diff options
Diffstat (limited to 'arch/x86/kernel')
41 files changed, 643 insertions, 324 deletions
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 1b18be3f35a8..082d7875cef8 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -9,6 +9,7 @@ #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> @@ -298,7 +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 @@ -328,6 +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); @@ -346,21 +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; @@ -376,7 +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. @@ -384,7 +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(); @@ -395,17 +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); @@ -864,6 +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/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 38276f58d3bf..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) { @@ -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; @@ -1044,6 +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) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 37672d299e35..38216f678fc3 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -47,6 +47,16 @@ 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); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 577e7f7ae273..eb75564f2d25 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -456,24 +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 */ @@ -656,8 +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); @@ -674,19 +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); @@ -699,7 +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); @@ -727,6 +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) { 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 c8e038800591..f591b01930db 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -436,8 +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; @@ -456,13 +455,13 @@ static u32 smca_get_block_address(unsigned int cpu, unsigned int bank, * 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)) + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) goto out; if (!(low & MCI_CONFIG_MCAX)) 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)) addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); @@ -471,7 +470,7 @@ out: 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; @@ -480,7 +479,7 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi return addr; 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) { @@ -558,7 +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; @@ -1175,7 +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/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/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/head64.c b/arch/x86/kernel/head64.c index 2d29e47c056e..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; @@ -281,7 +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/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 a15fe0e92cf9..108c48d0d40e 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -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/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/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6010449ca6d2..4c8acdfdc5a7 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -354,7 +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); 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/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_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/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 5c623dfe39d1..2f86d883dd95 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1312,11 +1312,3 @@ static int __init register_kernel_offset_dumper(void) return 0; } __initcall(register_kernel_offset_dumper); - -void arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) -{ - if (!boot_cpu_has(X86_FEATURE_OSPKE)) - return; - - seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); -} diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index 14c057f29979..9ccbf0576cd0 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -29,7 +29,7 @@ static inline void signal_compat_build_tests(void) 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 9dd324ae4832..c2f7d1d2a5c3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -81,13 +81,6 @@ #include <asm/cpu_device_id.h> #include <asm/spec-ctrl.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; - /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); 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/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 c84bb5396958..58d8d800875d 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -1083,8 +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 |