diff options
Diffstat (limited to 'arch/x86/kernel')
30 files changed, 928 insertions, 120 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 79076d75bdbf..05110c1097ae 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -123,6 +123,7 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o +obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o ifdef CONFIG_FRAME_POINTER obj-y += unwind_frame.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 066ceb7767b8..4764fa56924d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -456,6 +456,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* * stash over-ride to indicate we've been here diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4fdf6230d93c..458da8509b75 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -13,8 +13,20 @@ #include <linux/spinlock.h> #include <asm/amd_nb.h> +#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 +#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 + +/* Protect the PCI config register pairs used for SMN and DF indirect access. */ +static DEFINE_MUTEX(smn_mutex); + static u32 *flush_words; +static const struct pci_device_id amd_root_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, + {} +}; + const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -24,9 +36,10 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, {} }; -EXPORT_SYMBOL(amd_nb_misc_ids); +EXPORT_SYMBOL_GPL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, @@ -34,6 +47,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, {} }; @@ -44,8 +58,25 @@ const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = { { } }; -struct amd_northbridge_info amd_northbridges; -EXPORT_SYMBOL(amd_northbridges); +static struct amd_northbridge_info amd_northbridges; + +u16 amd_nb_num(void) +{ + return amd_northbridges.num; +} +EXPORT_SYMBOL_GPL(amd_nb_num); + +bool amd_nb_has_feature(unsigned int feature) +{ + return ((amd_northbridges.flags & feature) == feature); +} +EXPORT_SYMBOL_GPL(amd_nb_has_feature); + +struct amd_northbridge *node_to_amd_nb(int node) +{ + return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL; +} +EXPORT_SYMBOL_GPL(node_to_amd_nb); static struct pci_dev *next_northbridge(struct pci_dev *dev, const struct pci_device_id *ids) @@ -58,13 +89,106 @@ static struct pci_dev *next_northbridge(struct pci_dev *dev, return dev; } +static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) +{ + struct pci_dev *root; + int err = -ENODEV; + + if (node >= amd_northbridges.num) + goto out; + + root = node_to_amd_nb(node)->root; + if (!root) + goto out; + + mutex_lock(&smn_mutex); + + err = pci_write_config_dword(root, 0x60, address); + if (err) { + pr_warn("Error programming SMN address 0x%x.\n", address); + goto out_unlock; + } + + err = (write ? pci_write_config_dword(root, 0x64, *value) + : pci_read_config_dword(root, 0x64, value)); + if (err) + pr_warn("Error %s SMN address 0x%x.\n", + (write ? "writing to" : "reading from"), address); + +out_unlock: + mutex_unlock(&smn_mutex); + +out: + return err; +} + +int amd_smn_read(u16 node, u32 address, u32 *value) +{ + return __amd_smn_rw(node, address, value, false); +} +EXPORT_SYMBOL_GPL(amd_smn_read); + +int amd_smn_write(u16 node, u32 address, u32 value) +{ + return __amd_smn_rw(node, address, &value, true); +} +EXPORT_SYMBOL_GPL(amd_smn_write); + +/* + * Data Fabric Indirect Access uses FICAA/FICAD. + * + * Fabric Indirect Configuration Access Address (FICAA): Constructed based + * on the device's Instance Id and the PCI function and register offset of + * the desired register. + * + * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO + * and FICAD HI registers but so far we only need the LO register. + */ +int amd_df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) +{ + struct pci_dev *F4; + u32 ficaa; + int err = -ENODEV; + + if (node >= amd_northbridges.num) + goto out; + + F4 = node_to_amd_nb(node)->link; + if (!F4) + goto out; + + ficaa = 1; + ficaa |= reg & 0x3FC; + ficaa |= (func & 0x7) << 11; + ficaa |= instance_id << 16; + + mutex_lock(&smn_mutex); + + err = pci_write_config_dword(F4, 0x5C, ficaa); + if (err) { + pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa); + goto out_unlock; + } + + err = pci_read_config_dword(F4, 0x98, lo); + if (err) + pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa); + +out_unlock: + mutex_unlock(&smn_mutex); + +out: + return err; +} +EXPORT_SYMBOL_GPL(amd_df_indirect_read); + int amd_cache_northbridges(void) { u16 i = 0; struct amd_northbridge *nb; - struct pci_dev *misc, *link; + struct pci_dev *root, *misc, *link; - if (amd_nb_num()) + if (amd_northbridges.num) return 0; misc = NULL; @@ -74,15 +198,17 @@ int amd_cache_northbridges(void) if (!i) return -ENODEV; - nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); + nb = kcalloc(i, sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) return -ENOMEM; amd_northbridges.nb = nb; amd_northbridges.num = i; - link = misc = NULL; - for (i = 0; i != amd_nb_num(); i++) { + link = misc = root = NULL; + for (i = 0; i != amd_northbridges.num; i++) { + node_to_amd_nb(i)->root = root = + next_northbridge(root, amd_root_ids); node_to_amd_nb(i)->misc = misc = next_northbridge(misc, amd_nb_misc_ids); node_to_amd_nb(i)->link = link = @@ -139,13 +265,13 @@ struct resource *amd_get_mmconfig_range(struct resource *res) { u32 address; u64 base, msr; - unsigned segn_busn_bits; + unsigned int segn_busn_bits; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return NULL; /* assume all cpus from fam10h have mmconfig */ - if (boot_cpu_data.x86 < 0x10) + if (boot_cpu_data.x86 < 0x10) return NULL; address = MSR_FAM10H_MMIO_CONF_BASE; @@ -226,14 +352,14 @@ static void amd_cache_gart(void) if (!amd_nb_has_feature(AMD_NB_GART)) return; - flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL); + flush_words = kmalloc_array(amd_northbridges.num, sizeof(u32), GFP_KERNEL); if (!flush_words) { amd_northbridges.flags &= ~AMD_NB_GART; pr_notice("Cannot initialize GART flush words, GART support disabled\n"); return; } - for (i = 0; i != amd_nb_num(); i++) + for (i = 0; i != amd_northbridges.num; i++) pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c, &flush_words[i]); } @@ -246,18 +372,20 @@ void amd_flush_garts(void) if (!amd_nb_has_feature(AMD_NB_GART)) return; - /* Avoid races between AGP and IOMMU. In theory it's not needed - but I'm not sure if the hardware won't lose flush requests - when another is pending. This whole thing is so expensive anyways - that it doesn't matter to serialize more. -AK */ + /* + * Avoid races between AGP and IOMMU. In theory it's not needed + * but I'm not sure if the hardware won't lose flush requests + * when another is pending. This whole thing is so expensive anyways + * that it doesn't matter to serialize more. -AK + */ spin_lock_irqsave(&gart_lock, flags); flushed = 0; - for (i = 0; i < amd_nb_num(); i++) { + for (i = 0; i < amd_northbridges.num; i++) { pci_write_config_dword(node_to_amd_nb(i)->misc, 0x9c, flush_words[i] | 1); flushed++; } - for (i = 0; i < amd_nb_num(); i++) { + for (i = 0; i < amd_northbridges.num; i++) { u32 w; /* Make sure the hardware actually executed the flush*/ for (;;) { diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index aeef53ce93e1..35690a168cf7 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -815,9 +815,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) l = li; } addr1 = (base << shift) + - f * (unsigned long)(1 << m_io); + f * (1ULL << m_io); addr2 = (base << shift) + - (l + 1) * (unsigned long)(1 << m_io); + (l + 1) * (1ULL << m_io); pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2); if (max_io < l) diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index c7364bd633e1..643818a7688b 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -906,14 +906,14 @@ static int apm_cpu_idle(struct cpuidle_device *dev, static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ static unsigned int last_stime; /* = 0 */ - cputime_t stime; + cputime_t stime, utime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; unsigned int bucket; recalc: - task_cputime(current, NULL, &stime); + task_cputime(current, &utime, &stime); if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; } else if (jiffies_since_last_check > idle_period) { @@ -1042,8 +1042,11 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) if (apm_info.get_power_status_broken) return APM_32_UNSUPPORTED; - if (apm_bios_call(&call)) + if (apm_bios_call(&call)) { + if (!call.err) + return APM_NO_ERROR; return call.err; + } *status = call.ebx; *bat = call.ecx; if (apm_info.get_power_status_swabinminutes) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b81fe2d63e15..1e81a37c034e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -347,7 +347,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) #ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); - unsigned int socket_id, core_complex_id; bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ @@ -365,10 +364,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) if (c->x86 != 0x17 || !cpuid_edx(0x80000006)) return; - socket_id = (c->apicid >> bits) - 1; - core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3; - - per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id; + per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; #endif } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9bd910a7dd0a..cc9e980c68ec 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -979,6 +979,35 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c) } /* + * The physical to logical package id mapping is initialized from the + * acpi/mptables information. Make sure that CPUID actually agrees with + * that. + */ +static void sanitize_package_id(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int pkg, apicid, cpu = smp_processor_id(); + + apicid = apic->cpu_present_to_apicid(cpu); + pkg = apicid >> boot_cpu_data.x86_coreid_bits; + + if (apicid != c->initial_apicid) { + pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n", + cpu, apicid, c->initial_apicid); + c->initial_apicid = apicid; + } + if (pkg != c->phys_proc_id) { + pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n", + cpu, pkg, c->phys_proc_id); + c->phys_proc_id = pkg; + } + c->logical_proc_id = topology_phys_to_logical_pkg(pkg); +#else + c->logical_proc_id = 0; +#endif +} + +/* * This does the hard work of actually picking apart the CPU stuff... */ static void identify_cpu(struct cpuinfo_x86 *c) @@ -1103,8 +1132,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif - /* The boot/hotplug time assigment got cleared, restore it */ - c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id); + sanitize_package_id(c); } /* 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..a3cb27af4f9b 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, @@ -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); @@ -2138,6 +2185,7 @@ 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); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9b5403462936..1a0b0a0e5e2b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -69,7 +69,12 @@ 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 +89,25 @@ 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 +137,7 @@ 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 +163,34 @@ 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 +553,206 @@ 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 +865,7 @@ 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 +902,11 @@ 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 +1052,10 @@ 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 +1064,8 @@ 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; } 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/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 620ab06bcf45..017bda12caae 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -429,7 +429,7 @@ int __init save_microcode_in_initrd_amd(void) * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa_nodebug(container); cont_va = container; #endif diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 8cb57df9398d..1db8dc490b66 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -32,6 +32,8 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, + { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 }, + { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 81160578b91a..5130985b758b 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -27,6 +27,7 @@ #include <asm/div64.h> #include <asm/x86_init.h> #include <asm/hypervisor.h> +#include <asm/timer.h> #include <asm/apic.h> #define CPUID_VMWARE_INFO_LEAF 0x40000000 @@ -94,6 +95,10 @@ static void __init vmware_platform_setup(void) } else { pr_warn("Failed to get TSC freq from the hypervisor\n"); } + +#ifdef CONFIG_X86_IO_APIC + no_timer_check = 1; +#endif } /* diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9b7cf5c28f5f..85f854b98a9d 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -112,7 +112,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, for (; stack < stack_info.end; stack++) { unsigned long real_addr; int reliable = 0; - unsigned long addr = *stack; + unsigned long addr = READ_ONCE_NOCHECK(*stack); unsigned long *ret_addr_p = unwind_get_return_address_ptr(&state); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 47004010ad5d..ebb4e95fbd74 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -521,14 +521,14 @@ void fpu__clear(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ - if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) { - /* FPU state will be reallocated lazily at the first use. */ - fpu__drop(fpu); - } else { - if (!fpu->fpstate_active) { - fpu__activate_curr(fpu); - user_fpu_begin(); - } + fpu__drop(fpu); + + /* + * Make sure fpstate is cleared and initialized. + */ + if (static_cpu_has(X86_FEATURE_FPU)) { + fpu__activate_curr(fpu); + user_fpu_begin(); copy_init_fpstate_to_fpregs(); } } diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 124aa5c593f8..095ef7ddd6ae 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -74,6 +74,8 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_MPX); setup_clear_cpu_cap(X86_FEATURE_XGETBV1); setup_clear_cpu_cap(X86_FEATURE_PKU); + setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); + setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); } /* diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b6b2f0264af3..2dabea46f039 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -665,14 +665,17 @@ __PAGE_ALIGNED_BSS initial_pg_pmd: .fill 1024*KPMDS,4,0 #else -ENTRY(initial_page_table) +.globl initial_page_table +initial_page_table: .fill 1024,4,0 #endif initial_pg_fixmap: .fill 1024,4,0 -ENTRY(empty_zero_page) +.globl empty_zero_page +empty_zero_page: .fill 4096,1,0 -ENTRY(swapper_pg_dir) +.globl swapper_pg_dir +swapper_pg_dir: .fill 1024,4,0 EXPORT_SYMBOL(empty_zero_page) diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c new file mode 100644 index 000000000000..cb9c1ed1d391 --- /dev/null +++ b/arch/x86/kernel/itmt.c @@ -0,0 +1,215 @@ +/* + * itmt.c: Support Intel Turbo Boost Max Technology 3.0 + * + * (C) Copyright 2016 Intel Corporation + * Author: Tim Chen <tim.c.chen@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + * + * On platforms supporting Intel Turbo Boost Max Technology 3.0, (ITMT), + * the maximum turbo frequencies of some cores in a CPU package may be + * higher than for the other cores in the same package. In that case, + * better performance can be achieved by making the scheduler prefer + * to run tasks on the CPUs with higher max turbo frequencies. + * + * This file provides functions and data structures for enabling the + * scheduler to favor scheduling on cores can be boosted to a higher + * frequency under ITMT. + */ + +#include <linux/sched.h> +#include <linux/cpumask.h> +#include <linux/cpuset.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/sysctl.h> +#include <linux/nodemask.h> + +static DEFINE_MUTEX(itmt_update_mutex); +DEFINE_PER_CPU_READ_MOSTLY(int, sched_core_priority); + +/* Boolean to track if system has ITMT capabilities */ +static bool __read_mostly sched_itmt_capable; + +/* + * Boolean to control whether we want to move processes to cpu capable + * of higher turbo frequency for cpus supporting Intel Turbo Boost Max + * Technology 3.0. + * + * It can be set via /proc/sys/kernel/sched_itmt_enabled + */ +unsigned int __read_mostly sysctl_sched_itmt_enabled; + +static int sched_itmt_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned int old_sysctl; + int ret; + + mutex_lock(&itmt_update_mutex); + + if (!sched_itmt_capable) { + mutex_unlock(&itmt_update_mutex); + return -EINVAL; + } + + old_sysctl = sysctl_sched_itmt_enabled; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) { + x86_topology_update = true; + rebuild_sched_domains(); + } + + mutex_unlock(&itmt_update_mutex); + + return ret; +} + +static unsigned int zero; +static unsigned int one = 1; +static struct ctl_table itmt_kern_table[] = { + { + .procname = "sched_itmt_enabled", + .data = &sysctl_sched_itmt_enabled, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_itmt_update_handler, + .extra1 = &zero, + .extra2 = &one, + }, + {} +}; + +static struct ctl_table itmt_root_table[] = { + { + .procname = "kernel", + .mode = 0555, + .child = itmt_kern_table, + }, + {} +}; + +static struct ctl_table_header *itmt_sysctl_header; + +/** + * sched_set_itmt_support() - Indicate platform supports ITMT + * + * This function is used by the OS to indicate to scheduler that the platform + * is capable of supporting the ITMT feature. + * + * The current scheme has the pstate driver detects if the system + * is ITMT capable and call sched_set_itmt_support. + * + * This must be done only after sched_set_itmt_core_prio + * has been called to set the cpus' priorities. + * It must not be called with cpu hot plug lock + * held as we need to acquire the lock to rebuild sched domains + * later. + * + * Return: 0 on success + */ +int sched_set_itmt_support(void) +{ + mutex_lock(&itmt_update_mutex); + + if (sched_itmt_capable) { + mutex_unlock(&itmt_update_mutex); + return 0; + } + + itmt_sysctl_header = register_sysctl_table(itmt_root_table); + if (!itmt_sysctl_header) { + mutex_unlock(&itmt_update_mutex); + return -ENOMEM; + } + + sched_itmt_capable = true; + + sysctl_sched_itmt_enabled = 1; + + if (sysctl_sched_itmt_enabled) { + x86_topology_update = true; + rebuild_sched_domains(); + } + + mutex_unlock(&itmt_update_mutex); + + return 0; +} + +/** + * sched_clear_itmt_support() - Revoke platform's support of ITMT + * + * This function is used by the OS to indicate that it has + * revoked the platform's support of ITMT feature. + * + * It must not be called with cpu hot plug lock + * held as we need to acquire the lock to rebuild sched domains + * later. + */ +void sched_clear_itmt_support(void) +{ + mutex_lock(&itmt_update_mutex); + + if (!sched_itmt_capable) { + mutex_unlock(&itmt_update_mutex); + return; + } + sched_itmt_capable = false; + + if (itmt_sysctl_header) { + unregister_sysctl_table(itmt_sysctl_header); + itmt_sysctl_header = NULL; + } + + if (sysctl_sched_itmt_enabled) { + /* disable sched_itmt if we are no longer ITMT capable */ + sysctl_sched_itmt_enabled = 0; + x86_topology_update = true; + rebuild_sched_domains(); + } + + mutex_unlock(&itmt_update_mutex); +} + +int arch_asym_cpu_priority(int cpu) +{ + return per_cpu(sched_core_priority, cpu); +} + +/** + * sched_set_itmt_core_prio() - Set CPU priority based on ITMT + * @prio: Priority of cpu core + * @core_cpu: The cpu number associated with the core + * + * The pstate driver will find out the max boost frequency + * and call this function to set a priority proportional + * to the max boost frequency. CPU with higher boost + * frequency will receive higher priority. + * + * No need to rebuild sched domain after updating + * the CPU priorities. The sched domains have no + * dependency on CPU priorities. + */ +void sched_set_itmt_core_prio(int prio, int core_cpu) +{ + int cpu, i = 1; + + for_each_cpu(cpu, topology_sibling_cpumask(core_cpu)) { + int smt_prio; + + /* + * Ensure that the siblings are moved to the end + * of the priority chain and only used when + * all other high priority cpus are out of capacity. + */ + smt_prio = prio * smp_num_siblings / i; + per_cpu(sched_core_priority, cpu) = smt_prio; + i++; + } +} diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index aad52f1b0f9f..fb5afc6356b2 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -592,6 +592,14 @@ out: local_irq_restore(flags); } +__visible bool __kvm_vcpu_is_preempted(int cpu) +{ + struct kvm_steal_time *src = &per_cpu(steal_time, cpu); + + return !!src->preempted; +} +PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -608,6 +616,11 @@ void __init kvm_spinlock_init(void) pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); pv_lock_ops.wait = kvm_wait; pv_lock_ops.kick = kvm_kick_cpu; + + if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { + pv_lock_ops.vcpu_is_preempted = + PV_CALLEE_SAVE(__kvm_vcpu_is_preempted); + } } static __init int kvm_spinlock_init_jump(void) diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index efe73aacf966..7b0d3da52fb4 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -18,8 +18,10 @@ #ifdef CC_USING_FENTRY # define function_hook __fentry__ +EXPORT_SYMBOL(__fentry__) #else # define function_hook mcount +EXPORT_SYMBOL(mcount) #endif /* All cases save the original rbp (8 bytes) */ @@ -295,7 +297,6 @@ trace: jmp fgraph_trace END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ -EXPORT_SYMBOL(function_hook) #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 2c55a003b793..6d4bf812af45 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -12,7 +12,6 @@ __visible void __native_queued_spin_unlock(struct qspinlock *lock) { native_queued_spin_unlock(lock); } - PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock); bool pv_is_native_spin_unlock(void) @@ -21,12 +20,25 @@ bool pv_is_native_spin_unlock(void) __raw_callee_save___native_queued_spin_unlock; } +__visible bool __native_vcpu_is_preempted(int cpu) +{ + return false; +} +PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted); + +bool pv_is_native_vcpu_is_preempted(void) +{ + return pv_lock_ops.vcpu_is_preempted.func == + __raw_callee_save___native_vcpu_is_preempted; +} + struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), .wait = paravirt_nop, .kick = paravirt_nop, + .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted), #endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 920c6ae08592..33cdec221f3d 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -12,6 +12,7 @@ DEF_NATIVE(pv_cpu_ops, clts, "clts"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); +DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) @@ -27,6 +28,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) } extern bool pv_is_native_spin_unlock(void); +extern bool pv_is_native_vcpu_is_preempted(void); unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) @@ -56,9 +58,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, end = end_pv_lock_ops_queued_spin_unlock; goto patch_site; } + goto patch_default; + + case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted): + if (pv_is_native_vcpu_is_preempted()) { + start = start_pv_lock_ops_vcpu_is_preempted; + end = end_pv_lock_ops_vcpu_is_preempted; + goto patch_site; + } + goto patch_default; #endif default: +patch_default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index bb3840cedb4f..b0fceff502b3 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -21,6 +21,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); +DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) @@ -36,6 +37,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) } extern bool pv_is_native_spin_unlock(void); +extern bool pv_is_native_vcpu_is_preempted(void); unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) @@ -68,9 +70,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, end = end_pv_lock_ops_queued_spin_unlock; goto patch_site; } + goto patch_default; + + case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted): + if (pv_is_native_vcpu_is_preempted()) { + start = start_pv_lock_ops_vcpu_is_preempted; + end = end_pv_lock_ops_vcpu_is_preempted; + goto patch_site; + } + goto patch_default; #endif default: +patch_default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 51402a7e4ca6..0bee04d41bed 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -625,8 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, amd_disable_seq_and_redirect_scrub); -#endif - #if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) #include <linux/jump_label.h> #include <asm/string_64.h> @@ -657,3 +655,4 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); #endif +#endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bbfbca5fea0c..9c337b0e8ba7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1221,11 +1221,16 @@ void __init setup_arch(char **cmdline_p) */ get_smp_config(); + /* + * Systems w/o ACPI and mptables might not have it mapped the local + * APIC yet, but prefill_possible_map() might need to access it. + */ + init_apic_mappings(); + prefill_possible_map(); init_cpu_to_node(); - init_apic_mappings(); io_apic_init_mappings(); kvm_guest_init(); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index 40df33753bae..ec1f756f9dc9 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -105,9 +105,6 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) /* Don't let flags to be set from userspace */ act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); - if (user_64bit_mode(current_pt_regs())) - return; - if (in_ia32_syscall()) act->sa.sa_flags |= SA_IA32_ABI; if (in_x32_syscall()) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 951f093a96fe..118e792a7be6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -109,6 +109,17 @@ static bool logical_packages_frozen __read_mostly; /* Maximum number of SMT threads on any online core */ int __max_smt_threads __read_mostly; +/* Flag to indicate if a complete sched domain rebuild is required */ +bool x86_topology_update; + +int arch_update_cpu_topology(void) +{ + int retval = x86_topology_update; + + x86_topology_update = false; + return retval; +} + static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; @@ -471,22 +482,42 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } +#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC) +static inline int x86_sched_itmt_flags(void) +{ + return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0; +} + +#ifdef CONFIG_SCHED_MC +static int x86_core_flags(void) +{ + return cpu_core_flags() | x86_sched_itmt_flags(); +} +#endif +#ifdef CONFIG_SCHED_SMT +static int x86_smt_flags(void) +{ + return cpu_smt_flags() | x86_sched_itmt_flags(); +} +#endif +#endif + static struct sched_domain_topology_level x86_numa_in_package_topology[] = { #ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, + { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, #endif #ifdef CONFIG_SCHED_MC - { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, #endif { NULL, }, }; static struct sched_domain_topology_level x86_topology[] = { #ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, + { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, #endif #ifdef CONFIG_SCHED_MC - { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, #endif { cpu_cpu_mask, SD_INIT_NAME(DIE) }, { NULL, }, @@ -821,14 +852,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) return (send_status | accept_status); } -void smp_announce(void) -{ - int num_nodes = num_online_nodes(); - - printk(KERN_INFO "x86: Booted up %d node%s, %d CPUs\n", - num_nodes, (num_nodes > 1 ? "s" : ""), num_online_cpus()); -} - /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { @@ -1409,15 +1432,17 @@ __init void prefill_possible_map(void) /* No boot processor was found in mptable or ACPI MADT */ if (!num_processors) { - int apicid = boot_cpu_physical_apicid; - int cpu = hard_smp_processor_id(); + if (boot_cpu_has(X86_FEATURE_APIC)) { + int apicid = boot_cpu_physical_apicid; + int cpu = hard_smp_processor_id(); - pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu); + pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu); - /* Make sure boot cpu is enumerated */ - if (apic->cpu_present_to_apicid(0) == BAD_APICID && - apic->apic_id_valid(apicid)) - generic_processor_info(apicid, boot_cpu_apic_version); + /* Make sure boot cpu is enumerated */ + if (apic->cpu_present_to_apicid(0) == BAD_APICID && + apic->apic_id_valid(apicid)) + generic_processor_info(apicid, boot_cpu_apic_version); + } if (!num_processors) num_processors = 1; diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 764a29f84de7..85195d447a92 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -66,13 +66,36 @@ __init int create_simplefb(const struct screen_info *si, { struct platform_device *pd; struct resource res; - unsigned long len; + u64 base, size; + u32 length; - /* don't use lfb_size as it may contain the whole VMEM instead of only - * the part that is occupied by the framebuffer */ - len = mode->height * mode->stride; - len = PAGE_ALIGN(len); - if (len > (u64)si->lfb_size << 16) { + /* + * If the 64BIT_BASE capability is set, ext_lfb_base will contain the + * upper half of the base address. Assemble the address, then make sure + * it is valid and we can actually access it. + */ + base = si->lfb_base; + if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE) + base |= (u64)si->ext_lfb_base << 32; + if (!base || (u64)(resource_size_t)base != base) { + printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n"); + return -EINVAL; + } + + /* + * Don't use lfb_size as IORESOURCE size, since it may contain the + * entire VMEM, and thus require huge mappings. Use just the part we + * need, that is, the part where the framebuffer is located. But verify + * that it does not exceed the advertised VMEM. + * Note that in case of VBE, the lfb_size is shifted by 16 bits for + * historical reasons. + */ + size = si->lfb_size; + if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) + size <<= 16; + length = mode->height * mode->stride; + length = PAGE_ALIGN(length); + if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } @@ -81,8 +104,8 @@ __init int create_simplefb(const struct screen_info *si, memset(&res, 0, sizeof(res)); res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; res.name = simplefb_resname; - res.start = si->lfb_base; - res.end = si->lfb_base + len - 1; + res.start = base; + res.end = res.start + length - 1; if (res.end <= res.start) return -EINVAL; diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 9298993dc8b7..22881ddcbb9f 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -7,11 +7,15 @@ unsigned long unwind_get_return_address(struct unwind_state *state) { + unsigned long addr; + if (unwind_done(state)) return 0; + addr = READ_ONCE_NOCHECK(*state->sp); + return ftrace_graph_ret_addr(state->task, &state->graph_idx, - *state->sp, state->sp); + addr, state->sp); } EXPORT_SYMBOL_GPL(unwind_get_return_address); @@ -23,9 +27,12 @@ bool unwind_next_frame(struct unwind_state *state) return false; do { - for (state->sp++; state->sp < info->end; state->sp++) - if (__kernel_text_address(*state->sp)) + for (state->sp++; state->sp < info->end; state->sp++) { + unsigned long addr = READ_ONCE_NOCHECK(*state->sp); + + if (__kernel_text_address(addr)) return true; + } state->sp = info->next_sp; @@ -47,7 +54,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, get_stack_info(first_frame, state->task, &state->stack_info, &state->stack_mask); - if (!__kernel_text_address(*first_frame)) + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + if (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + !__kernel_text_address(*first_frame))) unwind_next_frame(state); } EXPORT_SYMBOL_GPL(__unwind_start); |