diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck')
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce-severity.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce.c | 202 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_amd.c | 357 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/mce_intel.c | 41 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/therm_throt.c | 57 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/threshold.c | 1 |
6 files changed, 467 insertions, 193 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 631356c8cca4..c7efbcfbeda6 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -311,7 +311,7 @@ static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_e *msg = s->msg; s->covered = 1; if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) { - if (panic_on_oops || tolerant < 1) + if (tolerant < 1) return MCE_PANIC_SEVERITY; } return s->sev; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a7fdf453d895..00ef43233e03 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -43,6 +43,7 @@ #include <linux/export.h> #include <linux/jump_label.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/traps.h> #include <asm/tlbflush.h> @@ -135,6 +136,9 @@ void mce_setup(struct mce *m) m->socketid = cpu_data(m->extcpu).phys_proc_id; m->apicid = cpu_data(m->extcpu).initial_apicid; rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); + + if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) + rdmsrl(MSR_PPIN, m->ppin); } DEFINE_PER_CPU(struct mce, injectm); @@ -207,8 +211,12 @@ EXPORT_SYMBOL_GPL(mce_inject_log); static struct notifier_block mce_srao_nb; +static atomic_t num_notifiers; + void mce_register_decode_chain(struct notifier_block *nb) { + atomic_inc(&num_notifiers); + /* Ensure SRAO notifier has the highest priority in the decode chain. */ if (nb != &mce_srao_nb && nb->priority == INT_MAX) nb->priority -= 1; @@ -219,6 +227,8 @@ EXPORT_SYMBOL_GPL(mce_register_decode_chain); void mce_unregister_decode_chain(struct notifier_block *nb) { + atomic_dec(&num_notifiers); + atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -270,17 +280,17 @@ struct mca_msr_regs msr_ops = { .misc = misc_reg }; -static void print_mce(struct mce *m) +static void __print_mce(struct mce *m) { - int ret = 0; - - pr_emerg(HW_ERR "CPU %d: Machine Check Exception: %Lx Bank %d: %016Lx\n", - m->extcpu, m->mcgstatus, m->bank, m->status); + pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", + m->extcpu, + (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""), + m->mcgstatus, m->bank, m->status); if (m->ip) { pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ", !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", - m->cs, m->ip); + m->cs, m->ip); if (m->cs == __KERNEL_CS) print_symbol("{%s}", m->ip); @@ -308,6 +318,13 @@ static void print_mce(struct mce *m) pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, cpu_data(m->extcpu).microcode); +} + +static void print_mce(struct mce *m) +{ + int ret = 0; + + __print_mce(m); /* * Print out human-readable details about the MCE error, @@ -499,7 +516,7 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { - if (!mce_gen_pool_empty() && keventd_up()) + if (!mce_gen_pool_empty()) schedule_work(&mce_work); } @@ -569,6 +586,32 @@ static struct notifier_block mce_srao_nb = { .priority = INT_MAX, }; +static int mce_default_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + /* + * Run the default notifier if we have only the SRAO + * notifier and us registered. + */ + if (atomic_read(&num_notifiers) > 2) + return NOTIFY_DONE; + + __print_mce(m); + + return NOTIFY_DONE; +} + +static struct notifier_block mce_default_nb = { + .notifier_call = mce_default_notifier, + /* lowest prio, we want it to run last. */ + .priority = 0, +}; + /* * Read ADDR and MISC registers. */ @@ -667,6 +710,15 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); + /* + * m.tsc was set in mce_setup(). Clear it if not requested. + * + * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid + * that dance. + */ + if (!(flags & MCP_TIMESTAMP)) + m.tsc = 0; + for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) continue; @@ -674,14 +726,12 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.misc = 0; m.addr = 0; m.bank = i; - m.tsc = 0; barrier(); m.status = mce_rdmsrl(msr_ops.status(i)); if (!(m.status & MCI_STATUS_VAL)) continue; - /* * Uncorrected or signalled events are handled by the exception * handler when it is enabled, so don't process those here. @@ -696,9 +746,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_read_aux(&m, i); - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; - severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) @@ -1355,7 +1402,7 @@ static void mce_timer_fn(unsigned long data) iv = __this_cpu_read(mce_next_interval); if (mce_available(this_cpu_ptr(&cpu_info))) { - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks)); + machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); if (mce_intel_cmci_poll()) { iv = mce_adjust_timer(iv); @@ -1745,6 +1792,14 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) add_timer_on(t, cpu); } +static void __mcheck_cpu_setup_timer(void) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + unsigned int cpu = smp_processor_id(); + + setup_pinned_timer(t, mce_timer_fn, cpu); +} + static void __mcheck_cpu_init_timer(void) { struct timer_list *t = this_cpu_ptr(&mce_timer); @@ -1796,7 +1851,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_clear_banks(); - __mcheck_cpu_init_timer(); + __mcheck_cpu_setup_timer(); } /* @@ -2138,6 +2193,7 @@ int __init mcheck_init(void) { mcheck_intel_therm_init(); mce_register_decode_chain(&mce_srao_nb); + mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); INIT_WORK(&mce_work, mce_process_work); @@ -2255,8 +2311,6 @@ static struct bus_type mce_subsys = { DEFINE_PER_CPU(struct device *, mce_device); -void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); - static inline struct mce_bank *attr_to_bank(struct device_attribute *attr) { return container_of(attr, struct mce_bank, attr); @@ -2409,6 +2463,10 @@ static int mce_device_create(unsigned int cpu) if (!mce_available(&boot_cpu_data)) return -EIO; + dev = per_cpu(mce_device, cpu); + if (dev) + return 0; + dev = kzalloc(sizeof *dev, GFP_KERNEL); if (!dev) return -ENOMEM; @@ -2468,28 +2526,25 @@ static void mce_device_remove(unsigned int cpu) } /* Make sure there are no machine checks on offlined CPUs. */ -static void mce_disable_cpu(void *h) +static void mce_disable_cpu(void) { - unsigned long action = *(unsigned long *)h; - if (!mce_available(raw_cpu_ptr(&cpu_info))) return; - if (!(action & CPU_TASKS_FROZEN)) + if (!cpuhp_tasks_frozen) cmci_clear(); vendor_disable_error_reporting(); } -static void mce_reenable_cpu(void *h) +static void mce_reenable_cpu(void) { - unsigned long action = *(unsigned long *)h; int i; if (!mce_available(raw_cpu_ptr(&cpu_info))) return; - if (!(action & CPU_TASKS_FROZEN)) + if (!cpuhp_tasks_frozen) cmci_reenable(); for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; @@ -2499,45 +2554,43 @@ static void mce_reenable_cpu(void *h) } } -/* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static int -mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) +static int mce_cpu_dead(unsigned int cpu) +{ + mce_intel_hcpu_update(cpu); + + /* intentionally ignoring frozen here */ + if (!cpuhp_tasks_frozen) + cmci_rediscover(); + return 0; +} + +static int mce_cpu_online(unsigned int cpu) { - unsigned int cpu = (unsigned long)hcpu; struct timer_list *t = &per_cpu(mce_timer, cpu); + int ret; - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: - mce_device_create(cpu); - if (threshold_cpu_callback) - threshold_cpu_callback(action, cpu); - break; - case CPU_DEAD: - if (threshold_cpu_callback) - threshold_cpu_callback(action, cpu); - mce_device_remove(cpu); - mce_intel_hcpu_update(cpu); + mce_device_create(cpu); - /* intentionally ignoring frozen here */ - if (!(action & CPU_TASKS_FROZEN)) - cmci_rediscover(); - break; - case CPU_DOWN_PREPARE: - smp_call_function_single(cpu, mce_disable_cpu, &action, 1); - del_timer_sync(t); - break; - case CPU_DOWN_FAILED: - smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); - mce_start_timer(cpu, t); - break; + ret = mce_threshold_create_device(cpu); + if (ret) { + mce_device_remove(cpu); + return ret; } - - return NOTIFY_OK; + mce_reenable_cpu(); + mce_start_timer(cpu, t); + return 0; } -static struct notifier_block mce_cpu_notifier = { - .notifier_call = mce_cpu_callback, -}; +static int mce_cpu_pre_down(unsigned int cpu) +{ + struct timer_list *t = &per_cpu(mce_timer, cpu); + + mce_disable_cpu(); + del_timer_sync(t); + mce_threshold_remove_device(cpu); + mce_device_remove(cpu); + return 0; +} static __init void mce_init_banks(void) { @@ -2559,8 +2612,8 @@ static __init void mce_init_banks(void) static __init int mcheck_init_device(void) { + enum cpuhp_state hp_online; int err; - int i = 0; if (!mce_available(&boot_cpu_data)) { err = -EIO; @@ -2578,23 +2631,16 @@ static __init int mcheck_init_device(void) if (err) goto err_out_mem; - cpu_notifier_register_begin(); - for_each_online_cpu(i) { - err = mce_device_create(i); - if (err) { - /* - * Register notifier anyway (and do not unreg it) so - * that we don't leave undeleted timers, see notifier - * callback above. - */ - __register_hotcpu_notifier(&mce_cpu_notifier); - cpu_notifier_register_done(); - goto err_device_create; - } - } + err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL, + mce_cpu_dead); + if (err) + goto err_out_mem; - __register_hotcpu_notifier(&mce_cpu_notifier); - cpu_notifier_register_done(); + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online", + mce_cpu_online, mce_cpu_pre_down); + if (err < 0) + goto err_out_online; + hp_online = err; register_syscore_ops(&mce_syscore_ops); @@ -2607,16 +2653,10 @@ static __init int mcheck_init_device(void) err_register: unregister_syscore_ops(&mce_syscore_ops); + cpuhp_remove_state(hp_online); -err_device_create: - /* - * We didn't keep track of which devices were created above, but - * even if we had, the set of online cpus might have changed. - * Play safe and remove for every possible cpu, since - * mce_device_remove() will do the right thing. - */ - for_each_possible_cpu(i) - mce_device_remove(i); +err_out_online: + cpuhp_remove_state(CPUHP_X86_MCE_DEAD); err_out_mem: free_cpumask_var(mce_device_initialized); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9b5403462936..ffacfdcacb85 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -24,7 +24,6 @@ #include <asm/amd_nb.h> #include <asm/apic.h> -#include <asm/idle.h> #include <asm/mce.h> #include <asm/msr.h> #include <asm/trace/irq_vectors.h> @@ -55,6 +54,8 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 +static bool thresholding_en; + static const char * const th_names[] = { "load_store", "insn_fetch", @@ -69,7 +70,12 @@ static const char * const smca_umc_block_names[] = { "misc_umc" }; -struct smca_bank_name smca_bank_names[] = { +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_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, @@ -84,9 +90,25 @@ struct smca_bank_name smca_bank_names[] = { [SMCA_PSP] = { "psp", "Platform Security Processor" }, [SMCA_SMU] = { "smu", "System Management Unit" }, }; -EXPORT_SYMBOL_GPL(smca_bank_names); -static struct smca_hwid_mcatype smca_hwid_mcatypes[] = { +const char *smca_get_name(enum smca_bank_types t) +{ + if (t >= N_SMCA_BANK_TYPES) + return NULL; + + return smca_names[t].name; +} + +const char *smca_get_long_name(enum smca_bank_types t) +{ + if (t >= N_SMCA_BANK_TYPES) + return NULL; + + return smca_names[t].long_name; +} +EXPORT_SYMBOL_GPL(smca_get_long_name); + +static struct smca_hwid smca_hwid_mcatypes[] = { /* { bank_type, hwid_mcatype, xec_bitmap } */ /* ZN Core (HWID=0xB0) MCA types */ @@ -116,7 +138,7 @@ static struct smca_hwid_mcatype smca_hwid_mcatypes[] = { { SMCA_SMU, HWID_MCATYPE(0x01, 0x0), 0x1 }, }; -struct smca_bank_info smca_banks[MAX_NR_BANKS]; +struct smca_bank smca_banks[MAX_NR_BANKS]; EXPORT_SYMBOL_GPL(smca_banks); /* @@ -142,35 +164,34 @@ static void default_deferred_error_interrupt(void) } void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; -/* - * CPU Initialization - */ - static void get_smca_bank_info(unsigned int bank) { unsigned int i, hwid_mcatype, cpu = smp_processor_id(); - struct smca_hwid_mcatype *type; - u32 high, instanceId; - u16 hwid, mcatype; + struct smca_hwid *s_hwid; + u32 high, instance_id; /* Collect bank_info using CPU 0 for now. */ if (cpu) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instanceId, &high)) { + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instance_id, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } - hwid = high & MCI_IPID_HWID; - mcatype = (high & MCI_IPID_MCATYPE) >> 16; - hwid_mcatype = HWID_MCATYPE(hwid, mcatype); + hwid_mcatype = HWID_MCATYPE(high & MCI_IPID_HWID, + (high & MCI_IPID_MCATYPE) >> 16); for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) { - type = &smca_hwid_mcatypes[i]; - if (hwid_mcatype == type->hwid_mcatype) { - smca_banks[bank].type = type; - smca_banks[bank].type_instance = instanceId; + s_hwid = &smca_hwid_mcatypes[i]; + if (hwid_mcatype == s_hwid->hwid_mcatype) { + + WARN(smca_banks[bank].hwid, + "Bank %s already initialized!\n", + smca_get_name(s_hwid->bank_type)); + + smca_banks[bank].hwid = s_hwid; + smca_banks[bank].id = instance_id; break; } } @@ -533,6 +554,206 @@ 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); + static void __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) { @@ -645,6 +866,7 @@ static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; unsigned int bank, block, cpu = smp_processor_id(); + struct thresh_restart tr; /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { @@ -681,6 +903,11 @@ static void amd_threshold_interrupt(void) log: __log_error(bank, false, true, ((u64)high << 32) | low); + + /* Reset threshold block after logging error. */ + memset(&tr, 0, sizeof(tr)); + tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block]; + threshold_restart_bank(&tr); } /* @@ -826,10 +1053,10 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return th_names[bank]; } - if (!smca_banks[bank].type) + if (!smca_banks[bank].hwid) return NULL; - bank_type = smca_banks[bank].type->bank_type; + bank_type = smca_banks[bank].hwid->bank_type; if (b && bank_type == SMCA_UMC) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) @@ -838,8 +1065,8 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) } snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, - "%s_%x", smca_bank_names[bank_type].name, - smca_banks[bank].type_instance); + "%s_%x", smca_get_name(bank_type), + smca_banks[bank].id); return buf_mcatype; } @@ -1010,31 +1237,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) return err; } -/* create dir/files for all valid threshold banks */ -static int threshold_create_device(unsigned int cpu) -{ - unsigned int bank; - struct threshold_bank **bp; - int err = 0; - - bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks, - GFP_KERNEL); - if (!bp) - return -ENOMEM; - - per_cpu(threshold_banks, cpu) = bp; - - for (bank = 0; bank < mca_cfg.banks; ++bank) { - if (!(per_cpu(bank_map, cpu) & (1 << bank))) - continue; - err = threshold_create_bank(cpu, bank); - if (err) - return err; - } - - return err; -} - static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) { @@ -1102,48 +1304,71 @@ free_out: per_cpu(threshold_banks, cpu)[bank] = NULL; } -static void threshold_remove_device(unsigned int cpu) +int mce_threshold_remove_device(unsigned int cpu) { unsigned int bank; + if (!thresholding_en) + return 0; + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; threshold_remove_bank(cpu, bank); } kfree(per_cpu(threshold_banks, cpu)); + per_cpu(threshold_banks, cpu) = NULL; + return 0; } -/* get notified when a cpu comes on/off */ -static void -amd_64_threshold_cpu_callback(unsigned long action, unsigned int cpu) +/* create dir/files for all valid threshold banks */ +int mce_threshold_create_device(unsigned int cpu) { - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - threshold_create_device(cpu); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - threshold_remove_device(cpu); - break; - default: - break; + unsigned int bank; + struct threshold_bank **bp; + int err = 0; + + if (!thresholding_en) + return 0; + + bp = per_cpu(threshold_banks, cpu); + if (bp) + return 0; + + bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks, + GFP_KERNEL); + if (!bp) + return -ENOMEM; + + per_cpu(threshold_banks, cpu) = bp; + + for (bank = 0; bank < mca_cfg.banks; ++bank) { + if (!(per_cpu(bank_map, cpu) & (1 << bank))) + continue; + err = threshold_create_bank(cpu, bank); + if (err) + goto err; } + return err; +err: + mce_threshold_remove_device(cpu); + return err; } static __init int threshold_init_device(void) { unsigned lcpu = 0; + if (mce_threshold_vector == amd_threshold_interrupt) + thresholding_en = true; + /* to hit CPUs online before the notifier is up */ for_each_online_cpu(lcpu) { - int err = threshold_create_device(lcpu); + int err = mce_threshold_create_device(lcpu); if (err) return err; } - threshold_cpu_callback = amd_64_threshold_cpu_callback; return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 1defb8ea882c..190b3e6cef4d 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -11,6 +11,8 @@ #include <linux/sched.h> #include <linux/cpumask.h> #include <asm/apic.h> +#include <asm/cpufeature.h> +#include <asm/intel-family.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/mce.h> @@ -130,7 +132,7 @@ bool mce_intel_cmci_poll(void) * Reset the counter if we've logged an error in the last poll * during the storm. */ - if (machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned))) + if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned))) this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); else this_cpu_dec(cmci_backoff_cnt); @@ -342,7 +344,7 @@ void cmci_recheck(void) return; local_irq_save(flags); - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); + machine_check_poll(0, this_cpu_ptr(&mce_banks_owned)); local_irq_restore(flags); } @@ -464,11 +466,46 @@ static void intel_clear_lmce(void) wrmsrl(MSR_IA32_MCG_EXT_CTL, val); } +static void intel_ppin_init(struct cpuinfo_x86 *c) +{ + unsigned long long val; + + /* + * Even if testing the presence of the MSR would be enough, we don't + * want to risk the situation where other models reuse this MSR for + * other purposes. + */ + switch (c->x86_model) { + case INTEL_FAM6_IVYBRIDGE_X: + case INTEL_FAM6_HASWELL_X: + case INTEL_FAM6_BROADWELL_XEON_D: + case INTEL_FAM6_BROADWELL_X: + case INTEL_FAM6_SKYLAKE_X: + if (rdmsrl_safe(MSR_PPIN_CTL, &val)) + return; + + if ((val & 3UL) == 1UL) { + /* PPIN available but disabled: */ + return; + } + + /* If PPIN is disabled, but not locked, try to enable: */ + if (!(val & 3UL)) { + wrmsrl_safe(MSR_PPIN_CTL, val | 2UL); + rdmsrl_safe(MSR_PPIN_CTL, &val); + } + + if ((val & 3UL) == 2UL) + set_cpu_cap(c, X86_FEATURE_INTEL_PPIN); + } +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); intel_init_cmci(); intel_init_lmce(); + intel_ppin_init(c); } void mce_intel_feature_clear(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 6b9dc4d18ccc..465aca8be009 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -26,7 +26,6 @@ #include <asm/processor.h> #include <asm/apic.h> -#include <asm/idle.h> #include <asm/mce.h> #include <asm/msr.h> #include <asm/trace/irq_vectors.h> @@ -271,58 +270,32 @@ static void thermal_throttle_remove_dev(struct device *dev) } /* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static int -thermal_throttle_cpu_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +static int thermal_throttle_online(unsigned int cpu) { - unsigned int cpu = (unsigned long)hcpu; - struct device *dev; - int err = 0; - - dev = get_cpu_device(cpu); - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - err = thermal_throttle_add_dev(dev, cpu); - WARN_ON(err); - break; - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - thermal_throttle_remove_dev(dev); - break; - } - return notifier_from_errno(err); + struct device *dev = get_cpu_device(cpu); + + return thermal_throttle_add_dev(dev, cpu); } -static struct notifier_block thermal_throttle_cpu_notifier = +static int thermal_throttle_offline(unsigned int cpu) { - .notifier_call = thermal_throttle_cpu_callback, -}; + struct device *dev = get_cpu_device(cpu); + + thermal_throttle_remove_dev(dev); + return 0; +} static __init int thermal_throttle_init_device(void) { - unsigned int cpu = 0; - int err; + int ret; if (!atomic_read(&therm_throt_en)) return 0; - cpu_notifier_register_begin(); - - /* connect live CPUs to sysfs */ - for_each_online_cpu(cpu) { - err = thermal_throttle_add_dev(get_cpu_device(cpu), cpu); - WARN_ON(err); - } - - __register_hotcpu_notifier(&thermal_throttle_cpu_notifier); - cpu_notifier_register_done(); - - return 0; + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/therm:online", + thermal_throttle_online, + thermal_throttle_offline); + return ret < 0 ? ret : 0; } device_initcall(thermal_throttle_init_device); diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index fcf9ae9384f4..9beb092d68a5 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -6,7 +6,6 @@ #include <asm/irq_vectors.h> #include <asm/apic.h> -#include <asm/idle.h> #include <asm/mce.h> #include <asm/trace/irq_vectors.h> |