diff options
Diffstat (limited to 'arch/x86/kernel')
71 files changed, 2041 insertions, 989 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 3b20607d581b..e8fea7ffa306 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -48,6 +48,7 @@ #include <asm/mpspec.h> #include <asm/smp.h> #include <asm/i8259.h> +#include <asm/setup.h> #include "sleep.h" /* To include x86_acpi_suspend_lowlevel */ static int __initdata acpi_force = 0; @@ -1771,3 +1772,8 @@ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) e820__range_add(addr, size, E820_TYPE_ACPI); e820__update_table_print(); } + +u64 x86_default_get_root_pointer(void) +{ + return boot_params.hdr.acpi_rsdp_addr; +} diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b9d5e7c9ef43..ebeac487a20c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -222,6 +222,10 @@ void __init arch_init_ideal_nops(void) } break; + case X86_VENDOR_HYGON: + ideal_nops = p6_nops; + return; + case X86_VENDOR_AMD: if (boot_cpu_data.x86 > 0xf) { ideal_nops = p6_nops; @@ -594,7 +598,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, BUG_ON(p->len > MAX_PATCH_LEN); /* prep the buffer with the original instructions */ memcpy(insnbuf, p->instr, p->len); - used = pv_init_ops.patch(p->instrtype, p->clobbers, insnbuf, + used = pv_ops.init.patch(p->instrtype, insnbuf, (unsigned long)p->instr, p->len); BUG_ON(used > p->len); 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/amd_nb.c b/arch/x86/kernel/amd_nb.c index b481b95bd8f6..a6eca647bc76 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -61,6 +61,21 @@ static const struct pci_device_id amd_nb_link_ids[] = { {} }; +static const struct pci_device_id hygon_root_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_ROOT) }, + {} +}; + +const struct pci_device_id hygon_nb_misc_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + {} +}; + +static const struct pci_device_id hygon_nb_link_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + {} +}; + const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[] __initconst = { { 0x00, 0x18, 0x20 }, { 0xff, 0x00, 0x20 }, @@ -194,15 +209,24 @@ EXPORT_SYMBOL_GPL(amd_df_indirect_read); int amd_cache_northbridges(void) { - u16 i = 0; - struct amd_northbridge *nb; + const struct pci_device_id *misc_ids = amd_nb_misc_ids; + const struct pci_device_id *link_ids = amd_nb_link_ids; + const struct pci_device_id *root_ids = amd_root_ids; struct pci_dev *root, *misc, *link; + struct amd_northbridge *nb; + u16 i = 0; if (amd_northbridges.num) return 0; + if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { + root_ids = hygon_root_ids; + misc_ids = hygon_nb_misc_ids; + link_ids = hygon_nb_link_ids; + } + misc = NULL; - while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) + while ((misc = next_northbridge(misc, misc_ids)) != NULL) i++; if (!i) @@ -218,11 +242,11 @@ int amd_cache_northbridges(void) link = misc = root = NULL; for (i = 0; i != amd_northbridges.num; i++) { node_to_amd_nb(i)->root = root = - next_northbridge(root, amd_root_ids); + next_northbridge(root, root_ids); node_to_amd_nb(i)->misc = misc = - next_northbridge(misc, amd_nb_misc_ids); + next_northbridge(misc, misc_ids); node_to_amd_nb(i)->link = link = - next_northbridge(link, amd_nb_link_ids); + next_northbridge(link, link_ids); } if (amd_gart_present()) @@ -261,11 +285,19 @@ EXPORT_SYMBOL_GPL(amd_cache_northbridges); */ bool __init early_is_amd_nb(u32 device) { + const struct pci_device_id *misc_ids = amd_nb_misc_ids; const struct pci_device_id *id; u32 vendor = device & 0xffff; + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return false; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + misc_ids = hygon_nb_misc_ids; + device >>= 16; - for (id = amd_nb_misc_ids; id->vendor; id++) + for (id = misc_ids; id->vendor; id++) if (vendor == id->vendor && device == id->device) return true; return false; @@ -277,7 +309,8 @@ struct resource *amd_get_mmconfig_range(struct resource *res) u64 base, msr; unsigned int segn_busn_bits; - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) return NULL; /* assume all cpus from fam10h have mmconfig */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 84132eddb5a8..ab731ab09f06 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -224,6 +224,11 @@ static int modern_apic(void) if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && boot_cpu_data.x86 >= 0xf) return 1; + + /* Hygon systems use modern APIC */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + return 1; + return lapic_get_version() >= 0x14; } @@ -1912,6 +1917,8 @@ static int __init detect_init_APIC(void) (boot_cpu_data.x86 >= 15)) break; goto no_apic; + case X86_VENDOR_HYGON: + break; case X86_VENDOR_INTEL: if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 || (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC))) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 02e8acb134f8..47ff2976c292 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -185,6 +185,7 @@ void __init default_setup_apic_routing(void) break; } /* If P4 and above fall through */ + case X86_VENDOR_HYGON: case X86_VENDOR_AMD: def_to_bigsmp = 1; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..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; @@ -413,7 +412,7 @@ static int activate_managed(struct irq_data *irqd) if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { /* Something in the core code broke! Survive gracefully */ pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); - return EINVAL; + return -EINVAL; } ret = assign_managed_vector(irqd, vector_searchmask); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ec00d1ff5098..f7151cd03cb0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } +#ifdef CONFIG_PROC_FS static int proc_apm_show(struct seq_file *m, void *v) { unsigned short bx; @@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v) units); return 0; } +#endif static int apm(void *unused) { diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 01de31db300d..72adf6c335dc 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -64,15 +64,12 @@ void common(void) { OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); #endif -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL BLANK(); - OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops); - OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); - OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); - OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); - OFFSET(PV_CPU_iret, pv_cpu_ops, iret); - OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); - OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); + OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable); + OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable); + OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret); + OFFSET(PV_MMU_read_cr2, paravirt_patch_template, mmu.read_cr2); #endif #ifdef CONFIG_XEN @@ -99,13 +96,12 @@ void common(void) { OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); /* Layout info for cpu_entry_area */ - OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); - OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page); DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack)); DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1))); - /* Offset for sp0 and sp1 into the tss_struct */ + /* Offset for fields in tss_struct */ OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); + OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 3b9405e7ba2b..ddced33184b5 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -21,10 +21,13 @@ static char syscalls_ia32[] = { int main(void) { #ifdef CONFIG_PARAVIRT - OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); - OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); +#ifdef CONFIG_PARAVIRT_XXL + OFFSET(PV_CPU_usergs_sysret64, paravirt_patch_template, + cpu.usergs_sysret64); + OFFSET(PV_CPU_swapgs, paravirt_patch_template, cpu.swapgs); #ifdef CONFIG_DEBUG_ENTRY - OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl); + OFFSET(PV_IRQ_save_fl, paravirt_patch_template, irq.save_fl); +#endif #endif BLANK(); #endif 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/Makefile b/arch/x86/kernel/cpu/Makefile index 347137e80bf5..1f5d2291c31e 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o +obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 22ab408177b2..eeea634bee0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c) static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ - if ((c->x86 == 6)) { + if (c->x86 == 6) { /* Duron Rev A0 */ if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 40bdaea97fe7..c37e66e493bf 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -35,12 +35,10 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); -/* - * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any - * writes to SPEC_CTRL contain whatever reserved bits have been set. - */ -u64 __ro_after_init x86_spec_ctrl_base; +/* The base value of the SPEC_CTRL MSR that always has to be preserved. */ +u64 x86_spec_ctrl_base; EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); +static DEFINE_MUTEX(spec_ctrl_mutex); /* * The vendor and possibly platform specific bits which can be modified in @@ -312,6 +310,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if (cmd == SPECTRE_V2_CMD_RETPOLINE_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON && boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); return SPECTRE_V2_CMD_AUTO; @@ -325,6 +324,46 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return cmd; } +static bool stibp_needed(void) +{ + if (spectre_v2_enabled == SPECTRE_V2_NONE) + return false; + + if (!boot_cpu_has(X86_FEATURE_STIBP)) + return false; + + return true; +} + +static void update_stibp_msr(void *info) +{ + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); +} + +void arch_smt_update(void) +{ + u64 mask; + + if (!stibp_needed()) + return; + + mutex_lock(&spec_ctrl_mutex); + mask = x86_spec_ctrl_base; + if (cpu_smt_control == CPU_SMT_ENABLED) + mask |= SPEC_CTRL_STIBP; + else + mask &= ~SPEC_CTRL_STIBP; + + if (mask != x86_spec_ctrl_base) { + pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n", + cpu_smt_control == CPU_SMT_ENABLED ? + "Enabling" : "Disabling"); + x86_spec_ctrl_base = mask; + on_each_cpu(update_stibp_msr, NULL, 1); + } + mutex_unlock(&spec_ctrl_mutex); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -371,7 +410,8 @@ static void __init spectre_v2_select_mitigation(void) return; retpoline_auto: - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { retpoline_amd: if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); @@ -424,6 +464,9 @@ specv2_set_mode: setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } + + /* Enable STIBP if appropriate */ + arch_smt_update(); } #undef pr_fmt @@ -814,6 +857,8 @@ static ssize_t l1tf_show_state(char *buf) static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { + int ret; + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); @@ -831,10 +876,13 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return sprintf(buf, "Mitigation: __user pointer sanitization\n"); case X86_BUG_SPECTRE_V2: - return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + ret = sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", spectre_v2_module_string()); + return ret; case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 0c5fcbd998cf..dc1b9342e9c4 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -602,6 +602,10 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) else amd_cpuid4(index, &eax, &ebx, &ecx); amd_init_l3_cache(this_leaf, index); + } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { + cpuid_count(0x8000001d, index, &eax.full, + &ebx.full, &ecx.full, &edx); + amd_init_l3_cache(this_leaf, index); } else { cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); } @@ -625,7 +629,8 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) union _cpuid4_leaf_eax cache_eax; int i = -1; - if (c->x86_vendor == X86_VENDOR_AMD) + if (c->x86_vendor == X86_VENDOR_AMD || + c->x86_vendor == X86_VENDOR_HYGON) op = 0x8000001d; else op = 4; @@ -678,6 +683,22 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) } } +void cacheinfo_hygon_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; + + /* + * 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; +} + void init_amd_cacheinfo(struct cpuinfo_x86 *c) { @@ -691,6 +712,11 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c) } } +void init_hygon_cacheinfo(struct cpuinfo_x86 *c) +{ + num_cache_leaves = find_num_cache_leaves(c); +} + void init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ @@ -913,7 +939,8 @@ static void __cache_cpumap_setup(unsigned int cpu, int index, int index_msb, i; struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86_vendor == X86_VENDOR_AMD) { + if (c->x86_vendor == X86_VENDOR_AMD || + c->x86_vendor == X86_VENDOR_HYGON) { if (__cache_amd_cpumap_setup(cpu, index, base)) return; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 44c4ef3d989b..660d0b22e962 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 }, @@ -963,15 +963,16 @@ static const __initconst struct x86_cpu_id cpu_no_speculation[] = { static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { { X86_VENDOR_AMD }, + { X86_VENDOR_HYGON }, {} }; /* 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 +985,14 @@ 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 }, {} @@ -1076,6 +1077,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) memset(&c->x86_capability, 0, sizeof c->x86_capability); c->extended_cpuid_level = 0; + if (!have_cpuid_p()) + identify_cpu_without_cpuid(c); + /* cyrix could have cpuid enabled via c_identify()*/ if (have_cpuid_p()) { cpu_detect(c); @@ -1093,7 +1097,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); } else { - identify_cpu_without_cpuid(c); setup_clear_cpu_cap(X86_FEATURE_CPUID); } @@ -1240,10 +1243,10 @@ static void generic_identify(struct cpuinfo_x86 *c) * ESPFIX issue, we can change this. */ #ifdef CONFIG_X86_32 -# ifdef CONFIG_PARAVIRT +# ifdef CONFIG_PARAVIRT_XXL do { extern void native_iret(void); - if (pv_cpu_ops.iret == native_iret) + if (pv_ops.cpu.iret == native_iret) set_cpu_bug(c, X86_BUG_ESPFIX); } while (0); # else @@ -1531,19 +1534,8 @@ EXPORT_PER_CPU_SYMBOL(__preempt_count); /* May not be marked __init: used by software suspend */ void syscall_init(void) { - extern char _entry_trampoline[]; - extern char entry_SYSCALL_64_trampoline[]; - - int cpu = smp_processor_id(); - unsigned long SYSCALL64_entry_trampoline = - (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + - (entry_SYSCALL_64_trampoline - _entry_trampoline); - wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - if (static_cpu_has(X86_FEATURE_PTI)) - wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); - else - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1554,7 +1546,8 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1669,6 +1662,29 @@ 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 +1722,7 @@ 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/cpu.h b/arch/x86/kernel/cpu/cpu.h index 7b229afa0a37..da5446acc241 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -54,6 +54,7 @@ extern u32 get_scattered_cpuid_leaf(unsigned int level, 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 init_hygon_cacheinfo(struct cpuinfo_x86 *c); extern void detect_num_cpu_cores(struct cpuinfo_x86 *c); extern int detect_extended_topology_early(struct cpuinfo_x86 *c); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 8949b7ae6d92..d12226f60168 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -437,7 +437,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c) /* enable MAPEN */ setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable cpuid */ - setCx86_old(CX86_CCR4, getCx86_old(CX86_CCR4) | 0x80); + setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80); /* disable MAPEN */ setCx86(CX86_CCR3, ccr3); local_irq_restore(flags); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c new file mode 100644 index 000000000000..cf25405444ab --- /dev/null +++ b/arch/x86/kernel/cpu/hygon.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Hygon Processor Support for Linux + * + * Copyright (C) 2018 Chengdu Haiguang IC Design Co., Ltd. + * + * Author: Pu Wen <puwen@hygon.cn> + */ +#include <linux/io.h> + +#include <asm/cpu.h> +#include <asm/smp.h> +#include <asm/cacheinfo.h> +#include <asm/spec-ctrl.h> +#include <asm/delay.h> +#ifdef CONFIG_X86_64 +# include <asm/set_memory.h> +#endif + +#include "cpu.h" + +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + +#ifdef CONFIG_NUMA +/* + * To workaround broken NUMA config. Read the comment in + * srat_detect_node(). + */ +static int nearby_node(int apicid) +{ + int i, node; + + for (i = apicid - 1; i >= 0; i--) { + node = __apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) { + node = __apicid_to_node[i]; + if (node != NUMA_NO_NODE && node_online(node)) + return node; + } + return first_node(node_online_map); /* Shouldn't happen */ +} +#endif + +static void hygon_get_topology_early(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; +} + +/* + * Fixup core topology information for + * (1) Hygon multi-node processors + * Assumption: Number of cores in each internal node is the same. + * (2) Hygon processors supporting compute units + */ +static void hygon_get_topology(struct cpuinfo_x86 *c) +{ + u8 node_id; + int cpu = smp_processor_id(); + + /* 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); + + node_id = ecx & 0xff; + + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + + /* + * In case leaf B is available, use it to derive + * topology information. + */ + err = detect_extended_topology(c); + if (!err) + c->x86_coreid_bits = get_count_order(c->x86_max_cores); + + cacheinfo_hygon_init_llc_id(c, cpu, node_id); + } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + node_id = value & 7; + + per_cpu(cpu_llc_id, cpu) = node_id; + } else + return; + + if (nodes_per_socket > 1) + set_cpu_cap(c, X86_FEATURE_AMD_DCM); +} + +/* + * On Hygon setup the lower bits of the APIC id distinguish the cores. + * Assumes number of cores is a power of two. + */ +static void hygon_detect_cmp(struct cpuinfo_x86 *c) +{ + unsigned int bits; + int cpu = smp_processor_id(); + + bits = c->x86_coreid_bits; + /* Low order bits define the core id (index of core in socket) */ + c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); + /* Convert the initial APIC ID into the socket ID */ + 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; +} + +static void srat_detect_node(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_NUMA + int cpu = smp_processor_id(); + int node; + unsigned int apicid = c->apicid; + + node = numa_cpu_node(cpu); + if (node == NUMA_NO_NODE) + node = per_cpu(cpu_llc_id, cpu); + + /* + * On multi-fabric platform (e.g. Numascale NumaChip) a + * platform-specific handler needs to be called to fixup some + * IDs of the CPU. + */ + if (x86_cpuinit.fixup_cpu_id) + x86_cpuinit.fixup_cpu_id(c, node); + + if (!node_online(node)) { + /* + * Two possibilities here: + * + * - The CPU is missing memory and no node was created. In + * that case try picking one from a nearby CPU. + * + * - The APIC IDs differ from the HyperTransport node IDs. + * Assume they are all increased by a constant offset, but + * in the same order as the HT nodeids. If that doesn't + * result in a usable node fall back to the path for the + * previous case. + * + * This workaround operates directly on the mapping between + * APIC ID and NUMA node, assuming certain relationship + * between APIC ID, HT node ID and NUMA topology. As going + * through CPU mapping may alter the outcome, directly + * access __apicid_to_node[]. + */ + int ht_nodeid = c->initial_apicid; + + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + node = __apicid_to_node[ht_nodeid]; + /* Pick a nearby node */ + if (!node_online(node)) + node = nearby_node(apicid); + } + numa_set_node(cpu, node); +#endif +} + +static void early_init_hygon_mc(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + unsigned int bits, ecx; + + /* Multi core CPU? */ + if (c->extended_cpuid_level < 0x80000008) + return; + + ecx = cpuid_ecx(0x80000008); + + c->x86_max_cores = (ecx & 0xff) + 1; + + /* CPU telling us the core id bits shift? */ + bits = (ecx >> 12) & 0xF; + + /* Otherwise recompute */ + if (bits == 0) { + while ((1 << bits) < c->x86_max_cores) + bits++; + } + + c->x86_coreid_bits = bits; +#endif +} + +static void bsp_init_hygon(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 + unsigned long long tseg; + + /* + * Split up direct mapping around the TSEG SMM area. + * Don't do it for gbpages because there seems very little + * benefit in doing so. + */ + if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { + unsigned long pfn = tseg >> PAGE_SHIFT; + + pr_debug("tseg: %010llx\n", tseg); + if (pfn_range_is_mapped(pfn, pfn + 1)) + set_memory_4k((unsigned long)__va(tseg), 1); + } +#endif + + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { + u64 val; + + rdmsrl(MSR_K7_HWCR, val); + if (!(val & BIT(24))) + pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n"); + } + + if (cpu_has(c, X86_FEATURE_MWAITX)) + use_mwaitx_delay(); + + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 ecx; + + ecx = cpuid_ecx(0x8000001e); + nodes_per_socket = ((ecx >> 8) & 7) + 1; + } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { + u64 value; + + rdmsrl(MSR_FAM10H_NODE_ID, value); + nodes_per_socket = ((value >> 3) & 7) + 1; + } + + if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && + !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << 10; + } + } +} + +static void early_init_hygon(struct cpuinfo_x86 *c) +{ + u32 dummy; + + early_init_hygon_mc(c); + + set_cpu_cap(c, X86_FEATURE_K8); + + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + + /* + * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate + * with P/T states and does not stop in deep C-states + */ + if (c->x86_power & (1 << 8)) { + set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + } + + /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ + if (c->x86_power & BIT(12)) + set_cpu_cap(c, X86_FEATURE_ACC_POWER); + +#ifdef CONFIG_X86_64 + set_cpu_cap(c, X86_FEATURE_SYSCALL32); +#endif + +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) + /* + * ApicID can always be treated as an 8-bit value for Hygon APIC So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally. + */ + if (boot_cpu_has(X86_FEATURE_APIC)) + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); +#endif + + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + + hygon_get_topology_early(c); +} + +static void init_hygon(struct cpuinfo_x86 *c) +{ + early_init_hygon(c); + + /* + * Bit 31 in normal CPUID used for nonstandard 3DNow ID; + * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway + */ + clear_cpu_cap(c, 0*32+31); + + set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* get apicid instead of initial apic id from cpuid */ + c->apicid = hard_smp_processor_id(); + + set_cpu_cap(c, X86_FEATURE_ZEN); + set_cpu_cap(c, X86_FEATURE_CPB); + + cpu_detect_cache_sizes(c); + + hygon_detect_cmp(c); + hygon_get_topology(c); + srat_detect_node(c); + + init_hygon_cacheinfo(c); + + if (cpu_has(c, X86_FEATURE_XMM2)) { + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } + } + + /* + * Hygon processors have APIC timer running in deep C states. + */ + set_cpu_cap(c, X86_FEATURE_ARAT); + + /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */ + if (!cpu_has(c, X86_FEATURE_XENPV)) + set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); +} + +static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) +{ + u32 ebx, eax, ecx, edx; + u16 mask = 0xfff; + + if (c->extended_cpuid_level < 0x80000006) + return; + + cpuid(0x80000006, &eax, &ebx, &ecx, &edx); + + tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask; + tlb_lli_4k[ENTRIES] = ebx & mask; + + /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!((eax >> 16) & mask)) + tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff; + else + tlb_lld_2m[ENTRIES] = (eax >> 16) & mask; + + /* a 4M entry uses two 2M entries */ + tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1; + + /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */ + if (!(eax & mask)) { + cpuid(0x80000005, &eax, &ebx, &ecx, &edx); + tlb_lli_2m[ENTRIES] = eax & 0xff; + } else + tlb_lli_2m[ENTRIES] = eax & mask; + + tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; +} + +static const struct cpu_dev hygon_cpu_dev = { + .c_vendor = "Hygon", + .c_ident = { "HygonGenuine" }, + .c_early_init = early_init_hygon, + .c_detect_tlb = cpu_detect_tlb_hygon, + .c_bsp_init = bsp_init_hygon, + .c_init = init_hygon, + .c_x86_vendor = X86_VENDOR_HYGON, +}; + +cpu_dev_register(hygon_cpu_dev); 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.h b/arch/x86/kernel/cpu/intel_rdt.h index 4e588f36228f..3736f6dc9545 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e) e <= QOS_L3_MBM_LOCAL_EVENT_ID); } +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /** * struct rdt_resource - attributes of an RDT resource * @rid: The index of the resource @@ -423,16 +428,19 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (void *data, struct rdt_resource *r, - struct rdt_domain *d); + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); struct list_head evt_list; int num_rmid; unsigned int mon_scale; unsigned long fflags; }; -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -521,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive); + unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, - u32 cbm); + unsigned long cbm); enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); int rdtgroup_tasks_assigned(struct rdtgroup *r); int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); int rdt_pseudo_lock_init(void); void rdt_pseudo_lock_release(void); @@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index af358ca05160..27937458c231 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; - char *buf = _buf; + unsigned long bw_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if (!bw_validate(buf, &data, r)) + if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = data; + d->new_ctrl = bw_val; d->have_new_ctrl = true; return 0; @@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } -struct rdt_cbm_parse_data { - struct rdtgroup *rdtgrp; - char *buf; -}; - /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - struct rdt_cbm_parse_data *data = _data; struct rdtgroup *rdtgrp = data->rdtgrp; u32 cbm_val; @@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) static int parse_line(char *line, struct rdt_resource *r, struct rdtgroup *rdtgrp) { - struct rdt_cbm_parse_data data; + struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + next: if (!line || line[0] == '\0') return 0; @@ -403,8 +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 40f3903ae5d9..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 @@ -797,25 +789,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) /** * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked * @d: RDT domain - * @_cbm: CBM to test + * @cbm: CBM to test * - * @d represents a cache instance and @_cbm a capacity bitmask that is - * considered for it. Determine if @_cbm overlaps with any existing + * @d represents a cache instance and @cbm a capacity bitmask that is + * considered for it. Determine if @cbm overlaps with any existing * pseudo-locked region on @d. * - * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: true if @cbm overlaps with pseudo-locked region on @d, false * otherwise. */ -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *cbm_b; unsigned int cbm_len; + unsigned long cbm_b; if (d->plr) { cbm_len = d->plr->r->cache.cbm_len; - cbm_b = (unsigned long *)&d->plr->cbm; - if (bitmap_intersects(cbm, cbm_b, cbm_len)) + cbm_b = d->plr->cbm; + if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) return true; } return false; @@ -886,31 +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. @@ -932,157 +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); @@ -1114,6 +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)) { @@ -1121,13 +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); @@ -1171,7 +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) @@ -1427,6 +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 b799c00bef09..f27b8115ffa2 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...) * limited as the number of resources grows. */ static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} static void closid_init(void) { @@ -111,6 +117,7 @@ static void closid_init(void) /* CLOSID 0 is always reserved for the default group */ closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) @@ -261,17 +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; } @@ -802,7 +819,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (!closid_allocated(i)) continue; mode = rdtgroup_mode_by_closid(i); @@ -954,7 +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. @@ -968,33 +1056,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * is false then overlaps with any resource group or hardware entities * will be considered. * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * * Return: false if CBM does not overlap, true if it does. */ -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _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) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *ctrl_b; enum rdtgrp_mode mode; + unsigned long ctrl_b; u32 *ctrl; int i; /* Check for any overlap with regions used by hardware directly */ if (!exclusive) { - if (bitmap_intersects(cbm, - (unsigned long *)&r->cache.shareable_bits, - r->cache.cbm_len)) + ctrl_b = r->cache.shareable_bits; + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) return true; } /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { - ctrl_b = (unsigned long *)ctrl; + for (i = 0; i < closids_supported(); i++, ctrl++) { + ctrl_b = *ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { - if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) { if (exclusive) { if (mode == RDT_MODE_EXCLUSIVE) return true; @@ -1009,6 +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 @@ -1024,16 +1148,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; struct rdt_resource *r; + bool has_cache = false; struct rdt_domain *d; for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; list_for_each_entry(d, &r->domains, list) { if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], - rdtgrp->closid, false)) + rdtgrp->closid, false)) { + rdt_last_cmd_puts("schemata overlaps\n"); return false; + } } } + if (!has_cache) { + rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n"); + return false; + } + return true; } @@ -1085,7 +1220,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, rdtgrp->mode = RDT_MODE_SHAREABLE; } else if (!strcmp(buf, "exclusive")) { if (!rdtgroup_mode_test_exclusive(rdtgrp)) { - rdt_last_cmd_printf("schemata overlaps\n"); ret = -EINVAL; goto out; } @@ -1121,15 +1255,18 @@ out: * computed by first dividing the total cache size by the CBM length to * determine how many bytes each bit in the bitmask represents. The result * is multiplied with the number of bits set in the bitmask. + * + * @cbm is unsigned long, even if only 32 bits are used to make the + * bitmap functions work correctly. */ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, - struct rdt_domain *d, u32 cbm) + struct rdt_domain *d, unsigned long cbm) { struct cpu_cacheinfo *ci; unsigned int size = 0; int num_b, i; - num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + num_b = bitmap_weight(&cbm, r->cache.cbm_len); ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); for (i = 0; i < ci->num_leaves; i++) { if (ci->info_list[i].level == r->cache_level) { @@ -1155,8 +1292,9 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; - bool sep = false; - u32 cbm; + int ret = 0; + bool sep; + u32 ctrl; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -1165,15 +1303,23 @@ 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; } for_each_alloc_enabled_rdt_resource(r) { + sep = false; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(d, &r->domains, list) { if (sep) @@ -1181,8 +1327,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - cbm = d->ctrl_val[rdtgrp->closid]; - size = rdtgroup_cbm_to_size(r, d, cbm); + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); } seq_printf(s, "%d=%u", d->id, size); sep = true; @@ -1193,7 +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. */ @@ -2327,28 +2478,48 @@ 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) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + 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; ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (closid_allocated(i) && i != closid) { 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) @@ -2361,9 +2532,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) * modify the CBM based on system availability. */ cbm_ensure_valid(&d->new_ctrl, r); - if (bitmap_weight((unsigned long *) &d->new_ctrl, - r->cache.cbm_len) < - r->cache.min_cbm_bits) { + /* + * Assign the u32 CBM to an unsigned long to ensure + * that bitmap_weight() does not access out-of-bound + * memory. + */ + tmp_cbm = d->new_ctrl; + if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < + r->cache.min_cbm_bits) { rdt_last_cmd_printf("no space on %s:%d\n", r->name, d->id); return -ENOSPC; @@ -2373,6 +2549,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; ret = update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("failed to initialize allocations\n"); @@ -2760,6 +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-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index f34d89c01edc..44396d521987 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -336,7 +336,8 @@ int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) = void __init mcheck_vendor_init_severity(void) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) mce_severity = mce_severity_amd; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 953b3ce92dcc..8cb3c02980cf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -270,7 +270,7 @@ static void print_mce(struct mce *m) { __print_mce(m); - if (m->cpuvendor != X86_VENDOR_AMD) + if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON) pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } @@ -508,9 +508,9 @@ static int mce_usable_address(struct mce *m) bool mce_is_memory_error(struct mce *m) { - if (m->cpuvendor == X86_VENDOR_AMD) { + if (m->cpuvendor == X86_VENDOR_AMD || + m->cpuvendor == X86_VENDOR_HYGON) { return amd_mce_is_memory_error(m); - } else if (m->cpuvendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -539,6 +539,9 @@ static bool mce_is_correctable(struct mce *m) if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; + if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED) + return false; + if (m->status & MCI_STATUS_UC) return false; @@ -1315,7 +1318,7 @@ 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); } @@ -1705,7 +1708,7 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) */ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) { - if (c->x86_vendor == X86_VENDOR_AMD) { + if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) { mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); @@ -1746,6 +1749,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_amd_feature_init(c); break; } + + case X86_VENDOR_HYGON: + mce_hygon_feature_init(c); + break; + case X86_VENDOR_CENTAUR: mce_centaur_feature_init(c); break; @@ -1971,12 +1979,14 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide. + * Don't clear on Intel or AMD or Hygon CPUs. Some of these MSRs + * are socket-wide. * Disabling them for just a single offlined CPU is bad, since it will * inhibit reporting for all shared resources on the socket like the * last level cache (LLC), the integrated memory controller (iMC), etc. */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || boot_cpu_data.x86_vendor == X86_VENDOR_AMD) return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 0624957aa068..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - return UCODE_UPDATED; +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 97ccf4c3b45b..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index ad12733f6058..1c72f3819eb1 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -199,6 +199,16 @@ static unsigned long hv_get_tsc_khz(void) return freq / 1000; } +#if defined(CONFIG_SMP) && IS_ENABLED(CONFIG_HYPERV) +static void __init hv_smp_prepare_boot_cpu(void) +{ + native_smp_prepare_boot_cpu(); +#if defined(CONFIG_X86_64) && defined(CONFIG_PARAVIRT_SPINLOCKS) + hv_init_spinlocks(); +#endif +} +#endif + static void __init ms_hyperv_init_platform(void) { int hv_host_info_eax; @@ -303,6 +313,10 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) alloc_intr_gate(HYPERV_STIMER0_VECTOR, hv_stimer0_callback_vector); + +# ifdef CONFIG_SMP + smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; +# endif #endif } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 765afd599039..3668c5df90c6 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -831,7 +831,8 @@ int __init amd_special_default_mtrr(void) { u32 l, h; - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) return 0; if (boot_cpu_data.x86 < 0xf) return 0; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 9a19c800fe40..507039c20128 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -127,7 +127,7 @@ static void __init set_num_var_ranges(void) if (use_intel()) rdmsr(MSR_MTRRcap, config, dummy); - else if (is_cpu(AMD)) + else if (is_cpu(AMD) || is_cpu(HYGON)) config = 2; else if (is_cpu(CYRIX) || is_cpu(CENTAUR)) config = 8; diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d389083330c5..9556930cd8c1 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -46,6 +46,7 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) { /* returns the bit offset of the performance counter register */ switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_HYGON: case X86_VENDOR_AMD: if (msr >= MSR_F15H_PERF_CTR) return (msr - MSR_F15H_PERF_CTR) >> 1; @@ -74,6 +75,7 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) { /* returns the bit offset of the event selection register */ switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_HYGON: case X86_VENDOR_AMD: if (msr >= MSR_F15H_PERF_CTL) return (msr - MSR_F15H_PERF_CTL) >> 1; diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 8e005329648b..d9ab49bed8af 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -97,14 +97,14 @@ static void __init vmware_sched_clock_setup(void) d->cyc2ns_offset = mul_u64_u32_shr(tsc_now, d->cyc2ns_mul, d->cyc2ns_shift); - pv_time_ops.sched_clock = vmware_sched_clock; + pv_ops.time.sched_clock = vmware_sched_clock; pr_info("using sched offset of %llu ns\n", d->cyc2ns_offset); } static void __init vmware_paravirt_ops_setup(void) { pv_info.name = "VMware hypervisor"; - pv_cpu_ops.io_delay = paravirt_nop; + pv_ops.cpu.io_delay = paravirt_nop; if (vmware_tsc_khz && vmw_sched_clock) vmware_sched_clock_setup(); diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index 4f2e0778feac..eb8ab3915268 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -11,40 +11,62 @@ #include <linux/uaccess.h> #include <linux/io.h> -/** - * copy_oldmem_page - copy one page from "oldmem" - * @pfn: page frame number to be copied - * @buf: target memory address for the copy; this can be in kernel address - * space or user address space (see @userbuf) - * @csize: number of bytes to copy - * @offset: offset in bytes into the page (based on pfn) to begin the copy - * @userbuf: if set, @buf is in user address space, use copy_to_user(), - * otherwise @buf is in kernel address space, use memcpy(). - * - * Copy a page from "oldmem". For this page, there is no pte mapped - * in the current kernel. We stitch up a pte, similar to kmap_atomic. - */ -ssize_t copy_oldmem_page(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, int userbuf) +static ssize_t __copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf, + bool encrypted) { void *vaddr; if (!csize) return 0; - vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE); + if (encrypted) + vaddr = (__force void *)ioremap_encrypted(pfn << PAGE_SHIFT, PAGE_SIZE); + else + vaddr = (__force void *)ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!vaddr) return -ENOMEM; if (userbuf) { - if (copy_to_user(buf, vaddr + offset, csize)) { - iounmap(vaddr); + if (copy_to_user((void __user *)buf, vaddr + offset, csize)) { + iounmap((void __iomem *)vaddr); return -EFAULT; } } else memcpy(buf, vaddr + offset, csize); set_iounmap_nonlazy(); - iounmap(vaddr); + iounmap((void __iomem *)vaddr); return csize; } + +/** + * copy_oldmem_page - copy one page of memory + * @pfn: page frame number to be copied + * @buf: target memory address for the copy; this can be in kernel address + * space or user address space (see @userbuf) + * @csize: number of bytes to copy + * @offset: offset in bytes into the page (based on pfn) to begin the copy + * @userbuf: if set, @buf is in user address space, use copy_to_user(), + * otherwise @buf is in kernel address space, use memcpy(). + * + * Copy a page from the old kernel's memory. For this page, there is no pte + * mapped in the current kernel. We stitch up a pte, similar to kmap_atomic. + */ +ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf) +{ + return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, false); +} + +/** + * copy_oldmem_page_encrypted - same as copy_oldmem_page() above but ioremap the + * memory with the encryption mask set to accomodate kdump on SME-enabled + * machines. + */ +ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, size_t csize, + unsigned long offset, int userbuf) +{ + return __copy_oldmem_page(pfn, buf, csize, offset, userbuf, true); +} diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f56895106ccf..2b5886401e5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -146,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * they can be printed in the right context. */ if (!partial && on_stack(info, regs, sizeof(*regs))) { - __show_regs(regs, 0); + __show_regs(regs, SHOW_REGS_SHORT); } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, IRET_FRAME_SIZE)) { @@ -344,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) oops_exit(); /* Executive summary in case the oops scrolled away */ - __show_regs(&exec_summary_regs, true); + __show_regs(&exec_summary_regs, SHOW_REGS_ALL); if (!signr) return; @@ -407,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err) void show_regs(struct pt_regs *regs) { - bool all = true; - show_regs_print_info(KERN_DEFAULT); - if (IS_ENABLED(CONFIG_X86_32)) - all = !user_mode(regs); - - __show_regs(regs, all); + __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL); /* * When in-kernel, we also print out the stack at the time of the fault.. diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index f260e452e4f8..e8c8c5d78dbd 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -7,11 +7,17 @@ #include <linux/eisa.h> #include <linux/io.h> +#include <xen/xen.h> + static __init int eisa_bus_probe(void) { - void __iomem *p = ioremap(0x0FFFD9, 4); + void __iomem *p; + + if (xen_pv_domain() && !xen_initial_domain()) + return 0; - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + p = ioremap(0x0FFFD9, 4); + if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) EISA_bus = 1; iounmap(p); return 0; 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/head32.c b/arch/x86/kernel/head32.c index ec6fefbfd3c0..76fa3b836598 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -37,6 +37,7 @@ asmlinkage __visible void __init i386_start_kernel(void) cr4_init_shadow(); sanitize_boot_params(&boot_params); + x86_verify_bootdata_version(); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8047379e575a..5dc377dc9d7b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -35,6 +35,7 @@ #include <asm/bootparam_utils.h> #include <asm/microcode.h> #include <asm/kasan.h> +#include <asm/fixmap.h> /* * Manage page tables very early on. @@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { + unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[511] += load_delta; pmd = fixup_pointer(level2_fixmap_pgt, physaddr); - pmd[506] += load_delta; + for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) + pmd[i] += load_delta; /* * Set up the identity mapping for the switchover. These @@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr, sme_encrypt_kernel(bp); /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (mem_encrypt_active()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* * Return the SME encryption mask (if SME is active) to be used as a * modifier for the initial pgdir entry programmed into CR3. */ @@ -439,6 +457,8 @@ void __init x86_64_start_reservations(char *real_mode_data) if (!boot_params.hdr.version) copy_bootdata(__va(real_mode_data)); + x86_verify_bootdata_version(); + x86_early_init_platform_quirks(); switch (boot_params.hdr.hardware_subarch) { diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 15ebc2fc166e..747c758f67b7 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -24,8 +24,9 @@ #include "../entry/calling.h" #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/fixmap.h> -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/asm-offsets.h> #include <asm/paravirt.h> #define GET_CR2_INTO(reg) GET_CR2_INTO_RAX ; movq %rax, reg @@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt) KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_fixmap_pgt) - .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ - .fill 5,8,0 + .fill (512 - 4 - FIXMAP_PMD_NUM),8,0 + pgtno = 0 + .rept (FIXMAP_PMD_NUM) + .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \ + + _PAGE_TABLE_NOENC; + pgtno = pgtno + 1 + .endr + /* 6 MB reserved space + a 2MB hole */ + .fill 4,8,0 NEXT_PAGE(level1_fixmap_pgt) + .rept (FIXMAP_PMD_NUM) .fill 512,8,0 + .endr #undef PMDS 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..c33b06f5faa4 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1020,64 +1020,18 @@ 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; - -#ifdef CONFIG_X86_64 - is_in_entry_trampoline_section = - (addr >= (unsigned long)__entry_trampoline_start && - addr < (unsigned long)__entry_trampoline_end); -#endif return (addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end) || - is_in_entry_trampoline_section; + addr < (unsigned long)__entry_text_end); } int __init arch_init_kprobes(void) 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/kvm.c b/arch/x86/kernel/kvm.c index d9b71924c23c..ba4bfb7f6a36 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -283,7 +283,7 @@ static void __init paravirt_ops_setup(void) pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) - pv_cpu_ops.io_delay = kvm_io_delay; + pv_ops.cpu.io_delay = kvm_io_delay; #ifdef CONFIG_X86_IO_APIC no_timer_check = 1; @@ -632,14 +632,14 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { has_steal_clock = 1; - pv_time_ops.steal_clock = kvm_steal_clock; + pv_ops.time.steal_clock = kvm_steal_clock; } if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { - pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; - pv_mmu_ops.tlb_remove_table = tlb_remove_table; + pv_ops.mmu.flush_tlb_others = kvm_flush_tlb_others; + pv_ops.mmu.tlb_remove_table = tlb_remove_table; } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -850,13 +850,14 @@ void __init kvm_spinlock_init(void) return; __pv_init_lock_hash(); - pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; - pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); - pv_lock_ops.wait = kvm_wait; - pv_lock_ops.kick = kvm_kick_cpu; + pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_ops.lock.queued_spin_unlock = + PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_ops.lock.wait = kvm_wait; + pv_ops.lock.kick = kvm_kick_cpu; if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { - pv_lock_ops.vcpu_is_preempted = + pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(__kvm_vcpu_is_preempted); } } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1e6764648af3..30084ecaa20f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <linux/sched/clock.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/set_memory.h> #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> @@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) static struct pvclock_vsyscall_time_info - hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); -static struct pvclock_wall_clock wall_clock; + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __bss_decrypted; static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +static struct pvclock_vsyscall_time_info *hvclock_mem; static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) { @@ -116,13 +118,13 @@ static u64 kvm_sched_clock_read(void) static inline void kvm_sched_clock_init(bool stable) { if (!stable) { - pv_time_ops.sched_clock = kvm_clock_read; + pv_ops.time.sched_clock = kvm_clock_read; clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); - pv_time_ops.sched_clock = kvm_sched_clock_read; + pv_ops.time.sched_clock = kvm_sched_clock_read; pr_info("kvm-clock: using sched offset of %llu cycles", kvm_sched_clock_offset); @@ -236,6 +238,45 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static void __init kvmclock_init_mem(void) +{ + unsigned long ncpus; + unsigned int order; + struct page *p; + int r; + + if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus()) + return; + + ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE; + order = get_order(ncpus * sizeof(*hvclock_mem)); + + p = alloc_pages(GFP_KERNEL, order); + if (!p) { + pr_warn("%s: failed to alloc %d pages", __func__, (1U << order)); + return; + } + + hvclock_mem = page_address(p); + + /* + * hvclock is shared between the guest and the hypervisor, must + * be mapped decrypted. + */ + if (sev_active()) { + r = set_memory_decrypted((unsigned long) hvclock_mem, + 1UL << order); + if (r) { + __free_pages(p, order); + hvclock_mem = NULL; + pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n"); + return; + } + } + + memset(hvclock_mem, 0, PAGE_SIZE << order); +} + static int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 @@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void) kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif + + kvmclock_init_mem(); + return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); @@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu) /* Use the static page for the first CPUs, allocate otherwise */ if (cpu < HVC_BOOT_ARRAY_SIZE) p = &hv_clock_boot[cpu]; + else if (hvclock_mem) + p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE; else - p = kzalloc(sizeof(*p), GFP_KERNEL); + return -ENOMEM; per_cpu(hv_clock_per_cpu, cpu) = p; return p ? 0 : -ENOMEM; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 733e6ace0fa4..ab18e0884dc6 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -273,7 +273,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) map_ldt_struct_to_user(mm); va = (unsigned long)ldt_slot_va(slot); - flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0); + flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false); ldt->slot = slot; return 0; 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/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 71f2d1125ec0..4f75d0cf6305 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -17,7 +17,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock); bool pv_is_native_spin_unlock(void) { - return pv_lock_ops.queued_spin_unlock.func == + return pv_ops.lock.queued_spin_unlock.func == __raw_callee_save___native_queued_spin_unlock; } @@ -29,17 +29,6 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted); bool pv_is_native_vcpu_is_preempted(void) { - return pv_lock_ops.vcpu_is_preempted.func == + return pv_ops.lock.vcpu_is_preempted.func == __raw_callee_save___native_vcpu_is_preempted; } - -struct pv_lock_ops pv_lock_ops = { -#ifdef CONFIG_SMP - .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, - .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), - .wait = paravirt_nop, - .kick = paravirt_nop, - .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted), -#endif /* SMP */ -}; -EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index afdb303285f8..e4d4df37922a 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -81,17 +81,15 @@ struct branch { u32 delta; } __attribute__((packed)); -unsigned paravirt_patch_call(void *insnbuf, - const void *target, u16 tgt_clobbers, - unsigned long addr, u16 site_clobbers, - unsigned len) +static unsigned paravirt_patch_call(void *insnbuf, const void *target, + unsigned long addr, unsigned len) { struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5); if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } @@ -103,15 +101,16 @@ unsigned paravirt_patch_call(void *insnbuf, return 5; } -unsigned paravirt_patch_jmp(void *insnbuf, const void *target, - unsigned long addr, unsigned len) +#ifdef CONFIG_PARAVIRT_XXL +static unsigned paravirt_patch_jmp(void *insnbuf, const void *target, + unsigned long addr, unsigned len) { struct branch *b = insnbuf; unsigned long delta = (unsigned long)target - (addr+5); if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } @@ -121,6 +120,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, return 5; } +#endif DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); @@ -130,29 +130,14 @@ void __init native_pv_lock_init(void) static_branch_disable(&virt_spin_lock_key); } -/* - * Neat trick to map patch type back to the call within the - * corresponding structure. - */ -static void *get_call_destination(u8 type) -{ - struct paravirt_patch_template tmpl = { - .pv_init_ops = pv_init_ops, - .pv_time_ops = pv_time_ops, - .pv_cpu_ops = pv_cpu_ops, - .pv_irq_ops = pv_irq_ops, - .pv_mmu_ops = pv_mmu_ops, -#ifdef CONFIG_PARAVIRT_SPINLOCKS - .pv_lock_ops = pv_lock_ops, -#endif - }; - return *((void **)&tmpl + type); -} - -unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, +unsigned paravirt_patch_default(u8 type, void *insnbuf, unsigned long addr, unsigned len) { - void *opfunc = get_call_destination(type); + /* + * Neat trick to map patch type back to the call within the + * corresponding structure. + */ + void *opfunc = *((void **)&pv_ops + type); unsigned ret; if (opfunc == NULL) @@ -167,15 +152,15 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, else if (opfunc == _paravirt_ident_64) ret = paravirt_patch_ident_64(insnbuf, len); - else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || - type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) +#ifdef CONFIG_PARAVIRT_XXL + else if (type == PARAVIRT_PATCH(cpu.iret) || + type == PARAVIRT_PATCH(cpu.usergs_sysret64)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); +#endif else - /* Otherwise call the function; assume target could - clobber any caller-save reg */ - ret = paravirt_patch_call(insnbuf, opfunc, CLBR_ANY, - addr, clobbers, len); + /* Otherwise call the function. */ + ret = paravirt_patch_call(insnbuf, opfunc, addr, len); return ret; } @@ -281,6 +266,7 @@ void paravirt_flush_lazy_mmu(void) preempt_enable(); } +#ifdef CONFIG_PARAVIRT_XXL void paravirt_start_context_switch(struct task_struct *prev) { BUG_ON(preemptible()); @@ -301,6 +287,7 @@ void paravirt_end_context_switch(struct task_struct *next) if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES)) arch_enter_lazy_mmu_mode(); } +#endif enum paravirt_lazy_mode paravirt_get_lazy_mode(void) { @@ -312,85 +299,16 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) struct pv_info pv_info = { .name = "bare hardware", +#ifdef CONFIG_PARAVIRT_XXL .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ #ifdef CONFIG_X86_64 .extra_user_64bit_cs = __USER_CS, #endif -}; - -struct pv_init_ops pv_init_ops = { - .patch = native_patch, -}; - -struct pv_time_ops pv_time_ops = { - .sched_clock = native_sched_clock, - .steal_clock = native_steal_clock, -}; - -__visible struct pv_irq_ops pv_irq_ops = { - .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), - .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), - .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), - .irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), - .safe_halt = native_safe_halt, - .halt = native_halt, -}; - -__visible struct pv_cpu_ops pv_cpu_ops = { - .cpuid = native_cpuid, - .get_debugreg = native_get_debugreg, - .set_debugreg = native_set_debugreg, - .read_cr0 = native_read_cr0, - .write_cr0 = native_write_cr0, - .write_cr4 = native_write_cr4, -#ifdef CONFIG_X86_64 - .read_cr8 = native_read_cr8, - .write_cr8 = native_write_cr8, #endif - .wbinvd = native_wbinvd, - .read_msr = native_read_msr, - .write_msr = native_write_msr, - .read_msr_safe = native_read_msr_safe, - .write_msr_safe = native_write_msr_safe, - .read_pmc = native_read_pmc, - .load_tr_desc = native_load_tr_desc, - .set_ldt = native_set_ldt, - .load_gdt = native_load_gdt, - .load_idt = native_load_idt, - .store_tr = native_store_tr, - .load_tls = native_load_tls, -#ifdef CONFIG_X86_64 - .load_gs_index = native_load_gs_index, -#endif - .write_ldt_entry = native_write_ldt_entry, - .write_gdt_entry = native_write_gdt_entry, - .write_idt_entry = native_write_idt_entry, - - .alloc_ldt = paravirt_nop, - .free_ldt = paravirt_nop, - - .load_sp0 = native_load_sp0, - -#ifdef CONFIG_X86_64 - .usergs_sysret64 = native_usergs_sysret64, -#endif - .iret = native_iret, - .swapgs = native_swapgs, - - .set_iopl_mask = native_set_iopl_mask, - .io_delay = native_io_delay, - - .start_context_switch = paravirt_nop, - .end_context_switch = paravirt_nop, }; -/* At this point, native_get/set_debugreg has real function entries */ -NOKPROBE_SYMBOL(native_get_debugreg); -NOKPROBE_SYMBOL(native_set_debugreg); -NOKPROBE_SYMBOL(native_load_idt); - #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) /* 32-bit pagetable entries */ #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) @@ -399,85 +317,171 @@ NOKPROBE_SYMBOL(native_load_idt); #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) #endif -struct pv_mmu_ops pv_mmu_ops __ro_after_init = { +struct paravirt_patch_template pv_ops = { + /* Init ops. */ + .init.patch = native_patch, - .read_cr2 = native_read_cr2, - .write_cr2 = native_write_cr2, - .read_cr3 = __native_read_cr3, - .write_cr3 = native_write_cr3, + /* Time ops. */ + .time.sched_clock = native_sched_clock, + .time.steal_clock = native_steal_clock, - .flush_tlb_user = native_flush_tlb, - .flush_tlb_kernel = native_flush_tlb_global, - .flush_tlb_one_user = native_flush_tlb_one_user, - .flush_tlb_others = native_flush_tlb_others, - .tlb_remove_table = (void (*)(struct mmu_gather *, void *))tlb_remove_page, + /* Cpu ops. */ + .cpu.io_delay = native_io_delay, - .pgd_alloc = __paravirt_pgd_alloc, - .pgd_free = paravirt_nop, +#ifdef CONFIG_PARAVIRT_XXL + .cpu.cpuid = native_cpuid, + .cpu.get_debugreg = native_get_debugreg, + .cpu.set_debugreg = native_set_debugreg, + .cpu.read_cr0 = native_read_cr0, + .cpu.write_cr0 = native_write_cr0, + .cpu.write_cr4 = native_write_cr4, +#ifdef CONFIG_X86_64 + .cpu.read_cr8 = native_read_cr8, + .cpu.write_cr8 = native_write_cr8, +#endif + .cpu.wbinvd = native_wbinvd, + .cpu.read_msr = native_read_msr, + .cpu.write_msr = native_write_msr, + .cpu.read_msr_safe = native_read_msr_safe, + .cpu.write_msr_safe = native_write_msr_safe, + .cpu.read_pmc = native_read_pmc, + .cpu.load_tr_desc = native_load_tr_desc, + .cpu.set_ldt = native_set_ldt, + .cpu.load_gdt = native_load_gdt, + .cpu.load_idt = native_load_idt, + .cpu.store_tr = native_store_tr, + .cpu.load_tls = native_load_tls, +#ifdef CONFIG_X86_64 + .cpu.load_gs_index = native_load_gs_index, +#endif + .cpu.write_ldt_entry = native_write_ldt_entry, + .cpu.write_gdt_entry = native_write_gdt_entry, + .cpu.write_idt_entry = native_write_idt_entry, - .alloc_pte = paravirt_nop, - .alloc_pmd = paravirt_nop, - .alloc_pud = paravirt_nop, - .alloc_p4d = paravirt_nop, - .release_pte = paravirt_nop, - .release_pmd = paravirt_nop, - .release_pud = paravirt_nop, - .release_p4d = paravirt_nop, + .cpu.alloc_ldt = paravirt_nop, + .cpu.free_ldt = paravirt_nop, - .set_pte = native_set_pte, - .set_pte_at = native_set_pte_at, - .set_pmd = native_set_pmd, + .cpu.load_sp0 = native_load_sp0, - .ptep_modify_prot_start = __ptep_modify_prot_start, - .ptep_modify_prot_commit = __ptep_modify_prot_commit, +#ifdef CONFIG_X86_64 + .cpu.usergs_sysret64 = native_usergs_sysret64, +#endif + .cpu.iret = native_iret, + .cpu.swapgs = native_swapgs, + + .cpu.set_iopl_mask = native_set_iopl_mask, + + .cpu.start_context_switch = paravirt_nop, + .cpu.end_context_switch = paravirt_nop, + + /* Irq ops. */ + .irq.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), + .irq.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), + .irq.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), + .irq.irq_enable = __PV_IS_CALLEE_SAVE(native_irq_enable), + .irq.safe_halt = native_safe_halt, + .irq.halt = native_halt, +#endif /* CONFIG_PARAVIRT_XXL */ + + /* Mmu ops. */ + .mmu.flush_tlb_user = native_flush_tlb, + .mmu.flush_tlb_kernel = native_flush_tlb_global, + .mmu.flush_tlb_one_user = native_flush_tlb_one_user, + .mmu.flush_tlb_others = native_flush_tlb_others, + .mmu.tlb_remove_table = + (void (*)(struct mmu_gather *, void *))tlb_remove_page, + + .mmu.exit_mmap = paravirt_nop, + +#ifdef CONFIG_PARAVIRT_XXL + .mmu.read_cr2 = native_read_cr2, + .mmu.write_cr2 = native_write_cr2, + .mmu.read_cr3 = __native_read_cr3, + .mmu.write_cr3 = native_write_cr3, + + .mmu.pgd_alloc = __paravirt_pgd_alloc, + .mmu.pgd_free = paravirt_nop, + + .mmu.alloc_pte = paravirt_nop, + .mmu.alloc_pmd = paravirt_nop, + .mmu.alloc_pud = paravirt_nop, + .mmu.alloc_p4d = paravirt_nop, + .mmu.release_pte = paravirt_nop, + .mmu.release_pmd = paravirt_nop, + .mmu.release_pud = paravirt_nop, + .mmu.release_p4d = paravirt_nop, + + .mmu.set_pte = native_set_pte, + .mmu.set_pte_at = native_set_pte_at, + .mmu.set_pmd = native_set_pmd, + + .mmu.ptep_modify_prot_start = __ptep_modify_prot_start, + .mmu.ptep_modify_prot_commit = __ptep_modify_prot_commit, #if CONFIG_PGTABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE - .set_pte_atomic = native_set_pte_atomic, - .pte_clear = native_pte_clear, - .pmd_clear = native_pmd_clear, + .mmu.set_pte_atomic = native_set_pte_atomic, + .mmu.pte_clear = native_pte_clear, + .mmu.pmd_clear = native_pmd_clear, #endif - .set_pud = native_set_pud, + .mmu.set_pud = native_set_pud, - .pmd_val = PTE_IDENT, - .make_pmd = PTE_IDENT, + .mmu.pmd_val = PTE_IDENT, + .mmu.make_pmd = PTE_IDENT, #if CONFIG_PGTABLE_LEVELS >= 4 - .pud_val = PTE_IDENT, - .make_pud = PTE_IDENT, + .mmu.pud_val = PTE_IDENT, + .mmu.make_pud = PTE_IDENT, - .set_p4d = native_set_p4d, + .mmu.set_p4d = native_set_p4d, #if CONFIG_PGTABLE_LEVELS >= 5 - .p4d_val = PTE_IDENT, - .make_p4d = PTE_IDENT, + .mmu.p4d_val = PTE_IDENT, + .mmu.make_p4d = PTE_IDENT, - .set_pgd = native_set_pgd, + .mmu.set_pgd = native_set_pgd, #endif /* CONFIG_PGTABLE_LEVELS >= 5 */ #endif /* CONFIG_PGTABLE_LEVELS >= 4 */ #endif /* CONFIG_PGTABLE_LEVELS >= 3 */ - .pte_val = PTE_IDENT, - .pgd_val = PTE_IDENT, + .mmu.pte_val = PTE_IDENT, + .mmu.pgd_val = PTE_IDENT, - .make_pte = PTE_IDENT, - .make_pgd = PTE_IDENT, + .mmu.make_pte = PTE_IDENT, + .mmu.make_pgd = PTE_IDENT, - .dup_mmap = paravirt_nop, - .exit_mmap = paravirt_nop, - .activate_mm = paravirt_nop, + .mmu.dup_mmap = paravirt_nop, + .mmu.activate_mm = paravirt_nop, - .lazy_mode = { - .enter = paravirt_nop, - .leave = paravirt_nop, - .flush = paravirt_nop, + .mmu.lazy_mode = { + .enter = paravirt_nop, + .leave = paravirt_nop, + .flush = paravirt_nop, }, - .set_fixmap = native_set_fixmap, + .mmu.set_fixmap = native_set_fixmap, +#endif /* CONFIG_PARAVIRT_XXL */ + +#if defined(CONFIG_PARAVIRT_SPINLOCKS) + /* Lock ops. */ +#ifdef CONFIG_SMP + .lock.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, + .lock.queued_spin_unlock = + PV_CALLEE_SAVE(__native_queued_spin_unlock), + .lock.wait = paravirt_nop, + .lock.kick = paravirt_nop, + .lock.vcpu_is_preempted = + PV_CALLEE_SAVE(__native_vcpu_is_preempted), +#endif /* SMP */ +#endif }; -EXPORT_SYMBOL_GPL(pv_time_ops); -EXPORT_SYMBOL (pv_cpu_ops); -EXPORT_SYMBOL (pv_mmu_ops); +#ifdef CONFIG_PARAVIRT_XXL +/* At this point, native_get/set_debugreg has real function entries */ +NOKPROBE_SYMBOL(native_get_debugreg); +NOKPROBE_SYMBOL(native_set_debugreg); +NOKPROBE_SYMBOL(native_load_idt); +#endif + +EXPORT_SYMBOL_GPL(pv_ops); EXPORT_SYMBOL_GPL(pv_info); -EXPORT_SYMBOL (pv_irq_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 758e69d72ebf..6368c22fa1fa 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -1,18 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 #include <asm/paravirt.h> -DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); -DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); -DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); -DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); -DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); -DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); -DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); +#ifdef CONFIG_PARAVIRT_XXL +DEF_NATIVE(irq, irq_disable, "cli"); +DEF_NATIVE(irq, irq_enable, "sti"); +DEF_NATIVE(irq, restore_fl, "push %eax; popf"); +DEF_NATIVE(irq, save_fl, "pushf; pop %eax"); +DEF_NATIVE(cpu, iret, "iret"); +DEF_NATIVE(mmu, read_cr2, "mov %cr2, %eax"); +DEF_NATIVE(mmu, write_cr3, "mov %eax, %cr3"); +DEF_NATIVE(mmu, read_cr3, "mov %cr3, %eax"); +#endif #if defined(CONFIG_PARAVIRT_SPINLOCKS) -DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); -DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax"); +DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%eax)"); +DEF_NATIVE(lock, vcpu_is_preempted, "xor %eax, %eax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) @@ -30,53 +32,42 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) extern bool pv_is_native_spin_unlock(void); extern bool pv_is_native_vcpu_is_preempted(void); -unsigned native_patch(u8 type, u16 clobbers, void *ibuf, - unsigned long addr, unsigned len) +unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len) { - const unsigned char *start, *end; - unsigned ret; - #define PATCH_SITE(ops, x) \ - case PARAVIRT_PATCH(ops.x): \ - start = start_##ops##_##x; \ - end = end_##ops##_##x; \ - goto patch_site + case PARAVIRT_PATCH(ops.x): \ + return paravirt_patch_insns(ibuf, len, start_##ops##_##x, end_##ops##_##x) + switch (type) { - PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_irq_ops, irq_enable); - PATCH_SITE(pv_irq_ops, restore_fl); - PATCH_SITE(pv_irq_ops, save_fl); - PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_mmu_ops, read_cr2); - PATCH_SITE(pv_mmu_ops, read_cr3); - PATCH_SITE(pv_mmu_ops, write_cr3); +#ifdef CONFIG_PARAVIRT_XXL + PATCH_SITE(irq, irq_disable); + PATCH_SITE(irq, irq_enable); + PATCH_SITE(irq, restore_fl); + PATCH_SITE(irq, save_fl); + PATCH_SITE(cpu, iret); + PATCH_SITE(mmu, read_cr2); + PATCH_SITE(mmu, read_cr3); + PATCH_SITE(mmu, write_cr3); +#endif #if defined(CONFIG_PARAVIRT_SPINLOCKS) - case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): - if (pv_is_native_spin_unlock()) { - start = start_pv_lock_ops_queued_spin_unlock; - end = end_pv_lock_ops_queued_spin_unlock; - goto patch_site; - } - goto patch_default; + case PARAVIRT_PATCH(lock.queued_spin_unlock): + if (pv_is_native_spin_unlock()) + return paravirt_patch_insns(ibuf, len, + start_lock_queued_spin_unlock, + end_lock_queued_spin_unlock); + break; - case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted): - if (pv_is_native_vcpu_is_preempted()) { - start = start_pv_lock_ops_vcpu_is_preempted; - end = end_pv_lock_ops_vcpu_is_preempted; - goto patch_site; - } - goto patch_default; + case PARAVIRT_PATCH(lock.vcpu_is_preempted): + if (pv_is_native_vcpu_is_preempted()) + return paravirt_patch_insns(ibuf, len, + start_lock_vcpu_is_preempted, + end_lock_vcpu_is_preempted); + break; #endif default: -patch_default: __maybe_unused - ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); - break; - -patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); break; } #undef PATCH_SITE - return ret; + return paravirt_patch_default(type, ibuf, addr, len); } diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 9cb98f7b07c9..7ca9cb726f4d 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -3,24 +3,26 @@ #include <asm/asm-offsets.h> #include <linux/stringify.h> -DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); -DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); -DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); -DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); -DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); -DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); +#ifdef CONFIG_PARAVIRT_XXL +DEF_NATIVE(irq, irq_disable, "cli"); +DEF_NATIVE(irq, irq_enable, "sti"); +DEF_NATIVE(irq, restore_fl, "pushq %rdi; popfq"); +DEF_NATIVE(irq, save_fl, "pushfq; popq %rax"); +DEF_NATIVE(mmu, read_cr2, "movq %cr2, %rax"); +DEF_NATIVE(mmu, read_cr3, "movq %cr3, %rax"); +DEF_NATIVE(mmu, write_cr3, "movq %rdi, %cr3"); +DEF_NATIVE(cpu, wbinvd, "wbinvd"); -DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); -DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); +DEF_NATIVE(cpu, usergs_sysret64, "swapgs; sysretq"); +DEF_NATIVE(cpu, swapgs, "swapgs"); +#endif DEF_NATIVE(, mov32, "mov %edi, %eax"); DEF_NATIVE(, mov64, "mov %rdi, %rax"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) -DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); -DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax"); +DEF_NATIVE(lock, queued_spin_unlock, "movb $0, (%rdi)"); +DEF_NATIVE(lock, vcpu_is_preempted, "xor %eax, %eax"); #endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) @@ -38,55 +40,44 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) extern bool pv_is_native_spin_unlock(void); extern bool pv_is_native_vcpu_is_preempted(void); -unsigned native_patch(u8 type, u16 clobbers, void *ibuf, - unsigned long addr, unsigned len) +unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len) { - const unsigned char *start, *end; - unsigned ret; - #define PATCH_SITE(ops, x) \ - case PARAVIRT_PATCH(ops.x): \ - start = start_##ops##_##x; \ - end = end_##ops##_##x; \ - goto patch_site - switch(type) { - PATCH_SITE(pv_irq_ops, restore_fl); - PATCH_SITE(pv_irq_ops, save_fl); - PATCH_SITE(pv_irq_ops, irq_enable); - PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, usergs_sysret64); - PATCH_SITE(pv_cpu_ops, swapgs); - PATCH_SITE(pv_mmu_ops, read_cr2); - PATCH_SITE(pv_mmu_ops, read_cr3); - PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_cpu_ops, wbinvd); -#if defined(CONFIG_PARAVIRT_SPINLOCKS) - case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): - if (pv_is_native_spin_unlock()) { - start = start_pv_lock_ops_queued_spin_unlock; - end = end_pv_lock_ops_queued_spin_unlock; - goto patch_site; - } - goto patch_default; + case PARAVIRT_PATCH(ops.x): \ + return paravirt_patch_insns(ibuf, len, start_##ops##_##x, end_##ops##_##x) - case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted): - if (pv_is_native_vcpu_is_preempted()) { - start = start_pv_lock_ops_vcpu_is_preempted; - end = end_pv_lock_ops_vcpu_is_preempted; - goto patch_site; - } - goto patch_default; + switch (type) { +#ifdef CONFIG_PARAVIRT_XXL + PATCH_SITE(irq, restore_fl); + PATCH_SITE(irq, save_fl); + PATCH_SITE(irq, irq_enable); + PATCH_SITE(irq, irq_disable); + PATCH_SITE(cpu, usergs_sysret64); + PATCH_SITE(cpu, swapgs); + PATCH_SITE(cpu, wbinvd); + PATCH_SITE(mmu, read_cr2); + PATCH_SITE(mmu, read_cr3); + PATCH_SITE(mmu, write_cr3); #endif +#if defined(CONFIG_PARAVIRT_SPINLOCKS) + case PARAVIRT_PATCH(lock.queued_spin_unlock): + if (pv_is_native_spin_unlock()) + return paravirt_patch_insns(ibuf, len, + start_lock_queued_spin_unlock, + end_lock_queued_spin_unlock); + break; - default: -patch_default: __maybe_unused - ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); + case PARAVIRT_PATCH(lock.vcpu_is_preempted): + if (pv_is_native_vcpu_is_preempted()) + return paravirt_patch_insns(ibuf, len, + start_lock_vcpu_is_preempted, + end_lock_vcpu_is_preempted); break; +#endif -patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); + default: break; } #undef PATCH_SITE - return ret; + return paravirt_patch_default(type, ibuf, addr, len); } 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_32.c b/arch/x86/kernel/process_32.c index 2924fd447e61..5046a3c9dec2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,7 +59,7 @@ #include <asm/intel_rdt_sched.h> #include <asm/proto.h> -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all) 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) + if (mode != SHOW_REGS_ALL) return; cr0 = read_cr0(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..31b4755369f0 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -54,15 +54,14 @@ #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> #endif -__visible DEFINE_PER_CPU(unsigned long, rsp_scratch); - /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -87,9 +86,17 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); - if (!all) + if (mode == SHOW_REGS_SHORT) return; + if (mode == SHOW_REGS_USER) { + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", + fs, shadowgs); + return; + } + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); @@ -278,6 +285,138 @@ 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) { @@ -465,10 +604,7 @@ __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); @@ -619,54 +755,25 @@ 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..ffae9b9740fd 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 } @@ -1369,33 +1359,18 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) #endif } -static void fill_sigtrap_info(struct task_struct *tsk, - struct pt_regs *regs, - int error_code, int si_code, - struct siginfo *info) +void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, + int error_code, int si_code) { tsk->thread.trap_nr = X86_TRAP_DB; tsk->thread.error_code = error_code; - info->si_signo = SIGTRAP; - info->si_code = si_code; - info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL; -} - -void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, - struct siginfo *info) -{ - fill_sigtrap_info(tsk, regs, 0, TRAP_BRKPT, info); + /* Send us the fake SIGTRAP */ + force_sig_fault(SIGTRAP, si_code, + user_mode(regs) ? (void __user *)regs->ip : NULL, tsk); } -void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, - int error_code, int si_code) +void user_single_step_report(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); + send_sigtrap(current, regs, 0, TRAP_BRKPT); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4866badb235..7005f89bf3b2 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(); @@ -1281,6 +1281,23 @@ void __init setup_arch(char **cmdline_p) unwind_init(); } +/* + * From boot protocol 2.14 onwards we expect the bootloader to set the + * version to "0x8000 | <used version>". In case we find a version >= 2.14 + * without the 0x8000 we assume the boot loader supports 2.13 only and + * reset the version accordingly. The 0x8000 flag is removed in any case. + */ +void __init x86_verify_bootdata_version(void) +{ + if (boot_params.hdr.version & VERSION_WRITTEN) + boot_params.hdr.version &= ~VERSION_WRITTEN; + else if (boot_params.hdr.version >= 0x020e) + boot_params.hdr.version = 0x020d; + + if (boot_params.hdr.version < 0x020e) + boot_params.hdr.acpi_rsdp_addr = 0; +} + #ifdef CONFIG_X86_32 static struct resource video_ram_resource = { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f02ecaf97904..5369d7fac797 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -676,6 +676,7 @@ static void __init smp_quirk_init_udelay(void) /* if modern processor, use no delay */ if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || + ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) || ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) { init_udelay = 0; return; @@ -1592,7 +1593,8 @@ static inline void mwait_play_dead(void) void *mwait_ptr; int i; - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) return; if (!this_cpu_has(X86_FEATURE_MWAIT)) return; diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index be01328eb755..0e14f6c0d35e 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -10,6 +10,7 @@ * */ +#include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/irq.h> @@ -25,7 +26,7 @@ #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) @@ -105,3 +106,24 @@ void __init time_init(void) { late_time_init = x86_late_time_init; } + +/* + * Sanity check the vdso related archdata content. + */ +void clocksource_arch_init(struct clocksource *cs) +{ + if (cs->archdata.vclock_mode == VCLOCK_NONE) + return; + + if (cs->archdata.vclock_mode > VCLOCK_MAX) { + pr_warn("clocksource %s registered with invalid vclock_mode %d. Disabling vclock.\n", + cs->name, cs->archdata.vclock_mode); + cs->archdata.vclock_mode = VCLOCK_NONE; + } + + if (cs->mask != CLOCKSOURCE_MASK(64)) { + pr_warn("clocksource %s registered with invalid mask %016llx. Disabling vclock.\n", + cs->name, cs->mask); + cs->archdata.vclock_mode = VCLOCK_NONE; + } +} diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 12cbe2b88c0f..738bf42b0218 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -111,8 +111,10 @@ int arch_register_cpu(int num) /* * Currently CPU0 is only hotpluggable on Intel platforms. Other * vendors can add hotplug support later. + * Xen PV guests don't support CPU0 hotplug at all. */ - if (c->x86_vendor != X86_VENDOR_INTEL) + if (c->x86_vendor != X86_VENDOR_INTEL || + boot_cpu_has(X86_FEATURE_XENPV)) cpu0_hotpluggable = 0; /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index e6db475164ed..8f6dcd88202e 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -189,7 +189,7 @@ int fixup_bug(struct pt_regs *regs, int trapnr) } static nokprobe_inline int -do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, +do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, struct pt_regs *regs, long error_code) { if (v8086_mode(regs)) { @@ -202,11 +202,8 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, error_code, trapnr)) return 0; } - return -1; - } - - if (!user_mode(regs)) { - if (fixup_exception(regs, trapnr)) + } else if (!user_mode(regs)) { + if (fixup_exception(regs, trapnr, error_code, 0)) return 0; tsk->thread.error_code = error_code; @@ -214,49 +211,6 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, die(str, regs, error_code); } - return -1; -} - -static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr, - siginfo_t *info) -{ - unsigned long siaddr; - int sicode; - - switch (trapnr) { - default: - return SEND_SIG_PRIV; - - case X86_TRAP_DE: - sicode = FPE_INTDIV; - siaddr = uprobe_get_trap_addr(regs); - break; - case X86_TRAP_UD: - sicode = ILL_ILLOPN; - siaddr = uprobe_get_trap_addr(regs); - break; - case X86_TRAP_AC: - sicode = BUS_ADRALN; - siaddr = 0; - break; - } - - info->si_signo = signr; - info->si_errno = 0; - info->si_code = sicode; - info->si_addr = (void __user *)siaddr; - return info; -} - -static void -do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, - long error_code, siginfo_t *info) -{ - struct task_struct *tsk = current; - - - if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) - return; /* * We want error_code and trap_nr set for userspace faults and * kernelspace faults which result in die(), but not @@ -269,24 +223,45 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; + return -1; +} + +static void show_signal(struct task_struct *tsk, int signr, + const char *type, const char *desc, + struct pt_regs *regs, long error_code) +{ if (show_unhandled_signals && unhandled_signal(tsk, signr) && printk_ratelimit()) { - pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", - tsk->comm, tsk->pid, str, + pr_info("%s[%d] %s%s ip:%lx sp:%lx error:%lx", + tsk->comm, task_pid_nr(tsk), type, desc, regs->ip, regs->sp, error_code); print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } +} - force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk); +static void +do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, + long error_code, int sicode, void __user *addr) +{ + struct task_struct *tsk = current; + + + if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code)) + return; + + show_signal(tsk, signr, "trap ", str, regs, error_code); + + if (!sicode) + force_sig(signr, tsk); + else + force_sig_fault(signr, sicode, addr, tsk); } NOKPROBE_SYMBOL(do_trap); static void do_error_trap(struct pt_regs *regs, long error_code, char *str, - unsigned long trapnr, int signr) + unsigned long trapnr, int signr, int sicode, void __user *addr) { - siginfo_t info; - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); /* @@ -299,26 +274,26 @@ 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)); + do_trap(trapnr, signr, str, regs, error_code, sicode, addr); } } -#define DO_ERROR(trapnr, signr, str, name) \ -dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - do_error_trap(regs, error_code, str, trapnr, signr); \ +#define IP ((void __user *)uprobe_get_trap_addr(regs)) +#define DO_ERROR(trapnr, signr, sicode, addr, str, name) \ +dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ +{ \ + do_error_trap(regs, error_code, str, trapnr, signr, sicode, addr); \ } -DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error) -DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) -DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op) -DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun) -DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) -DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) -DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check) +DO_ERROR(X86_TRAP_DE, SIGFPE, FPE_INTDIV, IP, "divide error", divide_error) +DO_ERROR(X86_TRAP_OF, SIGSEGV, 0, NULL, "overflow", overflow) +DO_ERROR(X86_TRAP_UD, SIGILL, ILL_ILLOPN, IP, "invalid opcode", invalid_op) +DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, 0, NULL, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR(X86_TRAP_TS, SIGSEGV, 0, NULL, "invalid TSS", invalid_TSS) +DO_ERROR(X86_TRAP_NP, SIGBUS, 0, NULL, "segment not present", segment_not_present) +DO_ERROR(X86_TRAP_SS, SIGBUS, 0, NULL, "stack segment", stack_segment) +DO_ERROR(X86_TRAP_AC, SIGBUS, BUS_ADRALN, NULL, "alignment check", alignment_check) +#undef IP #ifdef CONFIG_VMAP_STACK __visible void __noreturn handle_stack_overflow(const char *message, @@ -383,6 +358,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * we won't enable interupts or schedule before we invoke * general_protection, so nothing will clobber the stack * frame we just set up. + * + * We will enter general_protection with kernel GSBASE, + * which is what the stub expects, given that the faulting + * RIP will be the IRET instruction. */ regs->ip = (unsigned long)general_protection; regs->sp = (unsigned long)&gpregs->orig_ax; @@ -455,7 +434,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { const struct mpx_bndcsr *bndcsr; - siginfo_t *info; RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); if (notify_die(DIE_TRAP, "bounds", regs, error_code, @@ -493,8 +471,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) goto exit_trap; break; /* Success, it was handled */ case 1: /* Bound violation. */ - info = mpx_generate_siginfo(regs); - if (IS_ERR(info)) { + { + struct task_struct *tsk = current; + struct mpx_fault_info mpx; + + if (mpx_fault_info(&mpx, regs)) { /* * We failed to decode the MPX instruction. Act as if * the exception was not caused by MPX. @@ -503,14 +484,20 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) } /* * Success, we decoded the instruction and retrieved - * an 'info' containing the address being accessed + * an 'mpx' containing the address being accessed * which caused the exception. This information * allows and application to possibly handle the * #BR exception itself. */ - do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info); - kfree(info); + if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs, + error_code)) + break; + + show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code); + + force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper); break; + } case 0: /* No exception caused by Intel MPX operations. */ goto exit_trap; default: @@ -527,12 +514,13 @@ exit_trap: * up here if the kernel has MPX turned off at compile * time.. */ - do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL); + do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL); } dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { + const char *desc = "general protection fault"; struct task_struct *tsk; RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); @@ -551,30 +539,33 @@ 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; - if (notify_die(DIE_GPF, "general protection fault", regs, error_code, + + /* + * 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, desc, regs, error_code, X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) - die("general protection fault", regs, error_code); + die(desc, regs, error_code); return; } tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; - if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && - printk_ratelimit()) { - pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx", - tsk->comm, task_pid_nr(tsk), - regs->ip, regs->sp, error_code); - print_vma_addr(KERN_CONT " in ", regs->ip); - pr_cont("\n"); - } + show_signal(tsk, SIGSEGV, "", desc, regs, error_code); - force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); + force_sig(SIGSEGV, tsk); } NOKPROBE_SYMBOL(do_general_protection); @@ -617,7 +608,7 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) goto exit; cond_local_irq_enable(regs); - do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, 0, NULL); cond_local_irq_disable(regs); exit: @@ -831,14 +822,14 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; struct fpu *fpu = &task->thread.fpu; - siginfo_t info; + int si_code; char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; 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; @@ -857,18 +848,14 @@ 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); - - info.si_code = fpu__exception_code(fpu, trapnr); + si_code = fpu__exception_code(fpu, trapnr); /* Retry when we get spurious exceptions: */ - if (!info.si_code) + if (!si_code) return; - force_sig_info(SIGFPE, &info, task); + force_sig_fault(SIGFPE, si_code, + (void __user *)uprobe_get_trap_addr(regs), task); } dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) @@ -928,20 +915,13 @@ NOKPROBE_SYMBOL(do_device_not_available); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { - siginfo_t info; - 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; - info.si_addr = NULL; if (notify_die(DIE_TRAP, "iret exception", regs, error_code, X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, - &info); + ILL_BADSTK, (void __user *)NULL); } } #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1463468ba9a0..e9f777bfed40 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -26,6 +26,7 @@ #include <asm/apic.h> #include <asm/intel-family.h> #include <asm/i8259.h> +#include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -57,7 +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; @@ -74,7 +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(); } @@ -103,7 +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; @@ -246,7 +247,7 @@ unsigned long long sched_clock(void) bool using_native_sched_clock(void) { - return pv_time_ops.sched_clock == native_sched_clock; + return pv_ops.time.sched_clock == native_sched_clock; } #else unsigned long long @@ -635,7 +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: @@ -1415,7 +1416,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early) static unsigned long __init get_loops_per_jiffy(void) { - unsigned long lpj = tsc_khz * KHZ; + u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; @@ -1433,6 +1434,9 @@ void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; + /* Don't change UV TSC multi-chassis synchronization */ + if (is_early_uv_system()) + return; if (!determine_cpu_tsc_frequencies(true)) return; loops_per_jiffy = get_loops_per_jiffy(); 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), {} }; diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index ff20b35e98dd..f8f3cfda01ae 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -271,19 +271,13 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst, */ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs) { - siginfo_t info; struct task_struct *tsk = current; tsk->thread.cr2 = (unsigned long)addr; 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; - info.si_addr = addr; - force_sig_info(SIGSEGV, &info, tsk); + force_sig_fault(SIGSEGV, SEGV_MAPERR, addr, tsk); if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV))) return; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index deb576b23b7c..843feb94a950 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -1086,7 +1086,7 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs 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); + force_sig(SIGSEGV, current); } return -1; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 1c03e4aa6474..c2fd39752da8 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -199,7 +199,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pte_unmap_unlock(pte, ptl); out: up_write(&mm->mmap_sem); - flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL); + flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT, false); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8bde0a419f86..0d618ee634ac 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,6 +65,23 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); #define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); +/* + * This section contains data which will be mapped as decrypted. Memory + * encryption operates on a page basis. Make this section PMD-aligned + * to avoid splitting the pages while mapping the section early. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#define BSS_DECRYPTED \ + . = ALIGN(PMD_SIZE); \ + __start_bss_decrypted = .; \ + *(.bss..decrypted); \ + . = ALIGN(PAGE_SIZE); \ + __start_bss_decrypted_unused = .; \ + . = ALIGN(PMD_SIZE); \ + __end_bss_decrypted = .; \ + #else #define X86_ALIGN_RODATA_BEGIN @@ -74,6 +91,7 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN #define ALIGN_ENTRY_TEXT_END +#define BSS_DECRYPTED #endif @@ -118,16 +136,6 @@ SECTIONS *(.fixup) *(.gnu.warning) -#ifdef CONFIG_X86_64 - . = ALIGN(PAGE_SIZE); - __entry_trampoline_start = .; - _entry_trampoline = .; - *(.entry_trampoline) - . = ALIGN(PAGE_SIZE); - __entry_trampoline_end = .; - ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); -#endif - #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; *(.text.__x86.indirect_thunk) @@ -355,6 +363,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) + BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 44685fb2a192..1eae5af491c2 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,7 +26,7 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -#if defined CONFIG_PCI && defined CONFIG_PARAVIRT +#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL /* * Interrupt control on vSMPowered systems: * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' @@ -69,17 +69,17 @@ asmlinkage __visible void vsmp_irq_enable(void) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); -static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf, +static unsigned __init vsmp_patch(u8 type, void *ibuf, unsigned long addr, unsigned len) { switch (type) { - case PARAVIRT_PATCH(pv_irq_ops.irq_enable): - case PARAVIRT_PATCH(pv_irq_ops.irq_disable): - case PARAVIRT_PATCH(pv_irq_ops.save_fl): - case PARAVIRT_PATCH(pv_irq_ops.restore_fl): - return paravirt_patch_default(type, clobbers, ibuf, addr, len); + case PARAVIRT_PATCH(irq.irq_enable): + case PARAVIRT_PATCH(irq.irq_disable): + case PARAVIRT_PATCH(irq.save_fl): + case PARAVIRT_PATCH(irq.restore_fl): + return paravirt_patch_default(type, ibuf, addr, len); default: - return native_patch(type, clobbers, ibuf, addr, len); + return native_patch(type, ibuf, addr, len); } } @@ -111,11 +111,11 @@ static void __init set_vsmp_pv_ops(void) if (cap & ctl & (1 << 4)) { /* Setup irq ops and turn on vSMP IRQ fastpath handling */ - pv_irq_ops.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); - pv_irq_ops.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); - pv_irq_ops.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); - pv_irq_ops.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); - pv_init_ops.patch = vsmp_patch; + pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); + pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); + pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); + pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); + pv_ops.init.patch = vsmp_patch; ctl &= ~(1 << 4); } writel(ctl, address + 4); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 2792b5573818..50a2b492fdd6 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -31,7 +31,6 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } static bool __init bool_x86_init_noop(void) { return false; } static void x86_op_int_noop(int cpu) { } -static u64 u64_x86_init_noop(void) { return 0; } /* * The platform setup functions are preset with the default functions @@ -96,7 +95,7 @@ struct x86_init_ops x86_init __initdata = { }, .acpi = { - .get_root_pointer = u64_x86_init_noop, + .get_root_pointer = x86_default_get_root_pointer, .reduced_hw_early_init = acpi_generic_reduced_hw_init, }, }; |