diff options
Diffstat (limited to 'arch/x86/kernel')
67 files changed, 1573 insertions, 870 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7a37d9357bc4..3b20607d581b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) { struct acpi_madt_local_x2apic *processor = NULL; #ifdef CONFIG_X86_X2APIC - int apic_id; + u32 apic_id; u8 enabled; #endif @@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) apic_id = processor->local_apic_id; enabled = processor->lapic_flags & ACPI_MADT_ENABLED; + /* Ignore invalid ID */ + if (apic_id == 0xffffffff) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size @@ -222,10 +226,13 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - if (!apic->apic_id_valid(apic_id) && enabled) - printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); - else - acpi_register_lapic(apic_id, processor->uid, enabled); + if (!apic->apic_id_valid(apic_id)) { + if (enabled) + pr_warn(PREFIX "x2apic entry ignored\n"); + return 0; + } + + acpi_register_lapic(apic_id, processor->uid, enabled); #else printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); #endif diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c88e0b127810..b481b95bd8f6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -14,8 +14,11 @@ #include <asm/amd_nb.h> #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -24,6 +27,7 @@ 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) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, {} }; @@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { 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) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; @@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { 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) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c index a360801779ae..02b4839478b1 100644 --- a/arch/x86/kernel/apic/apic_common.c +++ b/arch/x86/kernel/apic/apic_common.c @@ -40,7 +40,7 @@ int default_check_phys_apicid_present(int phys_apicid) return physid_isset(phys_apicid, phys_cpu_present_map); } -int default_apic_id_valid(int apicid) +int default_apic_id_valid(u32 apicid) { return (apicid < 255); } diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 134e04506ab4..78778b54f904 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigned int id) return id << 24; } -static int numachip_apic_id_valid(int apicid) +static int numachip_apic_id_valid(u32 apicid) { /* Trust what bootloader passes in MADT */ return 1; diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h index b107de381cb5..a49b3604027f 100644 --- a/arch/x86/kernel/apic/x2apic.h +++ b/arch/x86/kernel/apic/x2apic.h @@ -1,6 +1,6 @@ /* Common bits for X2APIC cluster/physical modes. */ -int x2apic_apic_id_valid(int apicid); +int x2apic_apic_id_valid(u32 apicid); int x2apic_apic_id_registered(void); void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); unsigned int x2apic_get_apic_id(unsigned long id); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 8b04234e010b..7685444a106b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -116,6 +116,7 @@ static void init_x2apic_ldr(void) goto update; } cmsk = cluster_hotplug_mask; + cmsk->clusterid = cluster; cluster_hotplug_mask = NULL; update: this_cpu_write(cluster_masks, cmsk); diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index e2829bf40e4a..b5cf9e7b3830 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -101,7 +101,7 @@ static int x2apic_phys_probe(void) } /* Common x2apic functions, also used by x2apic_cluster */ -int x2apic_apic_id_valid(int apicid) +int x2apic_apic_id_valid(u32 apicid) { return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f11910b44638..efaf2d4f9c3c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -557,7 +557,7 @@ static void uv_send_IPI_all(int vector) uv_send_IPI_mask(cpu_online_mask, vector); } -static int uv_apic_id_valid(int apicid) +static int uv_apic_id_valid(u32 apicid) { return 1; } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index dfcbe6924eaf..5d0de79fdab0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1715,19 +1715,6 @@ static int proc_apm_show(struct seq_file *m, void *v) return 0; } -static int proc_apm_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_apm_show, NULL); -} - -static const struct file_operations apm_file_ops = { - .owner = THIS_MODULE, - .open = proc_apm_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int apm(void *unused) { unsigned short bx; @@ -2360,7 +2347,7 @@ static int __init apm_init(void) set_desc_base(&gdt[APM_DS >> 3], (unsigned long)__va((unsigned long)apm_info.bios.dseg << 4)); - proc_create("apm", 0, NULL, &apm_file_ops); + proc_create_single("apm", 0, NULL, proc_apm_show); kapmd_task = kthread_create(apm, NULL, "kapmd"); if (IS_ERR(kapmd_task)) { @@ -2446,7 +2433,7 @@ MODULE_PARM_DESC(idle_threshold, "System idle percentage above which to make APM BIOS idle calls"); module_param(idle_period, int, 0444); MODULE_PARM_DESC(idle_period, - "Period (in sec/100) over which to caculate the idle percentage"); + "Period (in sec/100) over which to calculate the idle percentage"); module_param(smp, bool, 0444); MODULE_PARM_DESC(smp, "Set this to enable APM use on an SMP platform. Use with caution on older systems"); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a66229f51b12..7a40196967cb 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -17,7 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) -obj-y := intel_cacheinfo.o scattered.o topology.o +obj-y := cacheinfo.o scattered.o topology.o obj-y += common.o obj-y += rdrand.o obj-y += match.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 12bc0a1139da..082d7875cef8 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -9,7 +9,9 @@ #include <linux/random.h> #include <asm/processor.h> #include <asm/apic.h> +#include <asm/cacheinfo.h> #include <asm/cpu.h> +#include <asm/spec-ctrl.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> @@ -297,7 +299,6 @@ static int nearby_node(int apicid) } #endif -#ifdef CONFIG_SMP /* * Fix up cpu_core_id for pre-F17h systems to be in the * [0 .. cores_per_node - 1] range. Not really needed but @@ -327,6 +328,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + int err; u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -345,21 +347,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c) } /* - * We may have multiple LLCs if L3 caches exist, so check if we - * have an L3 cache by looking at the L3 cache CPUID leaf. + * In case leaf B is available, use it to derive + * topology information. */ - if (cpuid_edx(0x80000006)) { - if (c->x86 == 0x17) { - /* - * LLC is at the core complex level. - * Core complex id is ApicId[3]. - */ - per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; - } else { - /* LLC is at the node level. */ - per_cpu(cpu_llc_id, cpu) = node_id; - } - } + err = detect_extended_topology(c); + if (!err) + c->x86_coreid_bits = get_count_order(c->x86_max_cores); + + cacheinfo_amd_init_llc_id(c, cpu, node_id); + } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; @@ -375,7 +371,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) legacy_fixup_core_id(c); } } -#endif /* * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. @@ -383,7 +378,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) */ static void amd_detect_cmp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); @@ -394,17 +388,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; - amd_get_topology(c); -#endif } u16 amd_get_nb_id(int cpu) { - u16 id = 0; -#ifdef CONFIG_SMP - id = per_cpu(cpu_llc_id, cpu); -#endif - return id; + return per_cpu(cpu_llc_id, cpu); } EXPORT_SYMBOL_GPL(amd_get_nb_id); @@ -554,6 +542,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_FAM10H_NODE_ID, value); nodes_per_socket = ((value >> 3) & 7) + 1; } + + if (c->x86 >= 0x15 && c->x86 <= 0x17) { + unsigned int bit; + + switch (c->x86) { + case 0x15: bit = 54; break; + case 0x16: bit = 33; break; + case 0x17: bit = 10; break; + default: return; + } + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << bit; + } + } } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -791,6 +799,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static void init_amd_zn(struct cpuinfo_x86 *c) { + set_cpu_cap(c, X86_FEATURE_ZEN); /* * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects * all up to and including B1. @@ -842,6 +851,7 @@ static void init_amd(struct cpuinfo_x86 *c) /* Multi core CPU? */ if (c->extended_cpuid_level >= 0x80000008) { amd_detect_cmp(c); + amd_get_topology(c); srat_detect_node(c); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bfca937bdcc3..7416fc206b4a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,8 +12,10 @@ #include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> +#include <linux/nospec.h> +#include <linux/prctl.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> @@ -27,6 +29,27 @@ #include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); +static void __init ssb_select_mitigation(void); + +/* + * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any + * writes to SPEC_CTRL contain whatever reserved bits have been set. + */ +u64 __ro_after_init x86_spec_ctrl_base; +EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* + * The vendor and possibly platform specific bits which can be modified in + * x86_spec_ctrl_base. + */ +static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; + +/* + * AMD specific MSR info for Speculative Store Bypass control. + * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). + */ +u64 __ro_after_init x86_amd_ls_cfg_base; +u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; void __init check_bugs(void) { @@ -37,9 +60,27 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* + * Read the SPEC_CTRL MSR to account for reserved bits which may + * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD + * init code as it is not enumerated and depends on the family. + */ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + /* Allow STIBP in MSR_SPEC_CTRL if supported */ + if (boot_cpu_has(X86_FEATURE_STIBP)) + x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; + /* Select the proper spectre mitigation before patching alternatives */ spectre_v2_select_mitigation(); + /* + * Select proper mitigation for any exposure to the Speculative Store + * Bypass vulnerability. + */ + ssb_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -93,7 +134,76 @@ static const char *spectre_v2_strings[] = { #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt -static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + +void +x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +{ + u64 msrval, guestval, hostval = x86_spec_ctrl_base; + struct thread_info *ti = current_thread_info(); + + /* Is MSR_SPEC_CTRL implemented ? */ + if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { + /* + * Restrict guest_spec_ctrl to supported values. Clear the + * modifiable bits in the host base value and or the + * modifiable bits from the guest value. + */ + guestval = hostval & ~x86_spec_ctrl_mask; + guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; + + /* SSBD controlled in MSR_SPEC_CTRL */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + + if (hostval != guestval) { + msrval = setguest ? guestval : hostval; + wrmsrl(MSR_IA32_SPEC_CTRL, msrval); + } + } + + /* + * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update + * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. + */ + if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !static_cpu_has(X86_FEATURE_VIRT_SSBD)) + return; + + /* + * If the host has SSBD mitigation enabled, force it in the host's + * virtual MSR value. If its not permanently enabled, evaluate + * current's TIF_SSBD thread flag. + */ + if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE)) + hostval = SPEC_CTRL_SSBD; + else + hostval = ssbd_tif_to_spec_ctrl(ti->flags); + + /* Sanitize the guest value */ + guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD; + + if (hostval != guestval) { + unsigned long tif; + + tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : + ssbd_spec_ctrl_to_tif(hostval); + + speculative_store_bypass_update(tif); + } +} +EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); + +static void x86_amd_ssb_disable(void) +{ + u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask; + + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD); + else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + wrmsrl(MSR_AMD64_LS_CFG, msrval); +} #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -312,32 +422,289 @@ retpoline_auto: } #undef pr_fmt +#define pr_fmt(fmt) "Speculative Store Bypass: " fmt + +static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE; + +/* The kernel command line selection */ +enum ssb_mitigation_cmd { + SPEC_STORE_BYPASS_CMD_NONE, + SPEC_STORE_BYPASS_CMD_AUTO, + SPEC_STORE_BYPASS_CMD_ON, + SPEC_STORE_BYPASS_CMD_PRCTL, + SPEC_STORE_BYPASS_CMD_SECCOMP, +}; + +static const char *ssb_strings[] = { + [SPEC_STORE_BYPASS_NONE] = "Vulnerable", + [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", + [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", + [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp", +}; + +static const struct { + const char *option; + enum ssb_mitigation_cmd cmd; +} ssb_mitigation_options[] = { + { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ + { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ + { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ + { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */ + { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */ +}; + +static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) +{ + enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; + char arg[20]; + int ret, i; + + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + return SPEC_STORE_BYPASS_CMD_NONE; + } else { + ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", + arg, sizeof(arg)); + if (ret < 0) + return SPEC_STORE_BYPASS_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { + if (!match_option(arg, ret, ssb_mitigation_options[i].option)) + continue; + + cmd = ssb_mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(ssb_mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPEC_STORE_BYPASS_CMD_AUTO; + } + } + + return cmd; +} + +static enum ssb_mitigation __init __ssb_select_mitigation(void) +{ + enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; + enum ssb_mitigation_cmd cmd; + + if (!boot_cpu_has(X86_FEATURE_SSBD)) + return mode; + + cmd = ssb_parse_cmdline(); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) && + (cmd == SPEC_STORE_BYPASS_CMD_NONE || + cmd == SPEC_STORE_BYPASS_CMD_AUTO)) + return mode; + + switch (cmd) { + case SPEC_STORE_BYPASS_CMD_AUTO: + case SPEC_STORE_BYPASS_CMD_SECCOMP: + /* + * Choose prctl+seccomp as the default mode if seccomp is + * enabled. + */ + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPEC_STORE_BYPASS_SECCOMP; + else + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_ON: + mode = SPEC_STORE_BYPASS_DISABLE; + break; + case SPEC_STORE_BYPASS_CMD_PRCTL: + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_NONE: + break; + } + + /* + * We have three CPU feature flags that are in play here: + * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. + * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass + * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation + */ + if (mode == SPEC_STORE_BYPASS_DISABLE) { + setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); + /* + * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses + * a completely different MSR and bit dependent on family. + */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + x86_spec_ctrl_base |= SPEC_CTRL_SSBD; + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + break; + case X86_VENDOR_AMD: + x86_amd_ssb_disable(); + break; + } + } + + return mode; +} + +static void ssb_select_mitigation(void) +{ + ssb_mode = __ssb_select_mitigation(); + + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + pr_info("%s\n", ssb_strings[ssb_mode]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Speculation prctl: " fmt + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + bool update; + + if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && + ssb_mode != SPEC_STORE_BYPASS_SECCOMP) + return -ENXIO; + + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + task_set_spec_ssb_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + /* + * If being set on non-current task, delay setting the CPU + * mitigation until it is next scheduled. + */ + if (task == current && update) + speculative_store_bypass_update_current(); + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +#ifdef CONFIG_SECCOMP +void arch_seccomp_spec_mitigate(struct task_struct *task) +{ + if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) + ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); +} +#endif + +static int ssb_prctl_get(struct task_struct *task) +{ + switch (ssb_mode) { + case SPEC_STORE_BYPASS_DISABLE: + return PR_SPEC_DISABLE; + case SPEC_STORE_BYPASS_SECCOMP: + case SPEC_STORE_BYPASS_PRCTL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + default: + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + return PR_SPEC_ENABLE; + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_get(task); + default: + return -ENODEV; + } +} + +void x86_spec_ctrl_setup_ap(void) +{ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) + x86_amd_ssb_disable(); +} #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) + +static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, + char *buf, unsigned int bug) { - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); - if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + + break; + + case X86_BUG_SPECTRE_V1: + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + + case X86_BUG_SPECTRE_V2: + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + spectre_v2_module_string()); + + case X86_BUG_SPEC_STORE_BYPASS: + return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + + default: + break; + } + return sprintf(buf, "Vulnerable\n"); } +ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN); +} + ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, char *buf) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) - return sprintf(buf, "Not affected\n"); - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1); } ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - return sprintf(buf, "Not affected\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); +} - return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - spectre_v2_module_string()); +ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } #endif diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 54d04d574148..38354c66df81 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -20,6 +20,8 @@ #include <asm/amd_nb.h> #include <asm/smp.h> +#include "cpu.h" + #define LVL_1_INST 1 #define LVL_1_DATA 2 #define LVL_2 3 @@ -637,6 +639,45 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) +{ + /* + * We may have multiple LLCs if L3 caches exist, so check if we + * have an L3 cache by looking at the L3 cache CPUID leaf. + */ + if (!cpuid_edx(0x80000006)) + return; + + if (c->x86 < 0x17) { + /* LLC is at the node level. */ + per_cpu(cpu_llc_id, cpu) = node_id; + } else if (c->x86 == 0x17 && + c->x86_model >= 0 && c->x86_model <= 0x1F) { + /* + * LLC is at the core complex level. + * Core complex ID is ApicId[3] for these processors. + */ + per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; + } else { + /* + * LLC ID is calculated from the number of threads sharing the + * cache. + * */ + u32 eax, ebx, ecx, edx, num_sharing_cache = 0; + u32 llc_index = find_num_cache_leaves(c) - 1; + + cpuid_count(0x8000001d, llc_index, &eax, &ebx, &ecx, &edx); + if (eax) + num_sharing_cache = ((eax >> 14) & 0xfff) + 1; + + if (num_sharing_cache) { + int bits = get_count_order(num_sharing_cache) - 1; + + per_cpu(cpu_llc_id, cpu) = c->apicid >> bits; + } + } +} + void init_amd_cacheinfo(struct cpuinfo_x86 *c) { @@ -650,7 +691,7 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c) } } -unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) +void init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; @@ -802,7 +843,8 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); - return l2; + if (!l2) + cpu_detect_cache_sizes(c); } static int __cache_amd_cpumap_setup(unsigned int cpu, int index, diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index e5ec0f11c0de..14433ff5b828 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -18,6 +18,13 @@ #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */ +#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 +#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 +#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 +#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 +#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 +#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 + static void init_c3(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -112,6 +119,31 @@ static void early_init_centaur(struct cpuinfo_x86 *c) } } +static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c) +{ + u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; + + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); + msr_ctl = vmx_msr_high | vmx_msr_low; + + if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) + set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); + if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) + set_cpu_cap(c, X86_FEATURE_VNMI); + if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, + vmx_msr_low, vmx_msr_high); + msr_ctl2 = vmx_msr_high | vmx_msr_low; + if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && + (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) + set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) + set_cpu_cap(c, X86_FEATURE_EPT); + if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) + set_cpu_cap(c, X86_FEATURE_VPID); + } +} + static void init_centaur(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -128,6 +160,24 @@ static void init_centaur(struct cpuinfo_x86 *c) clear_cpu_cap(c, 0*32+31); #endif early_init_centaur(c); + init_intel_cacheinfo(c); + detect_num_cpu_cores(c); +#ifdef CONFIG_X86_32 + detect_ht(c); +#endif + + if (c->cpuid_level > 9) { + unsigned int eax = cpuid_eax(10); + + /* + * Check for version and the number of counters + * Version(eax[7:0]) can't be 0; + * Counters(eax[15:8]) should be greater than 1; + */ + if ((eax & 0xff) && (((eax >> 8) & 0xff) > 1)) + set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON); + } + switch (c->x86) { #ifdef CONFIG_X86_32 case 5: @@ -199,6 +249,9 @@ static void init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); #endif + + if (cpu_has(c, X86_FEATURE_VMX)) + centaur_detect_vmx_virtcap(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 348cf4821240..95c8e507580d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -66,6 +66,13 @@ cpumask_var_t cpu_callin_mask; /* representing cpus for which sibling maps can be computed */ cpumask_var_t cpu_sibling_setup_mask; +/* Number of siblings per CPU package */ +int smp_num_siblings = 1; +EXPORT_SYMBOL(smp_num_siblings); + +/* Last level cache ID of each logical CPU */ +DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; + /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { @@ -487,7 +494,7 @@ void load_percpu_segment(int cpu) loadsegment(fs, __KERNEL_PERCPU); #else __loadsegment_simple(gs, 0); - wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu)); + wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu)); #endif load_stack_canary_segment(); } @@ -577,6 +584,19 @@ static void get_model_name(struct cpuinfo_x86 *c) *(s + 1) = '\0'; } +void detect_num_cpu_cores(struct cpuinfo_x86 *c) +{ + unsigned int eax, ebx, ecx, edx; + + c->x86_max_cores = 1; + if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) + return; + + cpuid_count(4, 0, &eax, &ebx, &ecx, &edx); + if (eax & 0x1f) + c->x86_max_cores = (eax >> 26) + 1; +} + void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) { unsigned int n, dummy, ebx, ecx, edx, l2size; @@ -757,17 +777,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c) * and they also have a different bit for STIBP support. Also, * a hypervisor might have set the individual AMD bits even on * Intel CPUs, for finer-grained selection of what's available. - * - * We use the AMD bits in 0x8000_0008 EBX as the generic hardware - * features, which are visible in /proc/cpuinfo and used by the - * kernel. So set those accordingly from the Intel bits. */ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { set_cpu_cap(c, X86_FEATURE_IBRS); set_cpu_cap(c, X86_FEATURE_IBPB); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) set_cpu_cap(c, X86_FEATURE_STIBP); + + if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) || + cpu_has(c, X86_FEATURE_VIRT_SSBD)) + set_cpu_cap(c, X86_FEATURE_SSBD); + + if (cpu_has(c, X86_FEATURE_AMD_IBRS)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } + + if (cpu_has(c, X86_FEATURE_AMD_IBPB)) + set_cpu_cap(c, X86_FEATURE_IBPB); + + if (cpu_has(c, X86_FEATURE_AMD_STIBP)) { + set_cpu_cap(c, X86_FEATURE_STIBP); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } } void get_cpu_cap(struct cpuinfo_x86 *c) @@ -850,15 +885,8 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; c->x86_capability[CPUID_8000_0008_EBX] = ebx; } -#ifdef CONFIG_X86_32 - else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) - c->x86_phys_bits = 36; -#endif if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); @@ -874,6 +902,22 @@ void get_cpu_cap(struct cpuinfo_x86 *c) apply_forced_caps(c); } +static void get_cpu_address_sizes(struct cpuinfo_x86 *c) +{ + u32 eax, ebx, ecx, edx; + + if (c->extended_cpuid_level >= 0x80000008) { + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); + + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + } +#ifdef CONFIG_X86_32 + else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; +#endif +} + static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -918,21 +962,47 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { {} }; -static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +/* Only list CPUs which speculate but are non susceptible to SSB */ +static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + { X86_VENDOR_AMD, 0x12, }, + { X86_VENDOR_AMD, 0x11, }, + { X86_VENDOR_AMD, 0x10, }, + { X86_VENDOR_AMD, 0xf, }, + {} +}; + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; - if (x86_match_cpu(cpu_no_meltdown)) - return false; + if (x86_match_cpu(cpu_no_speculation)) + return; + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + if (!x86_match_cpu(cpu_no_spec_store_bypass) && + !(ia32_cap & ARCH_CAP_SSB_NO)) + setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + + if (x86_match_cpu(cpu_no_meltdown)) + return; + /* Rogue Data Cache Load? No! */ if (ia32_cap & ARCH_CAP_RDCL_NO) - return false; + return; - return true; + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); } /* @@ -965,6 +1035,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); + get_cpu_address_sizes(c); setup_force_cpu_cap(X86_FEATURE_CPUID); if (this_cpu->c_early_init) @@ -982,12 +1053,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_force_cpu_cap(X86_FEATURE_ALWAYS); - if (!x86_match_cpu(cpu_no_speculation)) { - if (cpu_vulnerable_to_meltdown(c)) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - } + cpu_set_bug_bits(c); fpu__init_system(c); @@ -998,6 +1064,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) */ setup_clear_cpu_cap(X86_FEATURE_PCID); #endif + + /* + * Later in the boot process pgtable_l5_enabled() relies on + * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not + * enabled by this point we need to clear the feature bit to avoid + * false-positives at the later stage. + * + * pgtable_l5_enabled() can be false here for several reasons: + * - 5-level paging is disabled compile-time; + * - it's 32-bit kernel; + * - machine doesn't support 5-level paging; + * - user specified 'no5lvl' in kernel command line. + */ + if (!pgtable_l5_enabled()) + setup_clear_cpu_cap(X86_FEATURE_LA57); } void __init early_cpu_init(void) @@ -1097,6 +1178,8 @@ static void generic_identify(struct cpuinfo_x86 *c) get_cpu_cap(c); + get_cpu_address_sizes(c); + if (c->cpuid_level >= 0x00000001) { c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 @@ -1347,6 +1430,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #endif mtrr_ap_init(); validate_apic_and_package_id(c); + x86_spec_ctrl_setup_ap(); } static __init int setup_noclflush(char *arg) @@ -1398,6 +1482,7 @@ __setup("clearcpuid=", setup_clearcpuid); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; +EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union); /* * The following percpu variables are hot. Align current_task to diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e806b11a99af..38216f678fc3 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -47,7 +47,19 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); +extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); +extern u32 get_scattered_cpuid_leaf(unsigned int level, + unsigned int sub_leaf, + enum cpuid_regs_idx reg); +extern void init_intel_cacheinfo(struct cpuinfo_x86 *c); +extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); + +extern void detect_num_cpu_cores(struct cpuinfo_x86 *c); +extern int detect_extended_topology(struct cpuinfo_x86 *c); +extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +extern void x86_spec_ctrl_setup_ap(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 904b0a3c4e53..2c0bd38a44ab 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -19,7 +19,7 @@ struct cpuid_dep { * called from cpu hotplug. It shouldn't do anything in this case, * but it's difficult to tell that to the init reference checker. */ -const static struct cpuid_dep cpuid_deps[] = { +static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b9693b80fc21..eb75564f2d25 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -188,7 +188,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_IBPB); setup_clear_cpu_cap(X86_FEATURE_STIBP); setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL); setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SSBD); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD); } /* @@ -453,24 +456,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -/* - * find out the number of processor cores on the die - */ -static int intel_num_cpu_cores(struct cpuinfo_x86 *c) -{ - unsigned int eax, ebx, ecx, edx; - - if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) - return 1; - - /* Intel has a non-standard dependency on %ecx for this CPUID level. */ - cpuid_count(4, 0, &eax, &ebx, &ecx, &edx); - if (eax & 0x1f) - return (eax >> 26) + 1; - else - return 1; -} - static void detect_vmx_virtcap(struct cpuinfo_x86 *c) { /* Intel VMX MSR indicated features */ @@ -653,8 +638,6 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c) static void init_intel(struct cpuinfo_x86 *c) { - unsigned int l2 = 0; - early_init_intel(c); intel_workarounds(c); @@ -671,19 +654,13 @@ static void init_intel(struct cpuinfo_x86 *c) * let's use the legacy cpuid vector 0x1 and 0x4 for topology * detection. */ - c->x86_max_cores = intel_num_cpu_cores(c); + detect_num_cpu_cores(c); #ifdef CONFIG_X86_32 detect_ht(c); #endif } - l2 = init_intel_cacheinfo(c); - - /* Detect legacy cache sizes if init_intel_cacheinfo did not */ - if (l2 == 0) { - cpu_detect_cache_sizes(c); - l2 = c->x86_cache_size; - } + init_intel_cacheinfo(c); if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); @@ -696,7 +673,8 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); if (boot_cpu_has(X86_FEATURE_DS)) { - unsigned int l1; + unsigned int l1, l2; + rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) set_cpu_cap(c, X86_FEATURE_BTS); @@ -724,6 +702,7 @@ static void init_intel(struct cpuinfo_x86 *c) * Dixon is NOT a Celeron. */ if (c->x86 == 6) { + unsigned int l2 = c->x86_cache_size; char *p = NULL; switch (c->x86_model) { @@ -835,6 +814,9 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" }, + { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" }, + { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" }, { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 589b948e6e01..24bfa63e86cf 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -33,8 +33,8 @@ #include <asm/intel_rdt_sched.h> #include "intel_rdt.h" -#define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 +#define MBA_MAX_MBPS U32_MAX /* Mutex to protect rdtgroup access. */ DEFINE_MUTEX(rdtgroup_mutex); @@ -178,7 +178,7 @@ struct rdt_resource rdt_resources_all[] = { .msr_update = mba_wrmsr, .cache_level = 3, .parse_ctrlval = parse_bw, - .format_str = "%d=%*d", + .format_str = "%d=%*u", .fflags = RFTYPE_RES_MB, }, }; @@ -230,6 +230,14 @@ static inline void cache_alloc_hsw_probe(void) rdt_alloc_capable = true; } +bool is_mba_sc(struct rdt_resource *r) +{ + if (!r) + return rdt_resources_all[RDT_RESOURCE_MBA].membw.mba_sc; + + return r->membw.mba_sc; +} + /* * rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values * exposed to user interface and the h/w understandable delay values. @@ -341,7 +349,7 @@ static int get_cache_id(int cpu, int level) * that can be written to QOS_MSRs. * There are currently no SKUs which support non linear delay values. */ -static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) +u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) { if (r->membw.delay_linear) return MAX_MBA_BW - bw; @@ -431,25 +439,40 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id, return NULL; } +void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm) +{ + int i; + + /* + * Initialize the Control MSRs to having no control. + * For Cache Allocation: Set all bits in cbm + * For Memory Allocation: Set b/w requested to 100% + * and the bandwidth in MBps to U32_MAX + */ + for (i = 0; i < r->num_closid; i++, dc++, dm++) { + *dc = r->default_ctrl; + *dm = MBA_MAX_MBPS; + } +} + static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d) { struct msr_param m; - u32 *dc; - int i; + u32 *dc, *dm; dc = kmalloc_array(r->num_closid, sizeof(*d->ctrl_val), GFP_KERNEL); if (!dc) return -ENOMEM; - d->ctrl_val = dc; + dm = kmalloc_array(r->num_closid, sizeof(*d->mbps_val), GFP_KERNEL); + if (!dm) { + kfree(dc); + return -ENOMEM; + } - /* - * Initialize the Control MSRs to having no control. - * For Cache Allocation: Set all bits in cbm - * For Memory Allocation: Set b/w requested to 100 - */ - for (i = 0; i < r->num_closid; i++, dc++) - *dc = r->default_ctrl; + d->ctrl_val = dc; + d->mbps_val = dm; + setup_default_ctrlval(r, dc, dm); m.low = 0; m.high = r->num_closid; @@ -588,6 +611,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) } kfree(d->ctrl_val); + kfree(d->mbps_val); kfree(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 3fd7a70ee04a..39752825e376 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -28,6 +28,7 @@ #define MBM_CNTR_WIDTH 24 #define MBM_OVERFLOW_INTERVAL 1000 +#define MAX_MBA_BW 100u #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) @@ -180,10 +181,20 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes) * @prev_msr Value of IA32_QM_CTR for this RMID last time we read it + * @chunks_bw Total local data moved. Used for bandwidth calculation + * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting + * @prev_bw The most recent bandwidth in MBps + * @delta_bw Difference between the current and previous bandwidth + * @delta_comp Indicates whether to compute the delta_bw */ struct mbm_state { u64 chunks; u64 prev_msr; + u64 chunks_bw; + u64 prev_bw_msr; + u32 prev_bw; + u32 delta_bw; + bool delta_comp; }; /** @@ -202,6 +213,7 @@ struct mbm_state { * @cqm_work_cpu: * worker cpu for CQM h/w counters * @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID) + * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps * @new_ctrl: new ctrl value to be loaded * @have_new_ctrl: did user provide new_ctrl for this domain */ @@ -217,6 +229,7 @@ struct rdt_domain { int mbm_work_cpu; int cqm_work_cpu; u32 *ctrl_val; + u32 *mbps_val; u32 new_ctrl; bool have_new_ctrl; }; @@ -259,6 +272,7 @@ struct rdt_cache { * @min_bw: Minimum memory bandwidth percentage user can request * @bw_gran: Granularity at which the memory bandwidth is allocated * @delay_linear: True if memory B/W delay is in linear scale + * @mba_sc: True if MBA software controller(mba_sc) is enabled * @mb_map: Mapping of memory B/W percentage to memory B/W delay */ struct rdt_membw { @@ -266,6 +280,7 @@ struct rdt_membw { u32 min_bw; u32 bw_gran; u32 delay_linear; + bool mba_sc; u32 *mb_map; }; @@ -445,6 +460,9 @@ void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms); void mbm_handle_overflow(struct work_struct *work); +bool is_mba_sc(struct rdt_resource *r); +void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm); +u32 delay_bw_map(unsigned long bw, struct rdt_resource *r); void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 23e1d5c249c6..116d57b248d3 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -53,7 +53,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return false; } - if (bw < r->membw.min_bw || bw > r->default_ctrl) { + if ((bw < r->membw.min_bw || bw > r->default_ctrl) && + !is_mba_sc(r)) { rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, r->membw.min_bw, r->default_ctrl); return false; @@ -179,6 +180,8 @@ static int update_domains(struct rdt_resource *r, int closid) struct msr_param msr_param; cpumask_var_t cpu_mask; struct rdt_domain *d; + bool mba_sc; + u32 *dc; int cpu; if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) @@ -188,13 +191,20 @@ static int update_domains(struct rdt_resource *r, int closid) msr_param.high = msr_param.low + 1; msr_param.res = r; + mba_sc = is_mba_sc(r); list_for_each_entry(d, &r->domains, list) { - if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) { + dc = !mba_sc ? d->ctrl_val : d->mbps_val; + if (d->have_new_ctrl && d->new_ctrl != dc[closid]) { cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); - d->ctrl_val[closid] = d->new_ctrl; + dc[closid] = d->new_ctrl; } } - if (cpumask_empty(cpu_mask)) + + /* + * Avoid writing the control msr with control values when + * MBA software controller is enabled + */ + if (cpumask_empty(cpu_mask) || mba_sc) goto done; cpu = get_cpu(); /* Update CBM on this cpu if it's in cpu_mask. */ @@ -282,13 +292,17 @@ static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid) { struct rdt_domain *dom; bool sep = false; + u32 ctrl_val; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(dom, &r->domains, list) { if (sep) seq_puts(s, ";"); + + ctrl_val = (!is_mba_sc(r) ? dom->ctrl_val[closid] : + dom->mbps_val[closid]); seq_printf(s, r->format_str, dom->id, max_data_width, - dom->ctrl_val[closid]); + ctrl_val); sep = true; } seq_puts(s, "\n"); diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c index 681450eee428..b0f3aed76b75 100644 --- a/arch/x86/kernel/cpu/intel_rdt_monitor.c +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -225,10 +225,18 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } +static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr) +{ + u64 shift = 64 - MBM_CNTR_WIDTH, chunks; + + chunks = (cur_msr << shift) - (prev_msr << shift); + return chunks >>= shift; +} + static int __mon_event_count(u32 rmid, struct rmid_read *rr) { - u64 chunks, shift, tval; struct mbm_state *m; + u64 chunks, tval; tval = __rmid_read(rmid, rr->evtid); if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { @@ -254,14 +262,12 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) } if (rr->first) { - m->prev_msr = tval; - m->chunks = 0; + memset(m, 0, sizeof(struct mbm_state)); + m->prev_bw_msr = m->prev_msr = tval; return 0; } - shift = 64 - MBM_CNTR_WIDTH; - chunks = (tval << shift) - (m->prev_msr << shift); - chunks >>= shift; + chunks = mbm_overflow_count(m->prev_msr, tval); m->chunks += chunks; m->prev_msr = tval; @@ -270,6 +276,32 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) } /* + * Supporting function to calculate the memory bandwidth + * and delta bandwidth in MBps. + */ +static void mbm_bw_count(u32 rmid, struct rmid_read *rr) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; + struct mbm_state *m = &rr->d->mbm_local[rmid]; + u64 tval, cur_bw, chunks; + + tval = __rmid_read(rmid, rr->evtid); + if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + return; + + chunks = mbm_overflow_count(m->prev_bw_msr, tval); + m->chunks_bw += chunks; + m->chunks = m->chunks_bw; + cur_bw = (chunks * r->mon_scale) >> 20; + + if (m->delta_comp) + m->delta_bw = abs(cur_bw - m->prev_bw); + m->delta_comp = false; + m->prev_bw = cur_bw; + m->prev_bw_msr = tval; +} + +/* * This is called via IPI to read the CQM/MBM counters * on a domain. */ @@ -297,6 +329,118 @@ void mon_event_count(void *info) } } +/* + * Feedback loop for MBA software controller (mba_sc) + * + * mba_sc is a feedback loop where we periodically read MBM counters and + * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so + * that: + * + * current bandwdith(cur_bw) < user specified bandwidth(user_bw) + * + * This uses the MBM counters to measure the bandwidth and MBA throttle + * MSRs to control the bandwidth for a particular rdtgrp. It builds on the + * fact that resctrl rdtgroups have both monitoring and control. + * + * The frequency of the checks is 1s and we just tag along the MBM overflow + * timer. Having 1s interval makes the calculation of bandwidth simpler. + * + * Although MBA's goal is to restrict the bandwidth to a maximum, there may + * be a need to increase the bandwidth to avoid uncecessarily restricting + * the L2 <-> L3 traffic. + * + * Since MBA controls the L2 external bandwidth where as MBM measures the + * L3 external bandwidth the following sequence could lead to such a + * situation. + * + * Consider an rdtgroup which had high L3 <-> memory traffic in initial + * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but + * after some time rdtgroup has mostly L2 <-> L3 traffic. + * + * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its + * throttle MSRs already have low percentage values. To avoid + * unnecessarily restricting such rdtgroups, we also increase the bandwidth. + */ +static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) +{ + u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val; + struct mbm_state *pmbm_data, *cmbm_data; + u32 cur_bw, delta_bw, user_bw; + struct rdt_resource *r_mba; + struct rdt_domain *dom_mba; + struct list_head *head; + struct rdtgroup *entry; + + r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; + closid = rgrp->closid; + rmid = rgrp->mon.rmid; + pmbm_data = &dom_mbm->mbm_local[rmid]; + + dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); + if (!dom_mba) { + pr_warn_once("Failure to get domain for MBA update\n"); + return; + } + + cur_bw = pmbm_data->prev_bw; + user_bw = dom_mba->mbps_val[closid]; + delta_bw = pmbm_data->delta_bw; + cur_msr_val = dom_mba->ctrl_val[closid]; + + /* + * For Ctrl groups read data from child monitor groups. + */ + head = &rgrp->mon.crdtgrp_list; + list_for_each_entry(entry, head, mon.crdtgrp_list) { + cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cur_bw += cmbm_data->prev_bw; + delta_bw += cmbm_data->delta_bw; + } + + /* + * Scale up/down the bandwidth linearly for the ctrl group. The + * bandwidth step is the bandwidth granularity specified by the + * hardware. + * + * The delta_bw is used when increasing the bandwidth so that we + * dont alternately increase and decrease the control values + * continuously. + * + * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if + * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep + * switching between 90 and 110 continuously if we only check + * cur_bw < user_bw. + */ + if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { + new_msr_val = cur_msr_val - r_mba->membw.bw_gran; + } else if (cur_msr_val < MAX_MBA_BW && + (user_bw > (cur_bw + delta_bw))) { + new_msr_val = cur_msr_val + r_mba->membw.bw_gran; + } else { + return; + } + + cur_msr = r_mba->msr_base + closid; + wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba)); + dom_mba->ctrl_val[closid] = new_msr_val; + + /* + * Delta values are updated dynamically package wise for each + * rdtgrp everytime the throttle MSR changes value. + * + * This is because (1)the increase in bandwidth is not perfectly + * linear and only "approximately" linear even when the hardware + * says it is linear.(2)Also since MBA is a core specific + * mechanism, the delta values vary based on number of cores used + * by the rdtgrp. + */ + pmbm_data->delta_comp = true; + list_for_each_entry(entry, head, mon.crdtgrp_list) { + cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cmbm_data->delta_comp = true; + } +} + static void mbm_update(struct rdt_domain *d, int rmid) { struct rmid_read rr; @@ -314,7 +458,16 @@ static void mbm_update(struct rdt_domain *d, int rmid) } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; - __mon_event_count(rmid, &rr); + + /* + * Call the MBA software controller only for the + * control groups and when user has enabled + * the software controller explicitly. + */ + if (!is_mba_sc(NULL)) + __mon_event_count(rmid, &rr); + else + mbm_bw_count(rmid, &rr); } } @@ -385,6 +538,9 @@ void mbm_handle_overflow(struct work_struct *work) head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) mbm_update(d, crgrp->mon.rmid); + + if (is_mba_sc(NULL)) + update_mba_bw(prgrp, d); } schedule_delayed_work_on(cpu, &d->mbm_over, delay); diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index fca759d272a1..749856a2e736 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -1005,6 +1005,11 @@ static void l2_qos_cfg_update(void *arg) wrmsrl(IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL); } +static inline bool is_mba_linear(void) +{ + return rdt_resources_all[RDT_RESOURCE_MBA].membw.delay_linear; +} + static int set_cache_qos_cfg(int level, bool enable) { void (*update)(void *arg); @@ -1041,6 +1046,28 @@ static int set_cache_qos_cfg(int level, bool enable) return 0; } +/* + * Enable or disable the MBA software controller + * which helps user specify bandwidth in MBps. + * MBA software controller is supported only if + * MBM is supported and MBA is in linear scale. + */ +static int set_mba_sc(bool mba_sc) +{ + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA]; + struct rdt_domain *d; + + if (!is_mbm_enabled() || !is_mba_linear() || + mba_sc == is_mba_sc(r)) + return -EINVAL; + + r->membw.mba_sc = mba_sc; + list_for_each_entry(d, &r->domains, list) + setup_default_ctrlval(r, d->ctrl_val, d->mbps_val); + + return 0; +} + static int cdp_enable(int level, int data_type, int code_type) { struct rdt_resource *r_ldata = &rdt_resources_all[data_type]; @@ -1123,6 +1150,10 @@ static int parse_rdtgroupfs_options(char *data) ret = cdpl2_enable(); if (ret) goto out; + } else if (!strcmp(token, "mba_MBps")) { + ret = set_mba_sc(true); + if (ret) + goto out; } else { ret = -EINVAL; goto out; @@ -1445,6 +1476,8 @@ static void rdt_kill_sb(struct super_block *sb) cpus_read_lock(); mutex_lock(&rdtgroup_mutex); + set_mba_sc(false); + /*Put everything back to default values. */ for_each_alloc_enabled_rdt_resource(r) reset_all_ctrls(r); diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 475cb4f5f14f..c805a06e14c3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -48,7 +48,7 @@ static struct dentry *dfs_inj; static u8 n_banks; -#define MAX_FLAG_OPT_SIZE 3 +#define MAX_FLAG_OPT_SIZE 4 #define NBCFG 0x44 enum injection_type { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 42cf2880d0ed..cd76380af79f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1727,6 +1727,21 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) } } +static void mce_centaur_feature_init(struct cpuinfo_x86 *c) +{ + struct mca_config *cfg = &mca_cfg; + + /* + * All newer Centaur CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) || + c->x86 > 6) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } +} + static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) { switch (c->x86_vendor) { @@ -1739,6 +1754,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_amd_feature_init(c); break; } + case X86_VENDOR_CENTAUR: + mce_centaur_feature_init(c); + break; default: break; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index f7666eef4a87..f591b01930db 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -94,6 +94,11 @@ static struct smca_bank_name smca_names[] = { [SMCA_SMU] = { "smu", "System Management Unit" }, }; +static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init = +{ + [0 ... MAX_NR_BANKS - 1] = { [0 ... NR_BLOCKS - 1] = -1 } +}; + const char *smca_get_name(enum smca_bank_types t) { if (t >= N_SMCA_BANK_TYPES) @@ -431,8 +436,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) wrmsr(MSR_CU_DEF_ERR, low, high); } -static u32 smca_get_block_address(unsigned int cpu, unsigned int bank, - unsigned int block) +static u32 smca_get_block_address(unsigned int bank, unsigned int block) { u32 low, high; u32 addr = 0; @@ -443,24 +447,30 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank, if (!block) return MSR_AMD64_SMCA_MCx_MISC(bank); + /* Check our cache first: */ + if (smca_bank_addrs[bank][block] != -1) + return smca_bank_addrs[bank][block]; + /* * For SMCA enabled processors, BLKPTR field of the first MISC register * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4). */ - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) - return addr; + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + goto out; if (!(low & MCI_CONFIG_MCAX)) - return addr; + goto out; - if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && + if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && (low & MASK_BLKPTR_LO)) - return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); +out: + smca_bank_addrs[bank][block] = addr; return addr; } -static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high, +static u32 get_block_address(u32 current_addr, u32 low, u32 high, unsigned int bank, unsigned int block) { u32 addr = 0, offset = 0; @@ -468,20 +478,8 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS)) return addr; - /* Get address from already initialized block. */ - if (per_cpu(threshold_banks, cpu)) { - struct threshold_bank *bankp = per_cpu(threshold_banks, cpu)[bank]; - - if (bankp && bankp->blocks) { - struct threshold_block *blockp = &bankp->blocks[block]; - - if (blockp) - return blockp->address; - } - } - if (mce_flags.smca) - return smca_get_block_address(cpu, bank, block); + return smca_get_block_address(bank, block); /* Fall back to method we used for older processors: */ switch (block) { @@ -559,7 +557,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) smca_configure(bank, cpu); for (block = 0; block < NR_BLOCKS; ++block) { - address = get_block_address(cpu, address, low, high, bank, block); + address = get_block_address(address, low, high, bank, block); if (!address) break; @@ -1176,7 +1174,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, if (err) goto out_free; recurse: - address = get_block_address(cpu, address, low, high, bank, ++block); + address = get_block_address(address, low, high, bank, ++block); if (!address) return 0; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 10c4fc2c91f8..77e201301528 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -564,14 +564,12 @@ static int __reload_late(void *info) apply_microcode_local(&err); spin_unlock(&update_lock); + /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - return -1; - /* siblings return UCODE_OK because their engine got updated already */ + ret = -1; } else if (err == UCODE_UPDATED || err == UCODE_OK) { ret = 1; - } else { - return ret; } /* diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 32b8e5724f96..1c2cfa0644aa 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -485,7 +485,6 @@ static void show_saved_mc(void) */ static void save_mc_for_early(u8 *mc, unsigned int size) { -#ifdef CONFIG_HOTPLUG_CPU /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); @@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size) show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); -#endif } static bool load_builtin_intel_microcode(struct cpio_data *cp) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 4488cf0dd499..031082c96db8 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -22,7 +22,7 @@ #include <linux/kexec.h> #include <asm/processor.h> #include <asm/hypervisor.h> -#include <asm/hyperv.h> +#include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/desc.h> #include <asm/irq_regs.h> @@ -216,8 +216,8 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); - ms_hyperv.max_vp_index = cpuid_eax(HVCPUID_IMPLEMENTATION_LIMITS); - ms_hyperv.max_lp_index = cpuid_ebx(HVCPUID_IMPLEMENTATION_LIMITS); + ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); + ms_hyperv.max_lp_index = cpuid_ebx(HYPERV_CPUID_IMPLEMENT_LIMITS); pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); @@ -225,11 +225,12 @@ static void __init ms_hyperv_init_platform(void) /* * Extract host information. */ - if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) { - hv_host_info_eax = cpuid_eax(HVCPUID_VERSION); - hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION); - hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION); - hv_host_info_edx = cpuid_edx(HVCPUID_VERSION); + if (cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS) >= + HYPERV_CPUID_VERSION) { + hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION); + hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION); + hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION); + hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION); pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n", hv_host_info_eax, hv_host_info_ebx >> 16, @@ -243,6 +244,11 @@ static void __init ms_hyperv_init_platform(void) x86_platform.calibrate_cpu = hv_get_tsc_khz; } + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) { + ms_hyperv.nested_features = + cpuid_eax(HYPERV_CPUID_NESTED_FEATURES); + } + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { diff --git a/arch/x86/kernel/cpu/mtrr/Makefile b/arch/x86/kernel/cpu/mtrr/Makefile index ad9e5ed81181..2ad9107ee980 100644 --- a/arch/x86/kernel/cpu/mtrr/Makefile +++ b/arch/x86/kernel/cpu/mtrr/Makefile @@ -1,3 +1,3 @@ -obj-y := main.o if.o generic.o cleanup.o +obj-y := mtrr.o if.o generic.o cleanup.o obj-$(CONFIG_X86_32) += amd.o cyrix.o centaur.o diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 7468de429087..9a19c800fe40 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -46,6 +46,7 @@ #include <linux/pci.h> #include <linux/smp.h> #include <linux/syscore_ops.h> +#include <linux/rcupdate.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> @@ -100,7 +101,7 @@ static int have_wrcomb(void) if (dev->vendor == PCI_VENDOR_ID_SERVERWORKS && dev->device == PCI_DEVICE_ID_SERVERWORKS_LE && dev->revision <= 5) { - pr_info("mtrr: Serverworks LE rev < 6 detected. Write-combining disabled.\n"); + pr_info("Serverworks LE rev < 6 detected. Write-combining disabled.\n"); pci_dev_put(dev); return 0; } @@ -110,7 +111,7 @@ static int have_wrcomb(void) */ if (dev->vendor == PCI_VENDOR_ID_INTEL && dev->device == PCI_DEVICE_ID_INTEL_82451NX) { - pr_info("mtrr: Intel 450NX MMC detected. Write-combining disabled.\n"); + pr_info("Intel 450NX MMC detected. Write-combining disabled.\n"); pci_dev_put(dev); return 0; } @@ -312,24 +313,24 @@ int mtrr_add_page(unsigned long base, unsigned long size, return error; if (type >= MTRR_NUM_TYPES) { - pr_warn("mtrr: type: %u invalid\n", type); + pr_warn("type: %u invalid\n", type); return -EINVAL; } /* If the type is WC, check that this processor supports it */ if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) { - pr_warn("mtrr: your processor doesn't support write-combining\n"); + pr_warn("your processor doesn't support write-combining\n"); return -ENOSYS; } if (!size) { - pr_warn("mtrr: zero sized request\n"); + pr_warn("zero sized request\n"); return -EINVAL; } if ((base | (base + size - 1)) >> (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { - pr_warn("mtrr: base or size exceeds the MTRR width\n"); + pr_warn("base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -360,8 +361,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, } else if (types_compatible(type, ltype)) continue; } - pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing" - " 0x%lx000,0x%lx000\n", base, size, lbase, + pr_warn("0x%lx000,0x%lx000 overlaps existing 0x%lx000,0x%lx000\n", base, size, lbase, lsize); goto out; } @@ -369,7 +369,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (ltype != type) { if (types_compatible(type, ltype)) continue; - pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", + pr_warn("type mismatch for %lx000,%lx000 old: %s new: %s\n", base, size, mtrr_attrib_to_str(ltype), mtrr_attrib_to_str(type)); goto out; @@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, } } } else { - pr_info("mtrr: no more MTRRs available\n"); + pr_info("no more MTRRs available\n"); } error = i; out: @@ -407,8 +407,8 @@ int mtrr_add_page(unsigned long base, unsigned long size, static int mtrr_check(unsigned long base, unsigned long size) { if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { - pr_warn("mtrr: size and base must be multiples of 4 kiB\n"); - pr_debug("mtrr: size: 0x%lx base: 0x%lx\n", size, base); + pr_warn("size and base must be multiples of 4 kiB\n"); + pr_debug("size: 0x%lx base: 0x%lx\n", size, base); dump_stack(); return -1; } @@ -499,22 +499,22 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) } } if (reg < 0) { - pr_debug("mtrr: no MTRR for %lx000,%lx000 found\n", + pr_debug("no MTRR for %lx000,%lx000 found\n", base, size); goto out; } } if (reg >= max) { - pr_warn("mtrr: register: %d too big\n", reg); + pr_warn("register: %d too big\n", reg); goto out; } mtrr_if->get(reg, &lbase, &lsize, <ype); if (lsize < 1) { - pr_warn("mtrr: MTRR %d not used\n", reg); + pr_warn("MTRR %d not used\n", reg); goto out; } if (mtrr_usage_table[reg] < 1) { - pr_warn("mtrr: reg: %d has count=0\n", reg); + pr_warn("reg: %d has count=0\n", reg); goto out; } if (--mtrr_usage_table[reg] < 1) @@ -775,7 +775,7 @@ void __init mtrr_bp_init(void) } if (!mtrr_enabled()) { - pr_info("MTRR: Disabled\n"); + pr_info("Disabled\n"); /* * PAT initialization relies on MTRR's rendezvous handler. @@ -793,6 +793,9 @@ void mtrr_ap_init(void) if (!use_intel() || mtrr_aps_delayed_init) return; + + rcu_cpu_starting(smp_processor_id()); + /* * Ideally we should hold mtrr_mutex here to avoid mtrr entries * changed, but this routine will be called in cpu boot time, diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index b099024d339c..81c0afb39d0a 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -27,7 +27,7 @@ * exists, use it for populating initial_apicid and cpu topology * detection. */ -void detect_extended_topology(struct cpuinfo_x86 *c) +int detect_extended_topology(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP unsigned int eax, ebx, ecx, edx, sub_index; @@ -36,7 +36,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c) static bool printed; if (c->cpuid_level < 0xb) - return; + return -1; cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); @@ -44,7 +44,7 @@ void detect_extended_topology(struct cpuinfo_x86 *c) * check if the cpuid leaf 0xb is actually implemented. */ if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) - return; + return -1; set_cpu_cap(c, X86_FEATURE_XTOPOLOGY); @@ -95,6 +95,6 @@ void detect_extended_topology(struct cpuinfo_x86 *c) c->cpu_core_id); printed = 1; } - return; #endif + return 0; } diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 1f6680427ff0..f631a3f15587 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -38,37 +38,6 @@ #include <asm/virtext.h> #include <asm/intel_pt.h> -/* Alignment required for elf header segment */ -#define ELF_CORE_HEADER_ALIGN 4096 - -/* This primarily represents number of split ranges due to exclusion */ -#define CRASH_MAX_RANGES 16 - -struct crash_mem_range { - u64 start, end; -}; - -struct crash_mem { - unsigned int nr_ranges; - struct crash_mem_range ranges[CRASH_MAX_RANGES]; -}; - -/* Misc data about ram ranges needed to prepare elf headers */ -struct crash_elf_data { - struct kimage *image; - /* - * Total number of ram ranges we have after various adjustments for - * crash reserved region, etc. - */ - unsigned int max_nr_ranges; - - /* Pointer to elf header */ - void *ehdr; - /* Pointer to next phdr */ - void *bufp; - struct crash_mem mem; -}; - /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { struct boot_params *params; @@ -218,124 +187,49 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) return 0; } - /* Gather all the required information to prepare elf headers for ram regions */ -static void fill_up_crash_elf_data(struct crash_elf_data *ced, - struct kimage *image) +static struct crash_mem *fill_up_crash_elf_data(void) { unsigned int nr_ranges = 0; - - ced->image = image; + struct crash_mem *cmem; walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + if (!nr_ranges) + return NULL; - ced->max_nr_ranges = nr_ranges; - - /* Exclusion of crash region could split memory ranges */ - ced->max_nr_ranges++; - - /* If crashk_low_res is not 0, another range split possible */ - if (crashk_low_res.end) - ced->max_nr_ranges++; -} - -static int exclude_mem_range(struct crash_mem *mem, - unsigned long long mstart, unsigned long long mend) -{ - int i, j; - unsigned long long start, end; - struct crash_mem_range temp_range = {0, 0}; - - for (i = 0; i < mem->nr_ranges; i++) { - start = mem->ranges[i].start; - end = mem->ranges[i].end; - - if (mstart > end || mend < start) - continue; - - /* Truncate any area outside of range */ - if (mstart < start) - mstart = start; - if (mend > end) - mend = end; - - /* Found completely overlapping range */ - if (mstart == start && mend == end) { - mem->ranges[i].start = 0; - mem->ranges[i].end = 0; - if (i < mem->nr_ranges - 1) { - /* Shift rest of the ranges to left */ - for (j = i; j < mem->nr_ranges - 1; j++) { - mem->ranges[j].start = - mem->ranges[j+1].start; - mem->ranges[j].end = - mem->ranges[j+1].end; - } - } - mem->nr_ranges--; - return 0; - } - - if (mstart > start && mend < end) { - /* Split original range */ - mem->ranges[i].end = mstart - 1; - temp_range.start = mend + 1; - temp_range.end = end; - } else if (mstart != start) - mem->ranges[i].end = mstart - 1; - else - mem->ranges[i].start = mend + 1; - break; - } + /* + * Exclusion of crash region and/or crashk_low_res may cause + * another range split. So add extra two slots here. + */ + nr_ranges += 2; + cmem = vzalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges); + if (!cmem) + return NULL; - /* If a split happend, add the split to array */ - if (!temp_range.end) - return 0; + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; - /* Split happened */ - if (i == CRASH_MAX_RANGES - 1) { - pr_err("Too many crash ranges after split\n"); - return -ENOMEM; - } - - /* Location where new range should go */ - j = i + 1; - if (j < mem->nr_ranges) { - /* Move over all ranges one slot towards the end */ - for (i = mem->nr_ranges - 1; i >= j; i--) - mem->ranges[i + 1] = mem->ranges[i]; - } - - mem->ranges[j].start = temp_range.start; - mem->ranges[j].end = temp_range.end; - mem->nr_ranges++; - return 0; + return cmem; } /* * Look for any unwanted ranges between mstart, mend and remove them. This - * might lead to split and split ranges are put in ced->mem.ranges[] array + * might lead to split and split ranges are put in cmem->ranges[] array */ -static int elf_header_exclude_ranges(struct crash_elf_data *ced, - unsigned long long mstart, unsigned long long mend) +static int elf_header_exclude_ranges(struct crash_mem *cmem) { - struct crash_mem *cmem = &ced->mem; int ret = 0; - memset(cmem->ranges, 0, sizeof(cmem->ranges)); - - cmem->ranges[0].start = mstart; - cmem->ranges[0].end = mend; - cmem->nr_ranges = 1; - /* Exclude crashkernel region */ - ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) { - ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, + crashk_low_res.end); if (ret) return ret; } @@ -345,144 +239,12 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { - struct crash_elf_data *ced = arg; - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - unsigned long mstart, mend; - struct kimage *image = ced->image; - struct crash_mem *cmem; - int ret, i; - - ehdr = ced->ehdr; - - /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(ced, res->start, res->end); - if (ret) - return ret; - - /* Go through all the ranges in ced->mem.ranges[] and prepare phdr */ - cmem = &ced->mem; - - for (i = 0; i < cmem->nr_ranges; i++) { - mstart = cmem->ranges[i].start; - mend = cmem->ranges[i].end; - - phdr = ced->bufp; - ced->bufp += sizeof(Elf64_Phdr); - - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_offset = mstart; - - /* - * If a range matches backup region, adjust offset to backup - * segment. - */ - if (mstart == image->arch.backup_src_start && - (mend - mstart + 1) == image->arch.backup_src_sz) - phdr->p_offset = image->arch.backup_load_addr; - - phdr->p_paddr = mstart; - phdr->p_vaddr = (unsigned long long) __va(mstart); - phdr->p_filesz = phdr->p_memsz = mend - mstart + 1; - phdr->p_align = 0; - ehdr->e_phnum++; - pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n", - phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz, - ehdr->e_phnum, phdr->p_offset); - } - - return ret; -} - -static int prepare_elf64_headers(struct crash_elf_data *ced, - void **addr, unsigned long *sz) -{ - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz; - unsigned char *buf, *bufp; - unsigned int cpu; - unsigned long long notes_addr; - int ret; + struct crash_mem *cmem = arg; - /* extra phdr for vmcoreinfo elf note */ - nr_phdr = nr_cpus + 1; - nr_phdr += ced->max_nr_ranges; - - /* - * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping - * area on x86_64 (ffffffff80000000 - ffffffffa0000000). - * I think this is required by tools like gdb. So same physical - * memory will be mapped in two elf headers. One will contain kernel - * text virtual addresses and other will have __va(physical) addresses. - */ + cmem->ranges[cmem->nr_ranges].start = res->start; + cmem->ranges[cmem->nr_ranges].end = res->end; + cmem->nr_ranges++; - nr_phdr++; - elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr); - elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN); - - buf = vzalloc(elf_sz); - if (!buf) - return -ENOMEM; - - bufp = buf; - ehdr = (Elf64_Ehdr *)bufp; - bufp += sizeof(Elf64_Ehdr); - memcpy(ehdr->e_ident, ELFMAG, SELFMAG); - ehdr->e_ident[EI_CLASS] = ELFCLASS64; - ehdr->e_ident[EI_DATA] = ELFDATA2LSB; - ehdr->e_ident[EI_VERSION] = EV_CURRENT; - ehdr->e_ident[EI_OSABI] = ELF_OSABI; - memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); - ehdr->e_type = ET_CORE; - ehdr->e_machine = ELF_ARCH; - ehdr->e_version = EV_CURRENT; - ehdr->e_phoff = sizeof(Elf64_Ehdr); - ehdr->e_ehsize = sizeof(Elf64_Ehdr); - ehdr->e_phentsize = sizeof(Elf64_Phdr); - - /* Prepare one phdr of type PT_NOTE for each present cpu */ - for_each_present_cpu(cpu) { - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_NOTE; - notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu)); - phdr->p_offset = phdr->p_paddr = notes_addr; - phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t); - (ehdr->e_phnum)++; - } - - /* Prepare one PT_NOTE header for vmcoreinfo */ - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_NOTE; - phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); - phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; - (ehdr->e_phnum)++; - -#ifdef CONFIG_X86_64 - /* Prepare PT_LOAD type program header for kernel text region */ - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_vaddr = (Elf64_Addr)_text; - phdr->p_filesz = phdr->p_memsz = _end - _text; - phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); - (ehdr->e_phnum)++; -#endif - - /* Prepare PT_LOAD headers for system ram chunks. */ - ced->ehdr = ehdr; - ced->bufp = bufp; - ret = walk_system_ram_res(0, -1, ced, - prepare_elf64_ram_headers_callback); - if (ret < 0) - return ret; - - *addr = buf; - *sz = elf_sz; return 0; } @@ -490,18 +252,46 @@ static int prepare_elf64_headers(struct crash_elf_data *ced, static int prepare_elf_headers(struct kimage *image, void **addr, unsigned long *sz) { - struct crash_elf_data *ced; - int ret; + struct crash_mem *cmem; + Elf64_Ehdr *ehdr; + Elf64_Phdr *phdr; + int ret, i; - ced = kzalloc(sizeof(*ced), GFP_KERNEL); - if (!ced) + cmem = fill_up_crash_elf_data(); + if (!cmem) return -ENOMEM; - fill_up_crash_elf_data(ced, image); + ret = walk_system_ram_res(0, -1, cmem, + prepare_elf64_ram_headers_callback); + if (ret) + goto out; + + /* Exclude unwanted mem ranges */ + ret = elf_header_exclude_ranges(cmem); + if (ret) + goto out; /* By default prepare 64bit headers */ - ret = prepare_elf64_headers(ced, addr, sz); - kfree(ced); + ret = crash_prepare_elf64_headers(cmem, + IS_ENABLED(CONFIG_X86_64), addr, sz); + if (ret) + goto out; + + /* + * If a range matches backup region, adjust offset to backup + * segment. + */ + ehdr = (Elf64_Ehdr *)*addr; + phdr = (Elf64_Phdr *)(ehdr + 1); + for (i = 0; i < ehdr->e_phnum; phdr++, i++) + if (phdr->p_type == PT_LOAD && + phdr->p_paddr == image->arch.backup_src_start && + phdr->p_memsz == image->arch.backup_src_sz) { + phdr->p_offset = image->arch.backup_load_addr; + break; + } +out: + vfree(cmem); return ret; } @@ -547,14 +337,14 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, /* Exclude Backup region */ start = image->arch.backup_load_addr; end = start + image->arch.backup_src_sz - 1; - ret = exclude_mem_range(cmem, start, end); + ret = crash_exclude_mem_range(cmem, start, end); if (ret) return ret; /* Exclude elf header region */ start = image->arch.elf_load_addr; end = start + image->arch.elf_headers_sz - 1; - return exclude_mem_range(cmem, start, end); + return crash_exclude_mem_range(cmem, start, end); } /* Prepare memory map for crash dump kernel */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 18fa9d74c182..666a284116ac 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -22,11 +22,14 @@ #include <asm/stacktrace.h> #include <asm/unwind.h> +#define OPCODE_BUFSIZE 64 + int panic_on_unrecovered_nmi; int panic_on_io_nmi; -static unsigned int code_bytes = 64; static int die_counter; +static struct pt_regs exec_summary_regs; + bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info) { @@ -69,9 +72,62 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +/* + * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus: + * + * In case where we don't have the exact kernel image (which, if we did, we can + * simply disassemble and navigate to the RIP), the purpose of the bigger + * prologue is to have more context and to be able to correlate the code from + * the different toolchains better. + * + * In addition, it helps in recreating the register allocation of the failing + * kernel and thus make sense of the register dump. + * + * What is more, the additional complication of a variable length insn arch like + * x86 warrants having longer byte sequence before rIP so that the disassembler + * can "sync" up properly and find instruction boundaries when decoding the + * opcode bytes. + * + * Thus, the 2/3rds prologue and 64 byte OPCODE_BUFSIZE is just a random + * guesstimate in attempt to achieve all of the above. + */ +void show_opcodes(u8 *rip, const char *loglvl) +{ + unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3; + u8 opcodes[OPCODE_BUFSIZE]; + u8 *ip; + int i; + + printk("%sCode: ", loglvl); + + ip = (u8 *)rip - code_prologue; + if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) { + pr_cont("Bad RIP value.\n"); + return; + } + + for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) { + if (ip == rip) + pr_cont("<%02x> ", opcodes[i]); + else + pr_cont("%02x ", opcodes[i]); + } + pr_cont("\n"); +} + +void show_ip(struct pt_regs *regs, const char *loglvl) +{ +#ifdef CONFIG_X86_32 + printk("%sEIP: %pS\n", loglvl, (void *)regs->ip); +#else + printk("%sRIP: %04x:%pS\n", loglvl, (int)regs->cs, (void *)regs->ip); +#endif + show_opcodes((u8 *)regs->ip, loglvl); +} + void show_iret_regs(struct pt_regs *regs) { - printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip); + show_ip(regs, KERN_DEFAULT); printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss, regs->sp, regs->flags); } @@ -267,7 +323,6 @@ unsigned long oops_begin(void) bust_spinlocks(1); return flags; } -EXPORT_SYMBOL_GPL(oops_begin); NOKPROBE_SYMBOL(oops_begin); void __noreturn rewind_stack_do_exit(int signr); @@ -287,6 +342,9 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) raw_local_irq_restore(flags); oops_exit(); + /* Executive summary in case the oops scrolled away */ + __show_regs(&exec_summary_regs, true); + if (!signr) return; if (in_interrupt()) @@ -305,10 +363,10 @@ NOKPROBE_SYMBOL(oops_end); int __die(const char *str, struct pt_regs *regs, long err) { -#ifdef CONFIG_X86_32 - unsigned short ss; - unsigned long sp; -#endif + /* Save the regs of the first oops for the executive summary later. */ + if (!die_counter) + exec_summary_regs = *regs; + printk(KERN_DEFAULT "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter, IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", @@ -318,26 +376,13 @@ int __die(const char *str, struct pt_regs *regs, long err) IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); + show_regs(regs); + print_modules(); + if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) return 1; - print_modules(); - show_regs(regs); -#ifdef CONFIG_X86_32 - if (user_mode(regs)) { - sp = regs->sp; - ss = regs->ss; - } else { - sp = kernel_stack_pointer(regs); - savesegment(ss, ss); - } - printk(KERN_EMERG "EIP: %pS SS:ESP: %04x:%08lx\n", - (void *)regs->ip, ss, sp); -#else - /* Executive summary in case the oops scrolled away */ - printk(KERN_ALERT "RIP: %pS RSP: %016lx\n", (void *)regs->ip, regs->sp); -#endif return 0; } NOKPROBE_SYMBOL(__die); @@ -356,30 +401,9 @@ void die(const char *str, struct pt_regs *regs, long err) oops_end(flags, regs, sig); } -static int __init code_bytes_setup(char *s) -{ - ssize_t ret; - unsigned long val; - - if (!s) - return -EINVAL; - - ret = kstrtoul(s, 0, &val); - if (ret) - return ret; - - code_bytes = val; - if (code_bytes > 8192) - code_bytes = 8192; - - return 1; -} -__setup("code_bytes=", code_bytes_setup); - void show_regs(struct pt_regs *regs) { bool all = true; - int i; show_regs_print_info(KERN_DEFAULT); @@ -389,36 +413,8 @@ void show_regs(struct pt_regs *regs) __show_regs(regs, all); /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. + * When in-kernel, we also print out the stack at the time of the fault.. */ - if (!user_mode(regs)) { - unsigned int code_prologue = code_bytes * 43 / 64; - unsigned int code_len = code_bytes; - unsigned char c; - u8 *ip; - + if (!user_mode(regs)) show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT); - - printk(KERN_DEFAULT "Code: "); - - ip = (u8 *)regs->ip - code_prologue; - if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - /* try starting at IP */ - ip = (u8 *)regs->ip; - code_len = code_len - code_prologue + 1; - } - for (i = 0; i < code_len; i++, ip++) { - if (ip < (u8 *)PAGE_OFFSET || - probe_kernel_address(ip, c)) { - pr_cont(" Bad RIP value."); - break; - } - if (ip == (u8 *)regs->ip) - pr_cont("<%02x> ", c); - else - pr_cont("%02x ", c); - } - } - pr_cont("\n"); } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 6a2cb1442e05..d1f25c831447 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -155,7 +155,8 @@ static void __init __e820__range_add(struct e820_table *table, u64 start, u64 si int x = table->nr_entries; if (x >= ARRAY_SIZE(table->entries)) { - pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1); + pr_err("too many entries; ignoring [mem %#010llx-%#010llx]\n", + start, start + size - 1); return; } @@ -190,9 +191,10 @@ void __init e820__print_table(char *who) int i; for (i = 0; i < e820_table->nr_entries; i++) { - pr_info("%s: [mem %#018Lx-%#018Lx] ", who, - e820_table->entries[i].addr, - e820_table->entries[i].addr + e820_table->entries[i].size - 1); + pr_info("%s: [mem %#018Lx-%#018Lx] ", + who, + e820_table->entries[i].addr, + e820_table->entries[i].addr + e820_table->entries[i].size - 1); e820_print_type(e820_table->entries[i].type); pr_cont("\n"); @@ -574,7 +576,7 @@ void __init e820__update_table_print(void) if (e820__update_table(e820_table)) return; - pr_info("e820: modified physical RAM map:\n"); + pr_info("modified physical RAM map:\n"); e820__print_table("modified"); } @@ -636,9 +638,8 @@ __init void e820__setup_pci_gap(void) if (!found) { #ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; - pr_err( - "e820: Cannot find an available gap in the 32-bit address range\n" - "e820: PCI devices with unassigned 32-bit BARs may not work!\n"); + pr_err("Cannot find an available gap in the 32-bit address range\n"); + pr_err("PCI devices with unassigned 32-bit BARs may not work!\n"); #else gapstart = 0x10000000; #endif @@ -649,7 +650,8 @@ __init void e820__setup_pci_gap(void) */ pci_mem_start = gapstart; - pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1); + pr_info("[mem %#010lx-%#010lx] available for PCI devices\n", + gapstart, gapstart + gapsize - 1); } /* @@ -711,7 +713,7 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len) memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); early_memunmap(sdata, data_len); - pr_info("e820: extended physical RAM map:\n"); + pr_info("extended physical RAM map:\n"); e820__print_table("extended"); } @@ -780,7 +782,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); if (addr) { e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); - pr_info("e820: update e820_table_kexec for e820__memblock_alloc_reserved()\n"); + pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); e820__update_table_kexec(); } @@ -830,8 +832,8 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type if (last_pfn > max_arch_pfn) last_pfn = max_arch_pfn; - pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n", - last_pfn, max_arch_pfn); + pr_info("last_pfn = %#lx max_arch_pfn = %#lx\n", + last_pfn, max_arch_pfn); return last_pfn; } @@ -1005,7 +1007,7 @@ void __init e820__finish_early_params(void) if (e820__update_table(e820_table) < 0) early_panic("Invalid user supplied memory map"); - pr_info("e820: user-defined physical RAM map:\n"); + pr_info("user-defined physical RAM map:\n"); e820__print_table("user"); } } @@ -1238,7 +1240,7 @@ void __init e820__memory_setup(void) memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec)); memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); - pr_info("e820: BIOS-provided physical RAM map:\n"); + pr_info("BIOS-provided physical RAM map:\n"); e820__print_table(who); } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bae0d32e327b..da5d8ac60062 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -28,8 +28,6 @@ #include <asm/irq_remapping.h> #include <asm/early_ioremap.h> -#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) - static void __init fix_hypertransport_config(int num, int slot, int func) { u32 htcfg; @@ -617,7 +615,8 @@ static void __init apple_airport_reset(int bus, int slot, int func) pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { - dev_err("Cannot power up Apple AirPort card\n"); + pr_err("pci 0000:%02x:%02x.%d: Cannot power up Apple AirPort card\n", + bus, slot, func); return; } } @@ -628,7 +627,8 @@ static void __init apple_airport_reset(int bus, int slot, int func) mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); if (!mmio) { - dev_err("Cannot iomap Apple AirPort card\n"); + pr_err("pci 0000:%02x:%02x.%d: Cannot iomap Apple AirPort card\n", + bus, slot, func); return; } diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index e5ec3cafa72e..aebd0d5bc086 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -195,6 +195,10 @@ void init_espfix_ap(int cpu) pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); + /* + * __PAGE_KERNEL_* includes _PAGE_GLOBAL, which we want since + * this is mapped to userspace. + */ pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 0c855deee165..a21d6ace648e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -6,6 +6,10 @@ */ #define DISABLE_BRANCH_PROFILING + +/* cpu_feature_enabled() cannot be used this early */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/init.h> #include <linux/linkage.h> #include <linux/types.h> @@ -32,11 +36,6 @@ #include <asm/microcode.h> #include <asm/kasan.h> -#ifdef CONFIG_X86_5LEVEL -#undef pgtable_l5_enabled -#define pgtable_l5_enabled __pgtable_l5_enabled -#endif - /* * Manage page tables very early on. */ @@ -45,8 +44,7 @@ static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); #ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled __ro_after_init; -EXPORT_SYMBOL(__pgtable_l5_enabled); +unsigned int __pgtable_l5_enabled __initdata; unsigned int pgdir_shift __ro_after_init = 39; EXPORT_SYMBOL(pgdir_shift); unsigned int ptrs_per_p4d __ro_after_init = 1; @@ -82,13 +80,14 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr) static bool __head check_la57_support(unsigned long physaddr) { - if (native_cpuid_eax(0) < 7) - return false; - - if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) + /* + * 5-level paging is detected and enabled at kernel decomression + * stage. Only check if it has been enabled there. + */ + if (!(native_read_cr4() & X86_CR4_LA57)) return false; - *fixup_int(&pgtable_l5_enabled, physaddr) = 1; + *fixup_int(&__pgtable_l5_enabled, physaddr) = 1; *fixup_int(&pgdir_shift, physaddr) = 48; *fixup_int(&ptrs_per_p4d, physaddr) = 512; *fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5; @@ -104,6 +103,12 @@ static bool __head check_la57_support(unsigned long physaddr) } #endif +/* Code in __startup_64() can be relocated during execution, but the compiler + * doesn't have to generate PC-relative relocations when accessing globals from + * that function. Clang actually does not generate them, which leads to + * boot-time crashes. To work around this problem, every global pointer must + * be adjusted using fixup_pointer(). + */ unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { @@ -113,6 +118,7 @@ unsigned long __head __startup_64(unsigned long physaddr, p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; + pteval_t *mask_ptr; bool la57; int i; unsigned int *next_pgt_ptr; @@ -195,6 +201,9 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[i + 1] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + /* Filter out unsupported __PAGE_KERNEL_* bits: */ + mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr); + pmd_entry &= *mask_ptr; pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; @@ -271,7 +280,7 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (!pgtable_l5_enabled) + if (!pgtable_l5_enabled()) p4d_p = pgd_p; else if (pgd) p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 48385c1074a5..8344dd2f310a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -399,8 +399,13 @@ NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .fill 511, 8, 0 NEXT_PAGE(level2_ident_pgt) - /* Since I easily can, map the first 1G. + /* + * Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. + * + * Note: This sets _PAGE_GLOBAL despite whether + * the CPU supports it or it is enabled. But, + * the CPU should ignore the bit. */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #else @@ -431,6 +436,10 @@ NEXT_PAGE(level2_kernel_pgt) * (NOTE: at +512MB starts the module area, see MODULES_VADDR. * If you want to increase this then increase MODULES_VADDR * too.) + * + * This table is eventually used by the kernel during normal + * runtime. Care must be taken to clear out undesired bits + * later, like _PAGE_RW or _PAGE_GLOBAL in some cases. */ PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 8ce4212e2b8d..b6be34ee88e9 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -975,8 +975,7 @@ int __init hpet_enable(void) cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY); hpet_writel(cfg, HPET_CFG); if (cfg) - pr_warn("HPET: Unrecognized bits %#x set in global cfg\n", - cfg); + pr_warn("Unrecognized bits %#x set in global cfg\n", cfg); for (i = 0; i <= last; ++i) { cfg = hpet_readl(HPET_Tn_CFG(i)); @@ -988,7 +987,7 @@ int __init hpet_enable(void) | HPET_TN_64BIT_CAP | HPET_TN_32BIT | HPET_TN_ROUTE | HPET_TN_FSB | HPET_TN_FSB_CAP); if (cfg) - pr_warn("HPET: Unrecognized bits %#x set in cfg#%u\n", + pr_warn("Unrecognized bits %#x set in cfg#%u\n", cfg, i); } hpet_print_config(); diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index fa183a131edc..108c48d0d40e 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL2.0 +// SPDX-License-Identifier: GPL-2.0 /* * Jailhouse paravirt_ops implementation * @@ -37,7 +37,7 @@ static uint32_t __init jailhouse_detect(void) return jailhouse_cpuid_base(); } -static void jailhouse_get_wallclock(struct timespec *now) +static void jailhouse_get_wallclock(struct timespec64 *now) { memset(now, 0, sizeof(*now)); } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index fb095ba0c02f..7326078eaa7a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -334,7 +334,6 @@ static void *bzImage64_load(struct kimage *image, char *kernel, unsigned long setup_header_size, params_cmdline_sz; struct boot_params *params; unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr; - unsigned long purgatory_load_addr; struct bzimage64_data *ldata; struct kexec_entry64_regs regs64; void *stack; @@ -342,6 +341,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset; struct kexec_buf kbuf = { .image = image, .buf_max = ULONG_MAX, .top_down = true }; + struct kexec_buf pbuf = { .image = image, .buf_min = MIN_PURGATORY_ADDR, + .buf_max = ULONG_MAX, .top_down = true }; header = (struct setup_header *)(kernel + setup_hdr_offset); setup_sects = header->setup_sects; @@ -379,14 +380,13 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * Load purgatory. For 64bit entry point, purgatory code can be * anywhere. */ - ret = kexec_load_purgatory(image, MIN_PURGATORY_ADDR, ULONG_MAX, 1, - &purgatory_load_addr); + ret = kexec_load_purgatory(image, &pbuf); if (ret) { pr_err("Loading purgatory failed\n"); return ERR_PTR(ret); } - pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); /* @@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * little bit simple */ efi_map_sz = efi_get_runtime_map_size(); - efi_map_sz = ALIGN(efi_map_sz, 16); params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + MAX_ELFCOREHDR_STR_LEN; params_cmdline_sz = ALIGN(params_cmdline_sz, 16); - kbuf.bufsz = params_cmdline_sz + efi_map_sz + + kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) + sizeof(struct setup_data) + sizeof(struct efi_setup_data); @@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, if (!params) return ERR_PTR(-ENOMEM); efi_map_offset = params_cmdline_sz; - efi_setup_data_offset = efi_map_offset + efi_map_sz; + efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16); /* Copy setup header onto bootparams. Documentation/x86/boot.txt */ setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset; @@ -538,7 +537,7 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) } #endif -struct kexec_file_ops kexec_bzImage64_ops = { +const struct kexec_file_ops kexec_bzImage64_ops = { .probe = bzImage64_probe, .load = bzImage64_load, .cleanup = bzImage64_cleanup, diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 0715f827607c..6f4d42377fe5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(insn)) + return 0; + #ifdef CONFIG_X86_64 /* Only x86_64 has RIP relative instructions */ if (insn_rip_relative(insn)) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index fae86e36e399..5b2300b818af 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -454,6 +454,13 @@ static void __init sev_map_percpu_data(void) } #ifdef CONFIG_SMP +static void __init kvm_smp_prepare_cpus(unsigned int max_cpus) +{ + native_smp_prepare_cpus(max_cpus); + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) + static_branch_disable(&virt_spin_lock_key); +} + static void __init kvm_smp_prepare_boot_cpu(void) { /* @@ -546,6 +553,7 @@ static void __init kvm_guest_init(void) } if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; @@ -556,6 +564,7 @@ static void __init kvm_guest_init(void) kvm_setup_vsyscall_timeinfo(); #ifdef CONFIG_SMP + smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online", kvm_cpu_online, kvm_cpu_down_prepare) < 0) @@ -605,6 +614,11 @@ unsigned int kvm_arch_para_features(void) return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES); } +unsigned int kvm_arch_para_hints(void) +{ + return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES); +} + static uint32_t __init kvm_detect(void) { return kvm_cpuid_base(); @@ -635,6 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void) int cpu; if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), @@ -730,6 +745,9 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) + return; + __pv_init_lock_hash(); pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 8b26c9e01cc4..bf8d1eb7fca3 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -53,7 +53,7 @@ static struct pvclock_wall_clock *wall_clock; * have elapsed since the hypervisor wrote the data. So we try to account for * that with system time */ -static void kvm_get_wallclock(struct timespec *now) +static void kvm_get_wallclock(struct timespec64 *now) { struct pvclock_vcpu_time_info *vcpu_time; int low, high; @@ -72,7 +72,7 @@ static void kvm_get_wallclock(struct timespec *now) put_cpu(); } -static int kvm_set_wallclock(const struct timespec *now) +static int kvm_set_wallclock(const struct timespec64 *now) { return -ENODEV; } diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 26d713ecad34..c9b14020f4dd 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -145,6 +145,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; + pgprot_t pte_prot; pte_t pte, *ptep; va = (unsigned long)ldt_slot_va(slot) + offset; @@ -163,7 +164,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) * target via some kernel interface which misses a * permission check. */ - pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL)); + pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL); + /* Filter out unsuppored __PAGE_KERNEL* bits: */ + pgprot_val(pte_prot) &= __supported_pte_mask; + pte = pfn_pte(pfn, pte_prot); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 60cdec6628b0..d1ab07ec8c9a 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -57,12 +57,17 @@ static void load_segments(void) static void machine_kexec_free_page_tables(struct kimage *image) { free_page((unsigned long)image->arch.pgd); + image->arch.pgd = NULL; #ifdef CONFIG_X86_PAE free_page((unsigned long)image->arch.pmd0); + image->arch.pmd0 = NULL; free_page((unsigned long)image->arch.pmd1); + image->arch.pmd1 = NULL; #endif free_page((unsigned long)image->arch.pte0); + image->arch.pte0 = NULL; free_page((unsigned long)image->arch.pte1); + image->arch.pte1 = NULL; } static int machine_kexec_alloc_page_tables(struct kimage *image) @@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image) !image->arch.pmd0 || !image->arch.pmd1 || #endif !image->arch.pte0 || !image->arch.pte1) { - machine_kexec_free_page_tables(image); return -ENOMEM; } return 0; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 93bd4fb603d1..4c8acdfdc5a7 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -30,17 +30,22 @@ #include <asm/set_memory.h> #ifdef CONFIG_KEXEC_FILE -static struct kexec_file_ops *kexec_file_loaders[] = { +const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_bzImage64_ops, + NULL }; #endif static void free_transition_pgtable(struct kimage *image) { free_page((unsigned long)image->arch.p4d); + image->arch.p4d = NULL; free_page((unsigned long)image->arch.pud); + image->arch.pud = NULL; free_page((unsigned long)image->arch.pmd); + image->arch.pmd = NULL; free_page((unsigned long)image->arch.pte); + image->arch.pte = NULL; } static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) @@ -90,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC)); return 0; err: - free_transition_pgtable(image); return result; } @@ -350,7 +354,8 @@ void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_base); VMCOREINFO_SYMBOL(init_top_pgt); - VMCOREINFO_NUMBER(pgtable_l5_enabled); + vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", + pgtable_l5_enabled()); #ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); @@ -364,27 +369,6 @@ void arch_crash_save_vmcoreinfo(void) /* arch-dependent functionality related to kexec file-based syscall */ #ifdef CONFIG_KEXEC_FILE -int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len) -{ - int i, ret = -ENOEXEC; - struct kexec_file_ops *fops; - - for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { - fops = kexec_file_loaders[i]; - if (!fops || !fops->probe) - continue; - - ret = fops->probe(buf, buf_len); - if (!ret) { - image->fops = fops; - return ret; - } - } - - return ret; -} - void *arch_kexec_kernel_image_load(struct kimage *image) { vfree(image->arch.elf_headers); @@ -399,88 +383,53 @@ void *arch_kexec_kernel_image_load(struct kimage *image) image->cmdline_buf_len); } -int arch_kimage_file_post_load_cleanup(struct kimage *image) -{ - if (!image->fops || !image->fops->cleanup) - return 0; - - return image->fops->cleanup(image->image_loader_data); -} - -#ifdef CONFIG_KEXEC_VERIFY_SIG -int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, - unsigned long kernel_len) -{ - if (!image->fops || !image->fops->verify_sig) { - pr_debug("kernel loader does not support signature verification."); - return -EKEYREJECTED; - } - - return image->fops->verify_sig(kernel, kernel_len); -} -#endif - /* * Apply purgatory relocations. * - * ehdr: Pointer to elf headers - * sechdrs: Pointer to section headers. - * relsec: section index of SHT_RELA section. + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtabsec: Corresponding symtab. * * TODO: Some of the code belongs to generic code. Move that in kexec.c. */ -int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, - Elf64_Shdr *sechdrs, unsigned int relsec) +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, const Elf_Shdr *relsec, + const Elf_Shdr *symtabsec) { unsigned int i; Elf64_Rela *rel; Elf64_Sym *sym; void *location; - Elf64_Shdr *section, *symtabsec; unsigned long address, sec_base, value; const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; - /* - * ->sh_offset has been modified to keep the pointer to section - * contents in memory - */ - rel = (void *)sechdrs[relsec].sh_offset; - - /* Section to which relocations apply */ - section = &sechdrs[sechdrs[relsec].sh_info]; - - pr_debug("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); - - /* Associated symbol table */ - symtabsec = &sechdrs[sechdrs[relsec].sh_link]; - - /* String table */ - if (symtabsec->sh_link >= ehdr->e_shnum) { - /* Invalid strtab section number */ - pr_err("Invalid string table section index %d\n", - symtabsec->sh_link); - return -ENOEXEC; - } + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; - strtab = (char *)sechdrs[symtabsec->sh_link].sh_offset; + rel = (void *)pi->ehdr + relsec->sh_offset; - /* section header string table */ - shstrtab = (char *)sechdrs[ehdr->e_shstrndx].sh_offset; + pr_debug("Applying relocate section %s to %u\n", + shstrtab + relsec->sh_name, relsec->sh_info); - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) { /* * rel[i].r_offset contains byte offset from beginning * of section to the storage unit affected. * - * This is location to update (->sh_offset). This is temporary - * buffer where section is currently loaded. This will finally - * be loaded to a different address later, pointed to by + * This is location to update. This is temporary buffer + * where section is currently loaded. This will finally be + * loaded to a different address later, pointed to by * ->sh_addr. kexec takes care of moving it * (kexec_load_segment()). */ - location = (void *)(section->sh_offset + rel[i].r_offset); + location = pi->purgatory_buf; + location += section->sh_offset; + location += rel[i].r_offset; /* Final address of the location */ address = section->sh_addr + rel[i].r_offset; @@ -491,8 +440,8 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, * to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get * these respectively. */ - sym = (Elf64_Sym *)symtabsec->sh_offset + - ELF64_R_SYM(rel[i].r_info); + sym = (void *)pi->ehdr + symtabsec->sh_offset; + sym += ELF64_R_SYM(rel[i].r_info); if (sym->st_name) name = strtab + sym->st_name; @@ -515,12 +464,12 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, if (sym->st_shndx == SHN_ABS) sec_base = 0; - else if (sym->st_shndx >= ehdr->e_shnum) { + else if (sym->st_shndx >= pi->ehdr->e_shnum) { pr_err("Invalid section %d for symbol %s\n", sym->st_shndx, name); return -ENOEXEC; } else - sec_base = sechdrs[sym->st_shndx].sh_addr; + sec_base = pi->sechdrs[sym->st_shndx].sh_addr; value = sym->st_value; value += sec_base; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 77625b60a510..ab5d9dd668d2 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -15,13 +15,11 @@ #include <asm/x86_init.h> #include <asm/iommu_table.h> -static int forbid_dac __read_mostly; +static bool disable_dac_quirk __read_mostly; const struct dma_map_ops *dma_ops = &dma_direct_ops; EXPORT_SYMBOL(dma_ops); -static int iommu_sac_force __read_mostly; - #ifdef CONFIG_IOMMU_DEBUG int panic_on_overflow __read_mostly = 1; int force_iommu __read_mostly = 1; @@ -55,9 +53,6 @@ struct device x86_dma_fallback_dev = { }; EXPORT_SYMBOL(x86_dma_fallback_dev); -/* Number of entries preallocated for DMA-API debugging */ -#define PREALLOC_DMA_DEBUG_ENTRIES 65536 - void __init pci_iommu_alloc(void) { struct iommu_table_entry *p; @@ -76,7 +71,7 @@ void __init pci_iommu_alloc(void) } } -bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) +bool arch_dma_alloc_attrs(struct device **dev) { if (!*dev) *dev = &x86_dma_fallback_dev; @@ -125,13 +120,13 @@ static __init int iommu_setup(char *p) if (!strncmp(p, "nomerge", 7)) iommu_merge = 0; if (!strncmp(p, "forcesac", 8)) - iommu_sac_force = 1; + pr_warn("forcesac option ignored.\n"); if (!strncmp(p, "allowdac", 8)) - forbid_dac = 0; + pr_warn("allowdac option ignored.\n"); if (!strncmp(p, "nodac", 5)) - forbid_dac = 1; + pr_warn("nodac option ignored.\n"); if (!strncmp(p, "usedac", 6)) { - forbid_dac = -1; + disable_dac_quirk = true; return 1; } #ifdef CONFIG_SWIOTLB @@ -156,40 +151,9 @@ static __init int iommu_setup(char *p) } early_param("iommu", iommu_setup); -int arch_dma_supported(struct device *dev, u64 mask) -{ -#ifdef CONFIG_PCI - if (mask > 0xffffffff && forbid_dac > 0) { - dev_info(dev, "PCI: Disallowing DAC for device\n"); - return 0; - } -#endif - - /* Tell the device to use SAC when IOMMU force is on. This - allows the driver to use cheaper accesses in some cases. - - Problem with this is that if we overflow the IOMMU area and - return DAC as fallback address the device may not handle it - correctly. - - As a special case some controllers have a 39bit address - mode that is as efficient as 32bit (aic79xx). Don't force - SAC for these. Assume all masks <= 40 bits are of this - type. Normally this doesn't make any difference, but gives - more gentle handling of IOMMU overflow. */ - if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) { - dev_info(dev, "Force SAC with mask %Lx\n", mask); - return 0; - } - - return 1; -} -EXPORT_SYMBOL(arch_dma_supported); - static int __init pci_iommu_init(void) { struct iommu_table_entry *p; - dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); #ifdef CONFIG_PCI dma_debug_add_bus(&pci_bus_type); @@ -209,11 +173,17 @@ rootfs_initcall(pci_iommu_init); #ifdef CONFIG_PCI /* Many VIA bridges seem to corrupt data for DAC. Disable it here */ +static int via_no_dac_cb(struct pci_dev *pdev, void *data) +{ + pdev->dev.dma_32bit_limit = true; + return 0; +} + static void via_no_dac(struct pci_dev *dev) { - if (forbid_dac == 0) { + if (!disable_dac_quirk) { dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); - forbid_dac = 1; + pci_walk_bus(dev->subordinate, via_no_dac_cb, NULL); } } DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c deleted file mode 100644 index ac7ea3a8242f..000000000000 --- a/arch/x86/kernel/pci-nommu.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Fallback functions when the main IOMMU code is not compiled in. This - code is roughly equivalent to i386. */ -#include <linux/dma-direct.h> -#include <linux/scatterlist.h> -#include <linux/string.h> -#include <linux/gfp.h> -#include <linux/pci.h> -#include <linux/mm.h> - -#include <asm/processor.h> -#include <asm/iommu.h> -#include <asm/dma.h> - -#define NOMMU_MAPPING_ERROR 0 - -static int -check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) -{ - if (hwdev && !dma_capable(hwdev, bus, size)) { - if (*hwdev->dma_mask >= DMA_BIT_MASK(32)) - printk(KERN_ERR - "nommu_%s: overflow %Lx+%zu of device mask %Lx\n", - name, (long long)bus, size, - (long long)*hwdev->dma_mask); - return 0; - } - return 1; -} - -static dma_addr_t nommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; - WARN_ON(size == 0); - if (!check_addr("map_single", dev, bus, size)) - return NOMMU_MAPPING_ERROR; - return bus; -} - -/* Map a set of buffers described by scatterlist in streaming - * mode for DMA. This is the scatter-gather version of the - * above pci_map_single interface. Here the scatter gather list - * elements are each tagged with the appropriate dma address - * and length. They are obtained via sg_dma_{address,length}(SG). - * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * - * Device ownership issues as mentioned above for pci_map_single are - * the same here. - */ -static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - WARN_ON(nents == 0 || sg[0].length == 0); - - for_each_sg(sg, s, nents, i) { - BUG_ON(!sg_page(s)); - s->dma_address = sg_phys(s); - if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) - return 0; - s->dma_length = s->length; - } - return nents; -} - -static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr == NOMMU_MAPPING_ERROR; -} - -const struct dma_map_ops nommu_dma_ops = { - .alloc = dma_generic_alloc_coherent, - .free = dma_generic_free_coherent, - .map_sg = nommu_map_sg, - .map_page = nommu_map_page, - .is_phys = 1, - .mapping_error = nommu_mapping_error, - .dma_supported = x86_dma_supported, -}; diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index e47b2dbbdef3..c06c4c16c6b6 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -151,17 +151,19 @@ void perf_get_regs_user(struct perf_regs *regs_user, regs_user_copy->sp = user_regs->sp; regs_user_copy->cs = user_regs->cs; regs_user_copy->ss = user_regs->ss; - /* - * Most system calls don't save these registers, don't report them. + * Store user space frame-pointer value on sample + * to facilitate stack unwinding for cases when + * user space executable code has such support + * enabled at compile time: */ + regs_user_copy->bp = user_regs->bp; + regs_user_copy->bx = -1; - regs_user_copy->bp = -1; regs_user_copy->r12 = -1; regs_user_copy->r13 = -1; regs_user_copy->r14 = -1; regs_user_copy->r15 = -1; - /* * For this to be at all useful, we need a reasonable guess for * the ABI. Be careful: we're in NMI context, and we're diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 03408b942adb..30ca2d1a9231 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -38,6 +38,7 @@ #include <asm/switch_to.h> #include <asm/desc.h> #include <asm/prctl.h> +#include <asm/spec-ctrl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -278,6 +279,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss, } } +#ifdef CONFIG_SMP + +struct ssb_state { + struct ssb_state *shared_state; + raw_spinlock_t lock; + unsigned int disable_state; + unsigned long local_state; +}; + +#define LSTATE_SSB 0 + +static DEFINE_PER_CPU(struct ssb_state, ssb_state); + +void speculative_store_bypass_ht_init(void) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + st->local_state = 0; + + /* + * Shared state setup happens once on the first bringup + * of the CPU. It's not destroyed on CPU hotunplug. + */ + if (st->shared_state) + return; + + raw_spin_lock_init(&st->lock); + + /* + * Go over HT siblings and check whether one of them has set up the + * shared state pointer already. + */ + for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) { + if (cpu == this_cpu) + continue; + + if (!per_cpu(ssb_state, cpu).shared_state) + continue; + + /* Link it to the state of the sibling: */ + st->shared_state = per_cpu(ssb_state, cpu).shared_state; + return; + } + + /* + * First HT sibling to come up on the core. Link shared state of + * the first HT sibling to itself. The siblings on the same core + * which come up later will see the shared state pointer and link + * themself to the state of this CPU. + */ + st->shared_state = st; +} + +/* + * Logic is: First HT sibling enables SSBD for both siblings in the core + * and last sibling to disable it, disables it for the whole core. This how + * MSR_SPEC_CTRL works in "hardware": + * + * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL + */ +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + u64 msr = x86_amd_ls_cfg_base; + + if (!static_cpu_has(X86_FEATURE_ZEN)) { + msr |= ssbd_tif_to_amd_ls_cfg(tifn); + wrmsrl(MSR_AMD64_LS_CFG, msr); + return; + } + + if (tifn & _TIF_SSBD) { + /* + * Since this can race with prctl(), block reentry on the + * same CPU. + */ + if (__test_and_set_bit(LSTATE_SSB, &st->local_state)) + return; + + msr |= x86_amd_ls_cfg_ssbd_mask; + + raw_spin_lock(&st->shared_state->lock); + /* First sibling enables SSBD: */ + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + st->shared_state->disable_state++; + raw_spin_unlock(&st->shared_state->lock); + } else { + if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state)) + return; + + raw_spin_lock(&st->shared_state->lock); + st->shared_state->disable_state--; + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + raw_spin_unlock(&st->shared_state->lock); + } +} +#else +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn); + + wrmsrl(MSR_AMD64_LS_CFG, msr); +} +#endif + +static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) +{ + /* + * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL, + * so ssbd_tif_to_spec_ctrl() just works. + */ + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); +} + +static __always_inline void intel_set_ssb_state(unsigned long tifn) +{ + u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn); + + wrmsrl(MSR_IA32_SPEC_CTRL, msr); +} + +static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +{ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) + amd_set_ssb_virt_state(tifn); + else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + amd_set_core_ssb_state(tifn); + else + intel_set_ssb_state(tifn); +} + +void speculative_store_bypass_update(unsigned long tif) +{ + preempt_disable(); + __speculative_store_bypass_update(tif); + preempt_enable(); +} + void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss) { @@ -309,6 +452,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOCPUID) set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); + + if ((tifp ^ tifn) & _TIF_SSBD) + __speculative_store_bypass_update(tifn); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 5224c6099184..0ae659de21eb 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -76,16 +76,14 @@ void __show_regs(struct pt_regs *regs, int all) savesegment(gs, gs); } - printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip); - printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags, - raw_smp_processor_id()); + show_ip(regs, KERN_DEFAULT); printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); printk(KERN_DEFAULT "ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", regs->si, regs->di, regs->bp, sp); - printk(KERN_DEFAULT " DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", - (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss); + printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", + (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); if (!all) return; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9eb448c7859d..12bb445fb98d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -205,6 +205,20 @@ static __always_inline void save_fsgs(struct task_struct *task) save_base_legacy(task, task->thread.gsindex, GS); } +#if IS_ENABLED(CONFIG_KVM) +/* + * While a process is running,current->thread.fsbase and current->thread.gsbase + * may not match the corresponding CPU registers (see save_base_legacy()). KVM + * wants an efficient way to save and restore FSBASE and GSBASE. + * When FSGSBASE extensions are enabled, this will have to use RD{FS,GS}BASE. + */ +void save_fsgs_for_kvm(void) +{ + save_fsgs(current); +} +EXPORT_SYMBOL_GPL(save_fsgs_for_kvm); +#endif + static __always_inline void loadseg(enum which_selector which, unsigned short sel) { @@ -528,6 +542,7 @@ void set_personality_64bit(void) clear_thread_flag(TIF_X32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; + current_thread_info()->status &= ~TS_COMPAT; /* Ensure the corresponding mm is not marked. */ if (current->mm) diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index ed5c4cdf0a34..e2ee403865eb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1377,7 +1377,6 @@ static void fill_sigtrap_info(struct task_struct *tsk, tsk->thread.trap_nr = X86_TRAP_DB; tsk->thread.error_code = error_code; - memset(info, 0, sizeof(*info)); info->si_signo = SIGTRAP; info->si_code = si_code; info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL; @@ -1395,6 +1394,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, { struct siginfo info; + clear_siginfo(&info); fill_sigtrap_info(tsk, regs, error_code, si_code, &info); /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 761f6af6efa5..637982efecd8 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -123,28 +123,35 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, struct pvclock_vcpu_time_info *vcpu_time, - struct timespec *ts) + struct timespec64 *ts) { u32 version; u64 delta; - struct timespec now; + struct timespec64 now; /* get wallclock at system boot */ do { version = wall_clock->version; rmb(); /* fetch version before time */ + /* + * Note: wall_clock->sec is a u32 value, so it can + * only store dates between 1970 and 2106. To allow + * times beyond that, we need to create a new hypercall + * interface with an extended pvclock_wall_clock structure + * like ARM has. + */ now.tv_sec = wall_clock->sec; now.tv_nsec = wall_clock->nsec; rmb(); /* fetch time before checking version */ } while ((wall_clock->version & 1) || (version != wall_clock->version)); delta = pvclock_clocksource_read(vcpu_time); /* time since system boot */ - delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec; + delta += now.tv_sec * NSEC_PER_SEC + now.tv_nsec; now.tv_nsec = do_div(delta, NSEC_PER_SEC); now.tv_sec = delta; - set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); + set_normalized_timespec64(ts, now.tv_sec, now.tv_nsec); } void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti) diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index f7b82ed7b5b5..586f718b8e95 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -39,7 +39,7 @@ EXPORT_SYMBOL(rtc_lock); * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(const struct timespec *now) +int mach_set_rtc_mmss(const struct timespec64 *now) { unsigned long long nowtime = now->tv_sec; struct rtc_time tm; @@ -60,7 +60,7 @@ int mach_set_rtc_mmss(const struct timespec *now) return retval; } -void mach_get_cmos_time(struct timespec *now) +void mach_get_cmos_time(struct timespec64 *now) { unsigned int status, year, mon, day, hour, min, sec, century = 0; unsigned long flags; @@ -118,7 +118,7 @@ void mach_get_cmos_time(struct timespec *now) } else year += CMOS_YEARS_OFFS; - now->tv_sec = mktime(year, mon, day, hour, min, sec); + now->tv_sec = mktime64(year, mon, day, hour, min, sec); now->tv_nsec = 0; } @@ -145,13 +145,13 @@ void rtc_cmos_write(unsigned char val, unsigned char addr) } EXPORT_SYMBOL(rtc_cmos_write); -int update_persistent_clock(struct timespec now) +int update_persistent_clock64(struct timespec64 now) { return x86_platform.set_wallclock(&now); } /* not static: needed by APM */ -void read_persistent_clock(struct timespec *ts) +void read_persistent_clock64(struct timespec64 *ts) { x86_platform.get_wallclock(ts); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6285697b6e56..5c623dfe39d1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> #include <linux/dma-contiguous.h> +#include <xen/xen.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void) high = true; } + if (xen_pv_domain()) { + pr_info("Ignoring crashkernel for a Xen PV domain\n"); + return; + } + /* 0 means: find the address automatically */ if (crash_base <= 0) { /* diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index df92605d8724..9ccbf0576cd0 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -26,10 +26,10 @@ static inline void signal_compat_build_tests(void) * new fields are handled in copy_siginfo_to_user32()! */ BUILD_BUG_ON(NSIGILL != 11); - BUILD_BUG_ON(NSIGFPE != 14); + BUILD_BUG_ON(NSIGFPE != 15); BUILD_BUG_ON(NSIGSEGV != 7); BUILD_BUG_ON(NSIGBUS != 5); - BUILD_BUG_ON(NSIGTRAP != 4); + BUILD_BUG_ON(NSIGTRAP != 5); BUILD_BUG_ON(NSIGCHLD != 6); BUILD_BUG_ON(NSIGSYS != 1); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ff99e2b6fc54..c2f7d1d2a5c3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,13 +77,9 @@ #include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> - -/* Number of siblings per CPU package */ -int smp_num_siblings = 1; -EXPORT_SYMBOL(smp_num_siblings); - -/* Last level cache ID of each logical CPU */ -DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> +#include <asm/spec-ctrl.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -242,6 +238,8 @@ static void notrace start_secondary(void *unused) */ check_tsc_sync_target(); + speculative_store_bypass_ht_init(); + /* * Lock vector_lock, set CPU online and bring the vector * allocator online. Online must be set with vector_lock held @@ -390,15 +388,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } +/* + * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs. + * + * These are Intel CPUs that enumerate an LLC that is shared by + * multiple NUMA nodes. The LLC on these systems is shared for + * off-package data access but private to the NUMA node (half + * of the package) for on-package access. + * + * CPUID (the source of the information about the LLC) can only + * enumerate the cache as being shared *or* unshared, but not + * this particular configuration. The CPU in this case enumerates + * the cache to be shared across the entire package (spanning both + * NUMA nodes). + */ + +static const struct x86_cpu_id snc_cpu[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X }, + {} +}; + static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) - return topology_sane(c, o, "llc"); + /* Do not match if we do not have a valid APICID for cpu: */ + if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID) + return false; - return false; + /* Do not match if LLC id does not match: */ + if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2)) + return false; + + /* + * Allow the SNC topology without warning. Return of false + * means 'c' does not share the LLC of 'o'. This will be + * reflected to userspace. + */ + if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu)) + return false; + + return topology_sane(c, o, "llc"); } /* @@ -456,7 +486,8 @@ static struct sched_domain_topology_level x86_topology[] = { /* * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours and Intel Cluster-on-Die have this. + * AMD Magny-Cours, Intel Cluster-on-Die, and Intel + * Sub-NUMA Clustering have this. */ static bool x86_has_numa_in_package; @@ -1257,6 +1288,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_mtrr_aps_delayed_init(); smp_quirk_init_udelay(); + + speculative_store_bypass_ht_init(); } void arch_enable_nonboot_cpus_begin(void) @@ -1536,6 +1569,8 @@ static inline void mwait_play_dead(void) void *mwait_ptr; int i; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return; if (!this_cpu_has(X86_FEATURE_MWAIT)) return; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index a3f15ed545b5..6a78d4b36a79 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/compat.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/sched/mm.h> @@ -19,7 +20,6 @@ #include <linux/elf.h> #include <asm/elf.h> -#include <asm/compat.h> #include <asm/ia32.h> #include <asm/syscalls.h> #include <asm/mpx.h> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 03f3d7695dac..a535dd64de63 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -299,6 +299,7 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str, if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { cond_local_irq_enable(regs); + clear_siginfo(&info); do_trap(trapnr, signr, str, regs, error_code, fill_trap_info(regs, signr, trapnr, &info)); } @@ -854,6 +855,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) task->thread.trap_nr = trapnr; task->thread.error_code = error_code; + clear_siginfo(&info); info.si_signo = SIGFPE; info.si_errno = 0; info.si_addr = (void __user *)uprobe_get_trap_addr(regs); @@ -929,6 +931,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); local_irq_enable(); + clear_siginfo(&info); info.si_signo = SIGILL; info.si_errno = 0; info.si_code = ILL_BADSTK; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ef32297ff17e..74392d9d51e0 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); - do_div(deltatsc, tmp); + deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } @@ -1067,6 +1067,7 @@ static struct clocksource clocksource_tsc_early = { .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, + .list = LIST_HEAD_INIT(clocksource_tsc_early.list), }; /* @@ -1086,6 +1087,7 @@ static struct clocksource clocksource_tsc = { .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, + .list = LIST_HEAD_INIT(clocksource_tsc.list), }; void mark_tsc_unstable(char *reason) @@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) { - clocksource_mark_unstable(&clocksource_tsc); - } else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + + clocksource_mark_unstable(&clocksource_tsc_early); + clocksource_mark_unstable(&clocksource_tsc); } EXPORT_SYMBOL_GPL(mark_tsc_unstable); @@ -1244,7 +1242,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Don't bother refining TSC on unstable systems */ if (tsc_unstable) - return; + goto unreg; /* * Since the work is started early in boot, we may be @@ -1297,11 +1295,12 @@ static void tsc_refine_calibration_work(struct work_struct *work) out: if (tsc_unstable) - return; + goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); +unreg: clocksource_unregister(&clocksource_tsc_early); } @@ -1311,8 +1310,8 @@ static int __init init_tsc_clocksource(void) if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) return 0; - if (check_tsc_unstable()) - return 0; + if (tsc_unstable) + goto unreg; if (tsc_clocksource_reliable) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; @@ -1328,6 +1327,7 @@ static int __init init_tsc_clocksource(void) if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); +unreg: clocksource_unregister(&clocksource_tsc_early); return 0; } diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index f44ce0fb3583..ff20b35e98dd 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -278,6 +278,7 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) tsk->thread.error_code = X86_PF_USER | X86_PF_WRITE; tsk->thread.trap_nr = X86_TRAP_PF; + clear_siginfo(&info); info.si_signo = SIGSEGV; info.si_errno = 0; info.si_code = SEGV_MAPERR; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 85c7ef23d99f..58d8d800875d 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool if (is_prefix_bad(insn)) return -ENOTSUPP; + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(insn)) + return -ENOTSUPP; + if (x86_64) good_insns = good_insns_64; else @@ -1079,8 +1083,8 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs return orig_ret_vaddr; if (nleft != rasize) { - pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " - "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); + pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n", + current->pid, regs->sp, regs->ip); force_sig_info(SIGSEGV, SEND_SIG_FORCED, current); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 795f3a80e576..5e1458f609a1 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -117,11 +117,11 @@ SECTIONS #ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); - VMLINUX_SYMBOL(__entry_trampoline_start) = .; + __entry_trampoline_start = .; _entry_trampoline = .; *(.entry_trampoline) . = ALIGN(PAGE_SIZE); - VMLINUX_SYMBOL(__entry_trampoline_end) = .; + __entry_trampoline_end = .; ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ebda84a91510..3ab867603e81 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -92,6 +92,7 @@ struct x86_init_ops x86_init __initdata = { .guest_late_init = x86_init_noop, .x2apic_available = bool_x86_init_noop, .init_mem_mapping = x86_init_noop, + .init_after_bootmem = x86_init_noop, }, .acpi = { |
