABEL), - HWMON_CHANNEL_INFO(curr, - HWMON_C_INPUT | HWMON_C_LABEL, - HWMON_C_INPUT | HWMON_C_LABEL), NULL }; @@ -387,7 +372,7 @@ static void k10temp_get_ccd_support(struct pci_dev *pdev, for (i = 0; i < limit; i++) { amd_smn_read(amd_pci_dev_to_node_id(pdev), - ZEN_CCD_TEMP(i), ®val); + ZEN_CCD_TEMP(data->ccd_offset, i), ®val); if (regval & ZEN_CCD_TEMP_VALID) data->show_temp |= BIT(TCCD_BIT(i)); } @@ -426,7 +411,6 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id) } else if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) { data->temp_adjust_mask = ZEN_CUR_TEMP_RANGE_SEL_MASK; data->read_tempreg = read_tempreg_nb_zen; - data->show_temp |= BIT(TDIE_BIT); /* show Tdie */ data->is_zen = true; switch (boot_cpu_data.x86_model) { @@ -434,23 +418,38 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id) case 0x8: /* Zen+ */ case 0x11: /* Zen APU */ case 0x18: /* Zen+ APU */ + data->ccd_offset = 0x154; k10temp_get_ccd_support(pdev, data, 4); break; case 0x31: /* Zen2 Threadripper */ + case 0x60: /* Renoir */ + case 0x68: /* Lucienne */ case 0x71: /* Zen2 */ + data->ccd_offset = 0x154; k10temp_get_ccd_support(pdev, data, 8); break; } } else if (boot_cpu_data.x86 == 0x19) { data->temp_adjust_mask = ZEN_CUR_TEMP_RANGE_SEL_MASK; data->read_tempreg = read_tempreg_nb_zen; - data->show_temp |= BIT(TDIE_BIT); data->is_zen = true; switch (boot_cpu_data.x86_model) { - case 0x0 ... 0x1: /* Zen3 */ + case 0x0 ... 0x1: /* Zen3 SP3/TR */ + case 0x21: /* Zen3 Ryzen Desktop */ + case 0x50 ... 0x5f: /* Green Sardine */ + data->ccd_offset = 0x154; k10temp_get_ccd_support(pdev, data, 8); break; + case 0x40 ... 0x4f: /* Yellow Carp */ + data->ccd_offset = 0x300; + k10temp_get_ccd_support(pdev, data, 8); + break; + case 0x10 ... 0x1f: + case 0xa0 ... 0xaf: + data->ccd_offset = 0x300; + k10temp_get_ccd_support(pdev, data, 12); + break; } } else { data->read_htcreg = read_htcreg_pci; @@ -462,6 +461,7 @@ static int k10temp_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (boot_cpu_data.x86 == entry->model && strstr(boot_cpu_data.x86_model_id, entry->id)) { + data->show_temp |= BIT(TDIE_BIT); /* show Tdie */ data->temp_offset = entry->offset; break; } @@ -490,6 +490,9 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, {} }; diff --git a/include/linux/edac.h b/include/linux/edac.h index 4901344950080ce5e034fbaf942068e63433851c..129d1abcc45ca235724fad925d93dfd41de8dcdf 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -180,6 +180,8 @@ static inline char *mc_event_error_type(const unsigned int err_type) * This is a variant of the DDR4 memories. * @MEM_LRDDR4: Load-Reduced DDR4 memory. * @MEM_DDR5: Unbuffered DDR5 RAM + * @MEM_RDDR5: Registered DDR5 RAM + * @MEM_LRDDR5: Load-Reduced DDR5 memory. * @MEM_NVDIMM: Non-volatile RAM * @MEM_HBM2: High bandwidth Memory Gen 2. */ @@ -206,6 +208,8 @@ enum mem_type { MEM_RDDR4, MEM_LRDDR4, MEM_DDR5, + MEM_RDDR5, + MEM_LRDDR5, MEM_NVDIMM, MEM_HBM2, }; @@ -231,6 +235,8 @@ enum mem_type { #define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) #define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) #define MEM_FLAG_DDR5 BIT(MEM_DDR5) +#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) +#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) #define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_HBM2 BIT(MEM_HBM2) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f9792f9128fb506eccc9634b8781adbba7f98eee..298b8ceda9cb35285939a52a4ccf71db7c6504fc 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -554,6 +554,9 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F3 0x14b0 +#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F3 0x167c +#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001