diff options
Diffstat (limited to 'arch/x86/kernel')
25 files changed, 709 insertions, 363 deletions
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index f299d8a479bb..3f9d1b4019bb 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -482,7 +482,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, { void *vaddr; - vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs); + vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs); if (!vaddr || !force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24)) return vaddr; @@ -494,7 +494,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, goto out_free; return vaddr; out_free: - dma_direct_free(dev, size, vaddr, *dma_addr, attrs); + dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs); return NULL; } @@ -504,7 +504,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, unsigned long attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0); - dma_direct_free(dev, size, vaddr, dma_addr, attrs); + dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 7654febd5102..652e7ffa9b9d 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -313,14 +313,13 @@ assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest) struct apic_chip_data *apicd = apic_chip_data(irqd); int vector, cpu; - cpumask_and(vector_searchmask, vector_searchmask, affmsk); - cpu = cpumask_first(vector_searchmask); - if (cpu >= nr_cpu_ids) - return -EINVAL; + cpumask_and(vector_searchmask, dest, affmsk); + /* set_affinity might call here for nothing */ if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask)) return 0; - vector = irq_matrix_alloc_managed(vector_matrix, cpu); + vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask, + &cpu); trace_vector_alloc_managed(irqd->irq, vector, vector); if (vector < 0) return vector; diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 33399426793e..1979a76bfadd 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -1,4 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/init.h> #include <linux/sched.h> #include <linux/kthread.h> @@ -31,11 +34,17 @@ static __init int set_corruption_check(char *arg) ssize_t ret; unsigned long val; + if (!arg) { + pr_err("memory_corruption_check config string not provided\n"); + return -EINVAL; + } + ret = kstrtoul(arg, 10, &val); if (ret) return ret; memory_corruption_check = val; + return 0; } early_param("memory_corruption_check", set_corruption_check); @@ -45,6 +54,11 @@ static __init int set_corruption_check_period(char *arg) ssize_t ret; unsigned long val; + if (!arg) { + pr_err("memory_corruption_check_period config string not provided\n"); + return -EINVAL; + } + ret = kstrtoul(arg, 10, &val); if (ret) return ret; @@ -59,6 +73,11 @@ static __init int set_corruption_check_size(char *arg) char *end; unsigned size; + if (!arg) { + pr_err("memory_corruption_check_size config string not provided\n"); + return -EINVAL; + } + size = memparse(arg, &end); if (*end == '\0') @@ -113,7 +132,7 @@ void __init setup_bios_corruption_check(void) } if (num_scan_areas) - printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas); + pr_info("Scanning %d areas for low memory corruption\n", num_scan_areas); } @@ -132,8 +151,7 @@ void check_for_bios_corruption(void) for (; size; addr++, size -= sizeof(unsigned long)) { if (!*addr) continue; - printk(KERN_ERR "Corrupted low memory at %p (%lx phys) = %08lx\n", - addr, __pa(addr), *addr); + pr_err("Corrupted low memory at %p (%lx phys) = %08lx\n", addr, __pa(addr), *addr); corruption = 1; *addr = 0; } @@ -157,11 +175,11 @@ static int start_periodic_check_for_corruption(void) if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0) return 0; - printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n", - corruption_check_period); + pr_info("Scanning for low memory corruption every %d seconds\n", corruption_check_period); /* First time we run the checks right away */ schedule_delayed_work(&bios_check_work, 0); + return 0; } device_initcall(start_periodic_check_for_corruption); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 44c4ef3d989b..0b99a7fae6be 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -949,11 +949,11 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) } static const __initconst struct x86_cpu_id cpu_no_speculation[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_TABLET, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL_MID, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SALTWELL_MID, X86_FEATURE_ANY }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_BONNELL, X86_FEATURE_ANY }, { X86_VENDOR_CENTAUR, 5 }, { X86_VENDOR_INTEL, 5 }, { X86_VENDOR_NSC, 5 }, @@ -968,10 +968,10 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { /* 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_SILVERMONT }, { 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_ATOM_SILVERMONT_X }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID }, { 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 }, @@ -984,14 +984,14 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { static const __initconst struct x86_cpu_id cpu_no_l1tf[] = { /* in addition to cpu_no_speculation */ - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_X }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT_MID }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT_MID }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON }, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_PLUS }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, {} @@ -1669,6 +1669,29 @@ static void wait_for_master_cpu(int cpu) #endif } +#ifdef CONFIG_X86_64 +static void setup_getcpu(int cpu) +{ + unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu)); + struct desc_struct d = { }; + + if (static_cpu_has(X86_FEATURE_RDTSCP)) + write_rdtscp_aux(cpudata); + + /* Store CPU and node number in limit. */ + d.limit0 = cpudata; + d.limit1 = cpudata >> 16; + + d.type = 5; /* RO data, expand down, accessed */ + d.dpl = 3; /* Visible to user code */ + d.s = 1; /* Not a system segment */ + d.p = 1; /* Present */ + d.d = 1; /* 32-bit */ + + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_CPUNODE, &d, DESCTYPE_S); +} +#endif + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -1706,6 +1729,7 @@ void cpu_init(void) early_cpu_to_node(cpu) != NUMA_NO_NODE) set_numa_node(early_cpu_to_node(cpu)); #endif + setup_getcpu(cpu); me = current; diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index abb71ac70443..44272b7107ad 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -485,9 +485,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) size_t tsize; if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid), - sizeof(unsigned long), - GFP_KERNEL); + d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); @@ -496,7 +494,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) tsize = sizeof(*d->mbm_total); d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); if (!d->mbm_total) { - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); return -ENOMEM; } } @@ -504,7 +502,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) tsize = sizeof(*d->mbm_local); d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); if (!d->mbm_local) { - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); return -ENOMEM; } @@ -610,9 +608,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + /* + * rdt_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + kfree(d->ctrl_val); kfree(d->mbps_val); - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); kfree(d); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 0f53049719cd..27937458c231 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -404,8 +404,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, for_each_alloc_enabled_rdt_resource(r) seq_printf(s, "%s:uninitialized\n", r->name); } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name, - rdtgrp->plr->d->id, rdtgrp->plr->cbm); + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%s:%d=%x\n", + rdtgrp->plr->r->name, + rdtgrp->plr->d->id, + rdtgrp->plr->cbm); + } } else { closid = rdtgrp->closid; for_each_alloc_enabled_rdt_resource(r) { diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index f8c260d522ca..815b4e92522c 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -17,6 +17,7 @@ #include <linux/debugfs.h> #include <linux/kthread.h> #include <linux/mman.h> +#include <linux/perf_event.h> #include <linux/pm_qos.h> #include <linux/slab.h> #include <linux/uaccess.h> @@ -26,6 +27,7 @@ #include <asm/intel_rdt_sched.h> #include <asm/perf_event.h> +#include "../../events/perf_event.h" /* For X86_CONFIG() */ #include "intel_rdt.h" #define CREATE_TRACE_POINTS @@ -91,7 +93,7 @@ static u64 get_prefetch_disable_bits(void) */ return 0xF; case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GEMINI_LAKE: + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: /* * SDM defines bits of MSR_MISC_FEATURE_CONTROL register * as: @@ -106,16 +108,6 @@ static u64 get_prefetch_disable_bits(void) return 0; } -/* - * Helper to write 64bit value to MSR without tracing. Used when - * use of the cache should be restricted and use of registers used - * for local variables avoided. - */ -static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val) -{ - __wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); -} - /** * pseudo_lock_minor_get - Obtain available minor number * @minor: Pointer to where new minor number will be stored @@ -888,31 +880,14 @@ static int measure_cycles_lat_fn(void *_plr) struct pseudo_lock_region *plr = _plr; unsigned long i; u64 start, end; -#ifdef CONFIG_KASAN - /* - * The registers used for local register variables are also used - * when KASAN is active. When KASAN is active we use a regular - * variable to ensure we always use a valid pointer to access memory. - * The cost is that accessing this pointer, which could be in - * cache, will be included in the measurement of memory read latency. - */ void *mem_r; -#else -#ifdef CONFIG_X86_64 - register void *mem_r asm("rbx"); -#else - register void *mem_r asm("ebx"); -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_KASAN */ local_irq_disable(); /* - * The wrmsr call may be reordered with the assignment below it. - * Call wrmsr as directly as possible to avoid tracing clobbering - * local register variable used for memory pointer. + * Disable hardware prefetchers. */ - __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); - mem_r = plr->kmem; + wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + mem_r = READ_ONCE(plr->kmem); /* * Dummy execute of the time measurement to load the needed * instructions into the L1 instruction cache. @@ -934,157 +909,240 @@ static int measure_cycles_lat_fn(void *_plr) return 0; } -static int measure_cycles_perf_fn(void *_plr) +/* + * Create a perf_event_attr for the hit and miss perf events that will + * be used during the performance measurement. A perf_event maintains + * a pointer to its perf_event_attr so a unique attribute structure is + * created for each perf_event. + * + * The actual configuration of the event is set right before use in order + * to use the X86_CONFIG macro. + */ +static struct perf_event_attr perf_miss_attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 0, + .exclude_user = 1, +}; + +static struct perf_event_attr perf_hit_attr = { + .type = PERF_TYPE_RAW, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 0, + .exclude_user = 1, +}; + +struct residency_counts { + u64 miss_before, hits_before; + u64 miss_after, hits_after; +}; + +static int measure_residency_fn(struct perf_event_attr *miss_attr, + struct perf_event_attr *hit_attr, + struct pseudo_lock_region *plr, + struct residency_counts *counts) { - unsigned long long l3_hits = 0, l3_miss = 0; - u64 l3_hit_bits = 0, l3_miss_bits = 0; - struct pseudo_lock_region *plr = _plr; - unsigned long long l2_hits, l2_miss; - u64 l2_hit_bits, l2_miss_bits; - unsigned long i; -#ifdef CONFIG_KASAN - /* - * The registers used for local register variables are also used - * when KASAN is active. When KASAN is active we use regular variables - * at the cost of including cache access latency to these variables - * in the measurements. - */ + u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0; + struct perf_event *miss_event, *hit_event; + int hit_pmcnum, miss_pmcnum; unsigned int line_size; unsigned int size; + unsigned long i; void *mem_r; -#else - register unsigned int line_size asm("esi"); - register unsigned int size asm("edi"); -#ifdef CONFIG_X86_64 - register void *mem_r asm("rbx"); -#else - register void *mem_r asm("ebx"); -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_KASAN */ + u64 tmp; + + miss_event = perf_event_create_kernel_counter(miss_attr, plr->cpu, + NULL, NULL, NULL); + if (IS_ERR(miss_event)) + goto out; + + hit_event = perf_event_create_kernel_counter(hit_attr, plr->cpu, + NULL, NULL, NULL); + if (IS_ERR(hit_event)) + goto out_miss; + + local_irq_disable(); + /* + * Check any possible error state of events used by performing + * one local read. + */ + if (perf_event_read_local(miss_event, &tmp, NULL, NULL)) { + local_irq_enable(); + goto out_hit; + } + if (perf_event_read_local(hit_event, &tmp, NULL, NULL)) { + local_irq_enable(); + goto out_hit; + } + + /* + * Disable hardware prefetchers. + */ + wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); + + /* Initialize rest of local variables */ + /* + * Performance event has been validated right before this with + * interrupts disabled - it is thus safe to read the counter index. + */ + miss_pmcnum = x86_perf_rdpmc_index(miss_event); + hit_pmcnum = x86_perf_rdpmc_index(hit_event); + line_size = READ_ONCE(plr->line_size); + mem_r = READ_ONCE(plr->kmem); + size = READ_ONCE(plr->size); + + /* + * Read counter variables twice - first to load the instructions + * used in L1 cache, second to capture accurate value that does not + * include cache misses incurred because of instruction loads. + */ + rdpmcl(hit_pmcnum, hits_before); + rdpmcl(miss_pmcnum, miss_before); + /* + * From SDM: Performing back-to-back fast reads are not guaranteed + * to be monotonic. + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + rdpmcl(hit_pmcnum, hits_before); + rdpmcl(miss_pmcnum, miss_before); + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + for (i = 0; i < size; i += line_size) { + /* + * Add a barrier to prevent speculative execution of this + * loop reading beyond the end of the buffer. + */ + rmb(); + asm volatile("mov (%0,%1,1), %%eax\n\t" + : + : "r" (mem_r), "r" (i) + : "%eax", "memory"); + } + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + rdpmcl(hit_pmcnum, hits_after); + rdpmcl(miss_pmcnum, miss_after); + /* + * Use LFENCE to ensure all previous instructions are retired + * before proceeding. + */ + rmb(); + /* Re-enable hardware prefetchers */ + wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); + local_irq_enable(); +out_hit: + perf_event_release_kernel(hit_event); +out_miss: + perf_event_release_kernel(miss_event); +out: + /* + * All counts will be zero on failure. + */ + counts->miss_before = miss_before; + counts->hits_before = hits_before; + counts->miss_after = miss_after; + counts->hits_after = hits_after; + return 0; +} + +static int measure_l2_residency(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + struct residency_counts counts = {0}; /* * Non-architectural event for the Goldmont Microarchitecture * from Intel x86 Architecture Software Developer Manual (SDM): * MEM_LOAD_UOPS_RETIRED D1H (event number) * Umask values: - * L1_HIT 01H * L2_HIT 02H - * L1_MISS 08H * L2_MISS 10H - * - * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event - * has two "no fix" errata associated with it: BDM35 and BDM100. On - * this platform we use the following events instead: - * L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/) - * REFERENCES FFH - * MISS 3FH - * LONGEST_LAT_CACHE 2EH (Documented in SDM) - * REFERENCE 4FH - * MISS 41H */ - - /* - * Start by setting flags for IA32_PERFEVTSELx: - * OS (Operating system mode) 0x2 - * INT (APIC interrupt enable) 0x10 - * EN (Enable counter) 0x40 - * - * Then add the Umask value and event number to select performance - * event. - */ - switch (boot_cpu_data.x86_model) { case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_ATOM_GEMINI_LAKE: - l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1; - l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1; - break; - case INTEL_FAM6_BROADWELL_X: - /* On BDW the l2_hit_bits count references, not hits */ - l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24; - l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24; - /* On BDW the l3_hit_bits count references, not hits */ - l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e; - l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e; + case INTEL_FAM6_ATOM_GOLDMONT_PLUS: + perf_miss_attr.config = X86_CONFIG(.event = 0xd1, + .umask = 0x10); + perf_hit_attr.config = X86_CONFIG(.event = 0xd1, + .umask = 0x2); break; default: goto out; } - local_irq_disable(); + measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts); /* - * Call wrmsr direcly to avoid the local register variables from - * being overwritten due to reordering of their assignment with - * the wrmsr calls. + * If a failure prevented the measurements from succeeding + * tracepoints will still be written and all counts will be zero. */ - __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0); - /* Disable events and reset counters */ - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0); - if (l3_hit_bits > 0) { - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0); - } - /* Set and enable the L2 counters */ - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits); - if (l3_hit_bits > 0) { - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, - l3_hit_bits); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, - l3_miss_bits); - } - mem_r = plr->kmem; - size = plr->size; - line_size = plr->line_size; - for (i = 0; i < size; i += line_size) { - asm volatile("mov (%0,%1,1), %%eax\n\t" - : - : "r" (mem_r), "r" (i) - : "%eax", "memory"); - } + trace_pseudo_lock_l2(counts.hits_after - counts.hits_before, + counts.miss_after - counts.miss_before); +out: + plr->thread_done = 1; + wake_up_interruptible(&plr->lock_thread_wq); + return 0; +} + +static int measure_l3_residency(void *_plr) +{ + struct pseudo_lock_region *plr = _plr; + struct residency_counts counts = {0}; + /* - * Call wrmsr directly (no tracing) to not influence - * the cache access counters as they are disabled. + * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event + * has two "no fix" errata associated with it: BDM35 and BDM100. On + * this platform the following events are used instead: + * LONGEST_LAT_CACHE 2EH (Documented in SDM) + * REFERENCE 4FH + * MISS 41H */ - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, - l2_hit_bits & ~(0x40ULL << 16)); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, - l2_miss_bits & ~(0x40ULL << 16)); - if (l3_hit_bits > 0) { - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, - l3_hit_bits & ~(0x40ULL << 16)); - pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, - l3_miss_bits & ~(0x40ULL << 16)); - } - l2_hits = native_read_pmc(0); - l2_miss = native_read_pmc(1); - if (l3_hit_bits > 0) { - l3_hits = native_read_pmc(2); - l3_miss = native_read_pmc(3); + + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_BROADWELL_X: + /* On BDW the hit event counts references, not hits */ + perf_hit_attr.config = X86_CONFIG(.event = 0x2e, + .umask = 0x4f); + perf_miss_attr.config = X86_CONFIG(.event = 0x2e, + .umask = 0x41); + break; + default: + goto out; } - wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0); - local_irq_enable(); + + measure_residency_fn(&perf_miss_attr, &perf_hit_attr, plr, &counts); /* - * On BDW we count references and misses, need to adjust. Sometimes - * the "hits" counter is a bit more than the references, for - * example, x references but x + 1 hits. To not report invalid - * hit values in this case we treat that as misses eaqual to - * references. + * If a failure prevented the measurements from succeeding + * tracepoints will still be written and all counts will be zero. */ - if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) - l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss); - trace_pseudo_lock_l2(l2_hits, l2_miss); - if (l3_hit_bits > 0) { - if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) - l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss); - trace_pseudo_lock_l3(l3_hits, l3_miss); + + counts.miss_after -= counts.miss_before; + if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X) { + /* + * On BDW references and misses are counted, need to adjust. + * Sometimes the "hits" counter is a bit more than the + * references, for example, x references but x + 1 hits. + * To not report invalid hit values in this case we treat + * that as misses equal to references. + */ + /* First compute the number of cache references measured */ + counts.hits_after -= counts.hits_before; + /* Next convert references to cache hits */ + counts.hits_after -= min(counts.miss_after, counts.hits_after); + } else { + counts.hits_after -= counts.hits_before; } + trace_pseudo_lock_l3(counts.hits_after, counts.miss_after); out: plr->thread_done = 1; wake_up_interruptible(&plr->lock_thread_wq); @@ -1116,6 +1174,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) goto out; } + if (!plr->d) { + ret = -ENODEV; + goto out; + } + plr->thread_done = 0; cpu = cpumask_first(&plr->d->cpu_mask); if (!cpu_online(cpu)) { @@ -1123,13 +1186,20 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) goto out; } + plr->cpu = cpu; + if (sel == 1) thread = kthread_create_on_node(measure_cycles_lat_fn, plr, cpu_to_node(cpu), "pseudo_lock_measure/%u", cpu); else if (sel == 2) - thread = kthread_create_on_node(measure_cycles_perf_fn, plr, + thread = kthread_create_on_node(measure_l2_residency, plr, + cpu_to_node(cpu), + "pseudo_lock_measure/%u", + cpu); + else if (sel == 3) + thread = kthread_create_on_node(measure_l3_residency, plr, cpu_to_node(cpu), "pseudo_lock_measure/%u", cpu); @@ -1173,7 +1243,7 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file, buf[buf_size] = '\0'; ret = kstrtoint(buf, 10, &sel); if (ret == 0) { - if (sel != 1) + if (sel != 1 && sel != 2 && sel != 3) return -EINVAL; ret = debugfs_file_get(file->f_path.dentry); if (ret) @@ -1429,6 +1499,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) plr = rdtgrp->plr; + if (!plr->d) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + /* * Task is required to run with affinity to the cpus associated * with the pseudo-locked region. If this is not the case the task diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index b140c68bc14b..f27b8115ffa2 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -268,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdtgroup *rdtgrp; + struct cpumask *mask; int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->plr->d->cpu_mask)); - else + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + mask = &rdtgrp->plr->d->cpu_mask; + seq_printf(s, is_cpu_list(of) ? + "%*pbl\n" : "%*pb\n", + cpumask_pr_args(mask)); + } + } else { seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); + } } else { ret = -ENOENT; } @@ -961,7 +971,78 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, } /** - * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * rdt_cdp_peer_get - Retrieve CDP peer if it exists + * @r: RDT resource to which RDT domain @d belongs + * @d: Cache instance for which a CDP peer is requested + * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer) + * Used to return the result. + * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer) + * Used to return the result. + * + * RDT resources are managed independently and by extension the RDT domains + * (RDT resource instances) are managed independently also. The Code and + * Data Prioritization (CDP) RDT resources, while managed independently, + * could refer to the same underlying hardware. For example, + * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache. + * + * When provided with an RDT resource @r and an instance of that RDT + * resource @d rdt_cdp_peer_get() will return if there is a peer RDT + * resource and the exact instance that shares the same hardware. + * + * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists. + * If a CDP peer was found, @r_cdp will point to the peer RDT resource + * and @d_cdp will point to the peer RDT domain. + */ +static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, + struct rdt_resource **r_cdp, + struct rdt_domain **d_cdp) +{ + struct rdt_resource *_r_cdp = NULL; + struct rdt_domain *_d_cdp = NULL; + int ret = 0; + + switch (r->rid) { + case RDT_RESOURCE_L3DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + break; + case RDT_RESOURCE_L3CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + break; + case RDT_RESOURCE_L2DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE]; + break; + case RDT_RESOURCE_L2CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA]; + break; + default: + ret = -ENOENT; + goto out; + } + + /* + * When a new CPU comes online and CDP is enabled then the new + * RDT domains (if any) associated with both CDP RDT resources + * are added in the same CPU online routine while the + * rdtgroup_mutex is held. It should thus not happen for one + * RDT domain to exist and be associated with its RDT CDP + * resource but there is no RDT domain associated with the + * peer RDT CDP resource. Hence the WARN. + */ + _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); + if (WARN_ON(!_d_cdp)) { + _r_cdp = NULL; + ret = -EINVAL; + } + +out: + *r_cdp = _r_cdp; + *d_cdp = _d_cdp; + + return ret; +} + +/** + * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other * @r: Resource to which domain instance @d belongs. * @d: The domain instance for which @closid is being tested. * @cbm: Capacity bitmask being tested. @@ -980,8 +1061,8 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * * Return: false if CBM does not overlap, true if it does. */ -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - unsigned long cbm, int closid, bool exclusive) +static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) { enum rdtgrp_mode mode; unsigned long ctrl_b; @@ -1017,6 +1098,41 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, } /** + * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Resources that can be allocated using a CBM can use the CBM to control + * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test + * for overlap. Overlap test is not limited to the specific resource for + * which the CBM is intended though - when dealing with CDP resources that + * share the underlying hardware the overlap check should be performed on + * the CDP resource sharing the hardware also. + * + * Refer to description of __rdtgroup_cbm_overlaps() for the details of the + * overlap test. + * + * Return: true if CBM overlap detected, false if there is no overlap + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + struct rdt_resource *r_cdp; + struct rdt_domain *d_cdp; + + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive)) + return true; + + if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0) + return false; + + return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive); +} + +/** * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive * * An exclusive resource group implies that there should be no sharing of @@ -1176,6 +1292,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; + int ret = 0; bool sep; u32 ctrl; @@ -1186,11 +1303,18 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name); - size = rdtgroup_cbm_to_size(rdtgrp->plr->r, - rdtgrp->plr->d, - rdtgrp->plr->cbm); - seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%*s:", max_name_width, + rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + } goto out; } @@ -1220,7 +1344,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, out: rdtgroup_kn_unlock(of->kn); - return 0; + return ret; } /* rdtgroup information files for one cache resource. */ @@ -2354,14 +2478,16 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) */ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) { + struct rdt_resource *r_cdp = NULL; + struct rdt_domain *d_cdp = NULL; u32 used_b = 0, unused_b = 0; u32 closid = rdtgrp->closid; struct rdt_resource *r; unsigned long tmp_cbm; enum rdtgrp_mode mode; struct rdt_domain *d; + u32 peer_ctl, *ctrl; int i, ret; - u32 *ctrl; for_each_alloc_enabled_rdt_resource(r) { /* @@ -2371,6 +2497,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) if (r->rid == RDT_RESOURCE_MBA) continue; list_for_each_entry(d, &r->domains, list) { + rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; @@ -2380,9 +2507,19 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) break; - used_b |= *ctrl; + /* + * If CDP is active include peer + * domain's usage to ensure there + * is no overlap with an exclusive + * group. + */ + if (d_cdp) + peer_ctl = d_cdp->ctrl_val[i]; + else + peer_ctl = 0; + used_b |= *ctrl | peer_ctl; if (mode == RDT_MODE_SHAREABLE) - d->new_ctrl |= *ctrl; + d->new_ctrl |= *ctrl | peer_ctl; } } if (d->plr && d->plr->cbm > 0) @@ -2805,6 +2942,13 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) seq_puts(seq, ",cdp"); + + if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + seq_puts(seq, ",cdpl2"); + + if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA])) + seq_puts(seq, ",mba_MBps"); + return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 97685a0c3175..27f394ac983f 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -38,9 +38,6 @@ static struct mce_log_buffer mcelog = { static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); -/* User mode helper program triggered by machine check event */ -extern char mce_helper[128]; - static int dev_mce_log(struct notifier_block *nb, unsigned long val, void *data) { diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index c805a06e14c3..1fc424c40a31 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -108,6 +108,9 @@ static void setup_inj_struct(struct mce *m) memset(m, 0, sizeof(struct mce)); m->cpuvendor = boot_cpu_data.x86_vendor; + m->time = ktime_get_real_seconds(); + m->cpuid = cpuid_eax(1); + m->microcode = boot_cpu_data.microcode; } /* Update fake mce registers on current CPU. */ @@ -576,6 +579,9 @@ static int inj_bank_set(void *data, u64 val) m->bank = val; do_inject(); + /* Reset injection struct */ + setup_inj_struct(&i_mce); + return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 953b3ce92dcc..ef8fd1f2ede0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1315,7 +1315,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) local_irq_disable(); ist_end_non_atomic(); } else { - if (!fixup_exception(regs, X86_TRAP_MC)) + if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) mce_panic("Failed kernel mode recovery", &m, NULL); } diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 23f1691670b6..61a949d84dfa 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -314,7 +314,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Validate and sanitize the copied state. */ - struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index eeea935e9bb5..aac0c1f7e354 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -42,55 +42,40 @@ static void __ref __jump_label_transform(struct jump_entry *entry, void *(*poker)(void *, const void *, size_t), int init) { - union jump_code_union code; + union jump_code_union jmp; const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; + const void *expect, *code; + int line; + + jmp.jump = 0xe9; + jmp.offset = jump_entry_target(entry) - + (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); if (early_boot_irqs_disabled) poker = text_poke_early; if (type == JUMP_LABEL_JMP) { if (init) { - /* - * Jump label is enabled for the first time. - * So we expect a default_nop... - */ - if (unlikely(memcmp((void *)entry->code, default_nop, 5) - != 0)) - bug_at((void *)entry->code, __LINE__); + expect = default_nop; line = __LINE__; } else { - /* - * ...otherwise expect an ideal_nop. Otherwise - * something went horribly wrong. - */ - if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) - != 0)) - bug_at((void *)entry->code, __LINE__); + expect = ideal_nop; line = __LINE__; } - code.jump = 0xe9; - code.offset = entry->target - - (entry->code + JUMP_LABEL_NOP_SIZE); + code = &jmp.code; } else { - /* - * We are disabling this jump label. If it is not what - * we think it is, then something must have gone wrong. - * If this is the first initialization call, then we - * are converting the default nop to the ideal nop. - */ if (init) { - if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0)) - bug_at((void *)entry->code, __LINE__); + expect = default_nop; line = __LINE__; } else { - code.jump = 0xe9; - code.offset = entry->target - - (entry->code + JUMP_LABEL_NOP_SIZE); - if (unlikely(memcmp((void *)entry->code, &code, 5) != 0)) - bug_at((void *)entry->code, __LINE__); + expect = &jmp.code; line = __LINE__; } - memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); + + code = ideal_nop; } + if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE)) + bug_at((void *)jump_entry_code(entry), line); + /* * Make text_poke_bp() a default fallback poker. * @@ -99,11 +84,14 @@ static void __ref __jump_label_transform(struct jump_entry *entry, * always nop being the 'currently valid' instruction * */ - if (poker) - (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); - else - text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE, - (void *)entry->code + JUMP_LABEL_NOP_SIZE); + if (poker) { + (*poker)((void *)jump_entry_code(entry), code, + JUMP_LABEL_NOP_SIZE); + return; + } + + text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE, + (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); } void arch_jump_label_transform(struct jump_entry *entry, diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index b0d1e81c96bb..f72a47b602e2 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1020,50 +1020,12 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) */ if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) return 1; - - /* - * In case the user-specified fault handler returned - * zero, try to fix up. - */ - if (fixup_exception(regs, trapnr)) - return 1; - - /* - * fixup routine could not handle it, - * Let do_page_fault() fix it. - */ } return 0; } NOKPROBE_SYMBOL(kprobe_fault_handler); -/* - * Wrapper routine for handling exceptions. - */ -int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, - void *data) -{ - struct die_args *args = data; - int ret = NOTIFY_DONE; - - if (args->regs && user_mode(args->regs)) - return ret; - - if (val == DIE_GPF) { - /* - * To be potentially processing a kprobe fault and to - * trust the result from kprobe_running(), we have - * be non-preemptible. - */ - if (!preemptible() && kprobe_running() && - kprobe_fault_handler(args->regs, args->trapnr)) - ret = NOTIFY_STOP; - } - return ret; -} -NOKPROBE_SYMBOL(kprobe_exceptions_notify); - bool arch_within_kprobe_blacklist(unsigned long addr) { bool is_in_entry_trampoline_section = false; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index eaf02f2e7300..40b16b270656 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -179,7 +179,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) opt_pre_handler(&op->kp, regs); __this_cpu_write(current_kprobe, NULL); } - preempt_enable_no_resched(); + preempt_enable(); } NOKPROBE_SYMBOL(optimized_callback); diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S new file mode 100644 index 000000000000..161c95059044 --- /dev/null +++ b/arch/x86/kernel/macros.S @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This file includes headers whose assembly part includes macros which are + * commonly used. The macros are precompiled into assmebly file which is later + * assembled together with each compiled file. + */ + +#include <linux/compiler.h> +#include <asm/refcount.h> +#include <asm/alternative-asm.h> +#include <asm/bug.h> +#include <asm/paravirt.h> +#include <asm/asm.h> +#include <asm/cpufeature.h> +#include <asm/jump_label.h> diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index f58336af095c..b052e883dd8c 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -201,6 +201,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, goto overflow; #endif break; + case R_X86_64_PC64: + if (*(u64 *)loc != 0) + goto invalid_relocation; + val -= (u64)loc; + *(u64 *)loc = val; + break; default: pr_err("%s: Unknown rela relocation: %llu\n", me->name, ELF64_R_TYPE(rel[i].r_info)); diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 661583662430..71c0b01d93b1 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -42,10 +42,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override, int __init pci_swiotlb_detect_4gb(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ -#ifdef CONFIG_X86_64 if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; -#endif /* * If SME is active then swiotlb will be set to 1 so that bounce diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ea5ea850348d..d6674a425714 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -54,6 +54,7 @@ #include <asm/vdso.h> #include <asm/intel_rdt_sched.h> #include <asm/unistd.h> +#include <asm/fsgsbase.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ #include <asm/unistd_32_ia32.h> @@ -286,6 +287,138 @@ static __always_inline void load_seg_legacy(unsigned short prev_index, } } +static __always_inline void x86_fsgsbase_load(struct thread_struct *prev, + struct thread_struct *next) +{ + load_seg_legacy(prev->fsindex, prev->fsbase, + next->fsindex, next->fsbase, FS); + load_seg_legacy(prev->gsindex, prev->gsbase, + next->gsindex, next->gsbase, GS); +} + +static unsigned long x86_fsgsbase_read_task(struct task_struct *task, + unsigned short selector) +{ + unsigned short idx = selector >> 3; + unsigned long base; + + if (likely((selector & SEGMENT_TI_MASK) == 0)) { + if (unlikely(idx >= GDT_ENTRIES)) + return 0; + + /* + * There are no user segments in the GDT with nonzero bases + * other than the TLS segments. + */ + if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) + return 0; + + idx -= GDT_ENTRY_TLS_MIN; + base = get_desc_base(&task->thread.tls_array[idx]); + } else { +#ifdef CONFIG_MODIFY_LDT_SYSCALL + struct ldt_struct *ldt; + + /* + * If performance here mattered, we could protect the LDT + * with RCU. This is a slow path, though, so we can just + * take the mutex. + */ + mutex_lock(&task->mm->context.lock); + ldt = task->mm->context.ldt; + if (unlikely(idx >= ldt->nr_entries)) + base = 0; + else + base = get_desc_base(ldt->entries + idx); + mutex_unlock(&task->mm->context.lock); +#else + base = 0; +#endif + } + + return base; +} + +void x86_fsbase_write_cpu(unsigned long fsbase) +{ + /* + * Set the selector to 0 as a notion, that the segment base is + * overwritten, which will be checked for skipping the segment load + * during context switch. + */ + loadseg(FS, 0); + wrmsrl(MSR_FS_BASE, fsbase); +} + +void x86_gsbase_write_cpu_inactive(unsigned long gsbase) +{ + /* Set the selector to 0 for the same reason as %fs above. */ + loadseg(GS, 0); + wrmsrl(MSR_KERNEL_GS_BASE, gsbase); +} + +unsigned long x86_fsbase_read_task(struct task_struct *task) +{ + unsigned long fsbase; + + if (task == current) + fsbase = x86_fsbase_read_cpu(); + else if (task->thread.fsindex == 0) + fsbase = task->thread.fsbase; + else + fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex); + + return fsbase; +} + +unsigned long x86_gsbase_read_task(struct task_struct *task) +{ + unsigned long gsbase; + + if (task == current) + gsbase = x86_gsbase_read_cpu_inactive(); + else if (task->thread.gsindex == 0) + gsbase = task->thread.gsbase; + else + gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex); + + return gsbase; +} + +int x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase) +{ + /* + * Not strictly needed for %fs, but do it for symmetry + * with %gs + */ + if (unlikely(fsbase >= TASK_SIZE_MAX)) + return -EPERM; + + preempt_disable(); + task->thread.fsbase = fsbase; + if (task == current) + x86_fsbase_write_cpu(fsbase); + task->thread.fsindex = 0; + preempt_enable(); + + return 0; +} + +int x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) +{ + if (unlikely(gsbase >= TASK_SIZE_MAX)) + return -EPERM; + + preempt_disable(); + task->thread.gsbase = gsbase; + if (task == current) + x86_gsbase_write_cpu_inactive(gsbase); + task->thread.gsindex = 0; + preempt_enable(); + + return 0; +} + int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { @@ -473,10 +606,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (unlikely(next->ds | prev->ds)) loadsegment(ds, next->ds); - load_seg_legacy(prev->fsindex, prev->fsbase, - next->fsindex, next->fsbase, FS); - load_seg_legacy(prev->gsindex, prev->gsbase, - next->gsindex, next->gsbase, GS); + x86_fsgsbase_load(prev, next); switch_fpu_finish(next_fpu, cpu); @@ -627,54 +757,25 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; - int doit = task == current; - int cpu; switch (option) { - case ARCH_SET_GS: - if (arg2 >= TASK_SIZE_MAX) - return -EPERM; - cpu = get_cpu(); - task->thread.gsindex = 0; - task->thread.gsbase = arg2; - if (doit) { - load_gs_index(0); - ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2); - } - put_cpu(); + case ARCH_SET_GS: { + ret = x86_gsbase_write_task(task, arg2); break; - case ARCH_SET_FS: - /* Not strictly needed for fs, but do it for symmetry - with gs */ - if (arg2 >= TASK_SIZE_MAX) - return -EPERM; - cpu = get_cpu(); - task->thread.fsindex = 0; - task->thread.fsbase = arg2; - if (doit) { - /* set the selector to 0 to not confuse __switch_to */ - loadsegment(fs, 0); - ret = wrmsrl_safe(MSR_FS_BASE, arg2); - } - put_cpu(); + } + case ARCH_SET_FS: { + ret = x86_fsbase_write_task(task, arg2); break; + } case ARCH_GET_FS: { - unsigned long base; + unsigned long base = x86_fsbase_read_task(task); - if (doit) - rdmsrl(MSR_FS_BASE, base); - else - base = task->thread.fsbase; ret = put_user(base, (unsigned long __user *)arg2); break; } case ARCH_GET_GS: { - unsigned long base; + unsigned long base = x86_gsbase_read_task(task); - if (doit) - rdmsrl(MSR_KERNEL_GS_BASE, base); - else - base = task->thread.gsbase; ret = put_user(base, (unsigned long __user *)arg2); break; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index e2ee403865eb..d8f49c7384a3 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -39,6 +39,7 @@ #include <asm/hw_breakpoint.h> #include <asm/traps.h> #include <asm/syscall.h> +#include <asm/fsgsbase.h> #include "tls.h" @@ -396,12 +397,11 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; /* - * When changing the segment base, use do_arch_prctl_64 - * to set either thread.fs or thread.fsindex and the - * corresponding GDT slot. + * When changing the FS base, use the same + * mechanism as for do_arch_prctl_64(). */ if (child->thread.fsbase != value) - return do_arch_prctl_64(child, ARCH_SET_FS, value); + return x86_fsbase_write_task(child, value); return 0; case offsetof(struct user_regs_struct,gs_base): /* @@ -410,7 +410,7 @@ static int putreg(struct task_struct *child, if (value >= TASK_SIZE_MAX) return -EIO; if (child->thread.gsbase != value) - return do_arch_prctl_64(child, ARCH_SET_GS, value); + return x86_gsbase_write_task(child, value); return 0; #endif } @@ -434,20 +434,10 @@ static unsigned long getreg(struct task_struct *task, unsigned long offset) return get_flags(task); #ifdef CONFIG_X86_64 - case offsetof(struct user_regs_struct, fs_base): { - /* - * XXX: This will not behave as expected if called on - * current or if fsindex != 0. - */ - return task->thread.fsbase; - } - case offsetof(struct user_regs_struct, gs_base): { - /* - * XXX: This will not behave as expected if called on - * current or if fsindex != 0. - */ - return task->thread.gsbase; - } + case offsetof(struct user_regs_struct, fs_base): + return x86_fsbase_read_task(task); + case offsetof(struct user_regs_struct, gs_base): + return x86_gsbase_read_task(task); #endif } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4866badb235..90ecc108bc8a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1251,7 +1251,7 @@ void __init setup_arch(char **cmdline_p) x86_init.hyper.guest_late_init(); e820__reserve_resources(); - e820__register_nosave_regions(max_low_pfn); + e820__register_nosave_regions(max_pfn); x86_init.resources.reserve_resources(); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index be01328eb755..fddaefc51fb6 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -25,7 +25,7 @@ #include <asm/time.h> #ifdef CONFIG_X86_64 -__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES; +__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES; #endif unsigned long profile_pc(struct pt_regs *regs) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index e6db475164ed..16c95cb90496 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -206,7 +206,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, } if (!user_mode(regs)) { - if (fixup_exception(regs, trapnr)) + if (fixup_exception(regs, trapnr, error_code, 0)) return 0; tsk->thread.error_code = error_code; @@ -551,11 +551,21 @@ do_general_protection(struct pt_regs *regs, long error_code) tsk = current; if (!user_mode(regs)) { - if (fixup_exception(regs, X86_TRAP_GP)) + if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) return; tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; + + /* + * To be potentially processing a kprobe fault and to + * trust the result from kprobe_running(), we have to + * be non-preemptible. + */ + if (!preemptible() && kprobe_running() && + kprobe_fault_handler(regs, X86_TRAP_GP)) + return; + if (notify_die(DIE_GPF, "general protection fault", regs, error_code, X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) die("general protection fault", regs, error_code); @@ -838,7 +848,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (fixup_exception(regs, trapnr)) + if (fixup_exception(regs, trapnr, error_code, 0)) return; task->thread.error_code = error_code; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index b52bd2b6cdb4..03b7529333a6 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -58,7 +58,7 @@ struct cyc2ns { static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); -void cyc2ns_read_begin(struct cyc2ns_data *data) +void __always_inline cyc2ns_read_begin(struct cyc2ns_data *data) { int seq, idx; @@ -75,7 +75,7 @@ void cyc2ns_read_begin(struct cyc2ns_data *data) } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); } -void cyc2ns_read_end(void) +void __always_inline cyc2ns_read_end(void) { preempt_enable_notrace(); } @@ -104,7 +104,7 @@ void cyc2ns_read_end(void) * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ -static inline unsigned long long cycles_2_ns(unsigned long long cyc) +static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc) { struct cyc2ns_data data; unsigned long long ns; @@ -636,7 +636,7 @@ unsigned long native_calibrate_tsc(void) case INTEL_FAM6_KABYLAKE_DESKTOP: crystal_khz = 24000; /* 24.0 MHz */ break; - case INTEL_FAM6_ATOM_DENVERTON: + case INTEL_FAM6_ATOM_GOLDMONT_X: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 27ef714d886c..3d0e9aeea7c8 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -59,12 +59,12 @@ static const struct freq_desc freq_desc_ann = { }; static const struct x86_cpu_id tsc_msr_cpu_ids[] = { - INTEL_CPU_FAM6(ATOM_PENWELL, freq_desc_pnw), - INTEL_CPU_FAM6(ATOM_CLOVERVIEW, freq_desc_clv), - INTEL_CPU_FAM6(ATOM_SILVERMONT1, freq_desc_byt), + INTEL_CPU_FAM6(ATOM_SALTWELL_MID, freq_desc_pnw), + INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET, freq_desc_clv), + INTEL_CPU_FAM6(ATOM_SILVERMONT, freq_desc_byt), + INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, freq_desc_tng), INTEL_CPU_FAM6(ATOM_AIRMONT, freq_desc_cht), - INTEL_CPU_FAM6(ATOM_MERRIFIELD, freq_desc_tng), - INTEL_CPU_FAM6(ATOM_MOOREFIELD, freq_desc_ann), + INTEL_CPU_FAM6(ATOM_AIRMONT_MID, freq_desc_ann), {} }; |
