diff options
Diffstat (limited to 'arch/x86/kernel')
26 files changed, 232 insertions, 502 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7a37d9357bc4..3b20607d581b 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -200,7 +200,7 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) { struct acpi_madt_local_x2apic *processor = NULL; #ifdef CONFIG_X86_X2APIC - int apic_id; + u32 apic_id; u8 enabled; #endif @@ -215,6 +215,10 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) apic_id = processor->local_apic_id; enabled = processor->lapic_flags & ACPI_MADT_ENABLED; + /* Ignore invalid ID */ + if (apic_id == 0xffffffff) + return 0; + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size @@ -222,10 +226,13 @@ acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - if (!apic->apic_id_valid(apic_id) && enabled) - printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); - else - acpi_register_lapic(apic_id, processor->uid, enabled); + if (!apic->apic_id_valid(apic_id)) { + if (enabled) + pr_warn(PREFIX "x2apic entry ignored\n"); + return 0; + } + + acpi_register_lapic(apic_id, processor->uid, enabled); #else printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); #endif diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c88e0b127810..b481b95bd8f6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -14,8 +14,11 @@ #include <asm/amd_nb.h> #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -24,6 +27,7 @@ static u32 *flush_words; static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, {} }; @@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; @@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c index a360801779ae..02b4839478b1 100644 --- a/arch/x86/kernel/apic/apic_common.c +++ b/arch/x86/kernel/apic/apic_common.c @@ -40,7 +40,7 @@ int default_check_phys_apicid_present(int phys_apicid) return physid_isset(phys_apicid, phys_cpu_present_map); } -int default_apic_id_valid(int apicid) +int default_apic_id_valid(u32 apicid) { return (apicid < 255); } diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 134e04506ab4..78778b54f904 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -56,7 +56,7 @@ static u32 numachip2_set_apic_id(unsigned int id) return id << 24; } -static int numachip_apic_id_valid(int apicid) +static int numachip_apic_id_valid(u32 apicid) { /* Trust what bootloader passes in MADT */ return 1; diff --git a/arch/x86/kernel/apic/x2apic.h b/arch/x86/kernel/apic/x2apic.h index b107de381cb5..a49b3604027f 100644 --- a/arch/x86/kernel/apic/x2apic.h +++ b/arch/x86/kernel/apic/x2apic.h @@ -1,6 +1,6 @@ /* Common bits for X2APIC cluster/physical modes. */ -int x2apic_apic_id_valid(int apicid); +int x2apic_apic_id_valid(u32 apicid); int x2apic_apic_id_registered(void); void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); unsigned int x2apic_get_apic_id(unsigned long id); diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index e2829bf40e4a..b5cf9e7b3830 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -101,7 +101,7 @@ static int x2apic_phys_probe(void) } /* Common x2apic functions, also used by x2apic_cluster */ -int x2apic_apic_id_valid(int apicid) +int x2apic_apic_id_valid(u32 apicid) { return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f11910b44638..efaf2d4f9c3c 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -557,7 +557,7 @@ static void uv_send_IPI_all(int vector) uv_send_IPI_mask(cpu_online_mask, vector); } -static int uv_apic_id_valid(int apicid) +static int uv_apic_id_valid(u32 apicid) { return 1; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4702fbd98f92..ce243f7d2d4e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -850,15 +850,8 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; c->x86_capability[CPUID_8000_0008_EBX] = ebx; } -#ifdef CONFIG_X86_32 - else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) - c->x86_phys_bits = 36; -#endif if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); @@ -874,6 +867,22 @@ void get_cpu_cap(struct cpuinfo_x86 *c) apply_forced_caps(c); } +static void get_cpu_address_sizes(struct cpuinfo_x86 *c) +{ + u32 eax, ebx, ecx, edx; + + if (c->extended_cpuid_level >= 0x80000008) { + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); + + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + } +#ifdef CONFIG_X86_32 + else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; +#endif +} + static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -965,6 +974,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); + get_cpu_address_sizes(c); setup_force_cpu_cap(X86_FEATURE_CPUID); if (this_cpu->c_early_init) @@ -1097,6 +1107,8 @@ static void generic_identify(struct cpuinfo_x86 *c) get_cpu_cap(c); + get_cpu_address_sizes(c); + if (c->cpuid_level >= 0x00000001) { c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 904b0a3c4e53..2c0bd38a44ab 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -19,7 +19,7 @@ struct cpuid_dep { * called from cpu hotplug. It shouldn't do anything in this case, * but it's difficult to tell that to the init reference checker. */ -const static struct cpuid_dep cpuid_deps[] = { +static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XSAVEOPT, X86_FEATURE_XSAVE }, { X86_FEATURE_XSAVEC, X86_FEATURE_XSAVE }, { X86_FEATURE_XSAVES, X86_FEATURE_XSAVE }, diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b9693b80fc21..60d1897041da 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -835,6 +835,9 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" }, + { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" }, + { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" }, { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 10c4fc2c91f8..77e201301528 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -564,14 +564,12 @@ static int __reload_late(void *info) apply_microcode_local(&err); spin_unlock(&update_lock); + /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - return -1; - /* siblings return UCODE_OK because their engine got updated already */ + ret = -1; } else if (err == UCODE_UPDATED || err == UCODE_OK) { ret = 1; - } else { - return ret; } /* diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 32b8e5724f96..1c2cfa0644aa 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -485,7 +485,6 @@ static void show_saved_mc(void) */ static void save_mc_for_early(u8 *mc, unsigned int size) { -#ifdef CONFIG_HOTPLUG_CPU /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); @@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size) show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); -#endif } static bool load_builtin_intel_microcode(struct cpio_data *cp) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 1f6680427ff0..f631a3f15587 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -38,37 +38,6 @@ #include <asm/virtext.h> #include <asm/intel_pt.h> -/* Alignment required for elf header segment */ -#define ELF_CORE_HEADER_ALIGN 4096 - -/* This primarily represents number of split ranges due to exclusion */ -#define CRASH_MAX_RANGES 16 - -struct crash_mem_range { - u64 start, end; -}; - -struct crash_mem { - unsigned int nr_ranges; - struct crash_mem_range ranges[CRASH_MAX_RANGES]; -}; - -/* Misc data about ram ranges needed to prepare elf headers */ -struct crash_elf_data { - struct kimage *image; - /* - * Total number of ram ranges we have after various adjustments for - * crash reserved region, etc. - */ - unsigned int max_nr_ranges; - - /* Pointer to elf header */ - void *ehdr; - /* Pointer to next phdr */ - void *bufp; - struct crash_mem mem; -}; - /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { struct boot_params *params; @@ -218,124 +187,49 @@ static int get_nr_ram_ranges_callback(struct resource *res, void *arg) return 0; } - /* Gather all the required information to prepare elf headers for ram regions */ -static void fill_up_crash_elf_data(struct crash_elf_data *ced, - struct kimage *image) +static struct crash_mem *fill_up_crash_elf_data(void) { unsigned int nr_ranges = 0; - - ced->image = image; + struct crash_mem *cmem; walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + if (!nr_ranges) + return NULL; - ced->max_nr_ranges = nr_ranges; - - /* Exclusion of crash region could split memory ranges */ - ced->max_nr_ranges++; - - /* If crashk_low_res is not 0, another range split possible */ - if (crashk_low_res.end) - ced->max_nr_ranges++; -} - -static int exclude_mem_range(struct crash_mem *mem, - unsigned long long mstart, unsigned long long mend) -{ - int i, j; - unsigned long long start, end; - struct crash_mem_range temp_range = {0, 0}; - - for (i = 0; i < mem->nr_ranges; i++) { - start = mem->ranges[i].start; - end = mem->ranges[i].end; - - if (mstart > end || mend < start) - continue; - - /* Truncate any area outside of range */ - if (mstart < start) - mstart = start; - if (mend > end) - mend = end; - - /* Found completely overlapping range */ - if (mstart == start && mend == end) { - mem->ranges[i].start = 0; - mem->ranges[i].end = 0; - if (i < mem->nr_ranges - 1) { - /* Shift rest of the ranges to left */ - for (j = i; j < mem->nr_ranges - 1; j++) { - mem->ranges[j].start = - mem->ranges[j+1].start; - mem->ranges[j].end = - mem->ranges[j+1].end; - } - } - mem->nr_ranges--; - return 0; - } - - if (mstart > start && mend < end) { - /* Split original range */ - mem->ranges[i].end = mstart - 1; - temp_range.start = mend + 1; - temp_range.end = end; - } else if (mstart != start) - mem->ranges[i].end = mstart - 1; - else - mem->ranges[i].start = mend + 1; - break; - } + /* + * Exclusion of crash region and/or crashk_low_res may cause + * another range split. So add extra two slots here. + */ + nr_ranges += 2; + cmem = vzalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges); + if (!cmem) + return NULL; - /* If a split happend, add the split to array */ - if (!temp_range.end) - return 0; + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; - /* Split happened */ - if (i == CRASH_MAX_RANGES - 1) { - pr_err("Too many crash ranges after split\n"); - return -ENOMEM; - } - - /* Location where new range should go */ - j = i + 1; - if (j < mem->nr_ranges) { - /* Move over all ranges one slot towards the end */ - for (i = mem->nr_ranges - 1; i >= j; i--) - mem->ranges[i + 1] = mem->ranges[i]; - } - - mem->ranges[j].start = temp_range.start; - mem->ranges[j].end = temp_range.end; - mem->nr_ranges++; - return 0; + return cmem; } /* * Look for any unwanted ranges between mstart, mend and remove them. This - * might lead to split and split ranges are put in ced->mem.ranges[] array + * might lead to split and split ranges are put in cmem->ranges[] array */ -static int elf_header_exclude_ranges(struct crash_elf_data *ced, - unsigned long long mstart, unsigned long long mend) +static int elf_header_exclude_ranges(struct crash_mem *cmem) { - struct crash_mem *cmem = &ced->mem; int ret = 0; - memset(cmem->ranges, 0, sizeof(cmem->ranges)); - - cmem->ranges[0].start = mstart; - cmem->ranges[0].end = mend; - cmem->nr_ranges = 1; - /* Exclude crashkernel region */ - ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) { - ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + ret = crash_exclude_mem_range(cmem, crashk_low_res.start, + crashk_low_res.end); if (ret) return ret; } @@ -345,144 +239,12 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { - struct crash_elf_data *ced = arg; - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - unsigned long mstart, mend; - struct kimage *image = ced->image; - struct crash_mem *cmem; - int ret, i; - - ehdr = ced->ehdr; - - /* Exclude unwanted mem ranges */ - ret = elf_header_exclude_ranges(ced, res->start, res->end); - if (ret) - return ret; - - /* Go through all the ranges in ced->mem.ranges[] and prepare phdr */ - cmem = &ced->mem; - - for (i = 0; i < cmem->nr_ranges; i++) { - mstart = cmem->ranges[i].start; - mend = cmem->ranges[i].end; - - phdr = ced->bufp; - ced->bufp += sizeof(Elf64_Phdr); - - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_offset = mstart; - - /* - * If a range matches backup region, adjust offset to backup - * segment. - */ - if (mstart == image->arch.backup_src_start && - (mend - mstart + 1) == image->arch.backup_src_sz) - phdr->p_offset = image->arch.backup_load_addr; - - phdr->p_paddr = mstart; - phdr->p_vaddr = (unsigned long long) __va(mstart); - phdr->p_filesz = phdr->p_memsz = mend - mstart + 1; - phdr->p_align = 0; - ehdr->e_phnum++; - pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n", - phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz, - ehdr->e_phnum, phdr->p_offset); - } - - return ret; -} - -static int prepare_elf64_headers(struct crash_elf_data *ced, - void **addr, unsigned long *sz) -{ - Elf64_Ehdr *ehdr; - Elf64_Phdr *phdr; - unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz; - unsigned char *buf, *bufp; - unsigned int cpu; - unsigned long long notes_addr; - int ret; + struct crash_mem *cmem = arg; - /* extra phdr for vmcoreinfo elf note */ - nr_phdr = nr_cpus + 1; - nr_phdr += ced->max_nr_ranges; - - /* - * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping - * area on x86_64 (ffffffff80000000 - ffffffffa0000000). - * I think this is required by tools like gdb. So same physical - * memory will be mapped in two elf headers. One will contain kernel - * text virtual addresses and other will have __va(physical) addresses. - */ + cmem->ranges[cmem->nr_ranges].start = res->start; + cmem->ranges[cmem->nr_ranges].end = res->end; + cmem->nr_ranges++; - nr_phdr++; - elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr); - elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN); - - buf = vzalloc(elf_sz); - if (!buf) - return -ENOMEM; - - bufp = buf; - ehdr = (Elf64_Ehdr *)bufp; - bufp += sizeof(Elf64_Ehdr); - memcpy(ehdr->e_ident, ELFMAG, SELFMAG); - ehdr->e_ident[EI_CLASS] = ELFCLASS64; - ehdr->e_ident[EI_DATA] = ELFDATA2LSB; - ehdr->e_ident[EI_VERSION] = EV_CURRENT; - ehdr->e_ident[EI_OSABI] = ELF_OSABI; - memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD); - ehdr->e_type = ET_CORE; - ehdr->e_machine = ELF_ARCH; - ehdr->e_version = EV_CURRENT; - ehdr->e_phoff = sizeof(Elf64_Ehdr); - ehdr->e_ehsize = sizeof(Elf64_Ehdr); - ehdr->e_phentsize = sizeof(Elf64_Phdr); - - /* Prepare one phdr of type PT_NOTE for each present cpu */ - for_each_present_cpu(cpu) { - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_NOTE; - notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu)); - phdr->p_offset = phdr->p_paddr = notes_addr; - phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t); - (ehdr->e_phnum)++; - } - - /* Prepare one PT_NOTE header for vmcoreinfo */ - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_NOTE; - phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note(); - phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE; - (ehdr->e_phnum)++; - -#ifdef CONFIG_X86_64 - /* Prepare PT_LOAD type program header for kernel text region */ - phdr = (Elf64_Phdr *)bufp; - bufp += sizeof(Elf64_Phdr); - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_vaddr = (Elf64_Addr)_text; - phdr->p_filesz = phdr->p_memsz = _end - _text; - phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); - (ehdr->e_phnum)++; -#endif - - /* Prepare PT_LOAD headers for system ram chunks. */ - ced->ehdr = ehdr; - ced->bufp = bufp; - ret = walk_system_ram_res(0, -1, ced, - prepare_elf64_ram_headers_callback); - if (ret < 0) - return ret; - - *addr = buf; - *sz = elf_sz; return 0; } @@ -490,18 +252,46 @@ static int prepare_elf64_headers(struct crash_elf_data *ced, static int prepare_elf_headers(struct kimage *image, void **addr, unsigned long *sz) { - struct crash_elf_data *ced; - int ret; + struct crash_mem *cmem; + Elf64_Ehdr *ehdr; + Elf64_Phdr *phdr; + int ret, i; - ced = kzalloc(sizeof(*ced), GFP_KERNEL); - if (!ced) + cmem = fill_up_crash_elf_data(); + if (!cmem) return -ENOMEM; - fill_up_crash_elf_data(ced, image); + ret = walk_system_ram_res(0, -1, cmem, + prepare_elf64_ram_headers_callback); + if (ret) + goto out; + + /* Exclude unwanted mem ranges */ + ret = elf_header_exclude_ranges(cmem); + if (ret) + goto out; /* By default prepare 64bit headers */ - ret = prepare_elf64_headers(ced, addr, sz); - kfree(ced); + ret = crash_prepare_elf64_headers(cmem, + IS_ENABLED(CONFIG_X86_64), addr, sz); + if (ret) + goto out; + + /* + * If a range matches backup region, adjust offset to backup + * segment. + */ + ehdr = (Elf64_Ehdr *)*addr; + phdr = (Elf64_Phdr *)(ehdr + 1); + for (i = 0; i < ehdr->e_phnum; phdr++, i++) + if (phdr->p_type == PT_LOAD && + phdr->p_paddr == image->arch.backup_src_start && + phdr->p_memsz == image->arch.backup_src_sz) { + phdr->p_offset = image->arch.backup_load_addr; + break; + } +out: + vfree(cmem); return ret; } @@ -547,14 +337,14 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, /* Exclude Backup region */ start = image->arch.backup_load_addr; end = start + image->arch.backup_src_sz - 1; - ret = exclude_mem_range(cmem, start, end); + ret = crash_exclude_mem_range(cmem, start, end); if (ret) return ret; /* Exclude elf header region */ start = image->arch.elf_load_addr; end = start + image->arch.elf_headers_sz - 1; - return exclude_mem_range(cmem, start, end); + return crash_exclude_mem_range(cmem, start, end); } /* Prepare memory map for crash dump kernel */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index e5ec3cafa72e..aebd0d5bc086 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -195,6 +195,10 @@ void init_espfix_ap(int cpu) pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); + /* + * __PAGE_KERNEL_* includes _PAGE_GLOBAL, which we want since + * this is mapped to userspace. + */ pte = __pte(__pa(stack_page) | ((__PAGE_KERNEL_RO | _PAGE_ENC) & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 0c855deee165..0c408f8c4ed4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -195,6 +195,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[i + 1] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + /* Filter out unsupported __PAGE_KERNEL_* bits: */ + pmd_entry &= __supported_pte_mask; pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 48385c1074a5..8344dd2f310a 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -399,8 +399,13 @@ NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .fill 511, 8, 0 NEXT_PAGE(level2_ident_pgt) - /* Since I easily can, map the first 1G. + /* + * Since I easily can, map the first 1G. * Don't set NX because code runs from these pages. + * + * Note: This sets _PAGE_GLOBAL despite whether + * the CPU supports it or it is enabled. But, + * the CPU should ignore the bit. */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #else @@ -431,6 +436,10 @@ NEXT_PAGE(level2_kernel_pgt) * (NOTE: at +512MB starts the module area, see MODULES_VADDR. * If you want to increase this then increase MODULES_VADDR * too.) + * + * This table is eventually used by the kernel during normal + * runtime. Care must be taken to clear out undesired bits + * later, like _PAGE_RW or _PAGE_GLOBAL in some cases. */ PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE) diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index fa183a131edc..a15fe0e92cf9 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL2.0 +// SPDX-License-Identifier: GPL-2.0 /* * Jailhouse paravirt_ops implementation * diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index fb095ba0c02f..7326078eaa7a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -334,7 +334,6 @@ static void *bzImage64_load(struct kimage *image, char *kernel, unsigned long setup_header_size, params_cmdline_sz; struct boot_params *params; unsigned long bootparam_load_addr, kernel_load_addr, initrd_load_addr; - unsigned long purgatory_load_addr; struct bzimage64_data *ldata; struct kexec_entry64_regs regs64; void *stack; @@ -342,6 +341,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, unsigned int efi_map_offset, efi_map_sz, efi_setup_data_offset; struct kexec_buf kbuf = { .image = image, .buf_max = ULONG_MAX, .top_down = true }; + struct kexec_buf pbuf = { .image = image, .buf_min = MIN_PURGATORY_ADDR, + .buf_max = ULONG_MAX, .top_down = true }; header = (struct setup_header *)(kernel + setup_hdr_offset); setup_sects = header->setup_sects; @@ -379,14 +380,13 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * Load purgatory. For 64bit entry point, purgatory code can be * anywhere. */ - ret = kexec_load_purgatory(image, MIN_PURGATORY_ADDR, ULONG_MAX, 1, - &purgatory_load_addr); + ret = kexec_load_purgatory(image, &pbuf); if (ret) { pr_err("Loading purgatory failed\n"); return ERR_PTR(ret); } - pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr); + pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); /* @@ -398,11 +398,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * little bit simple */ efi_map_sz = efi_get_runtime_map_size(); - efi_map_sz = ALIGN(efi_map_sz, 16); params_cmdline_sz = sizeof(struct boot_params) + cmdline_len + MAX_ELFCOREHDR_STR_LEN; params_cmdline_sz = ALIGN(params_cmdline_sz, 16); - kbuf.bufsz = params_cmdline_sz + efi_map_sz + + kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) + sizeof(struct setup_data) + sizeof(struct efi_setup_data); @@ -410,7 +409,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, if (!params) return ERR_PTR(-ENOMEM); efi_map_offset = params_cmdline_sz; - efi_setup_data_offset = efi_map_offset + efi_map_sz; + efi_setup_data_offset = efi_map_offset + ALIGN(efi_map_sz, 16); /* Copy setup header onto bootparams. Documentation/x86/boot.txt */ setup_header_size = 0x0202 + kernel[0x0201] - setup_hdr_offset; @@ -538,7 +537,7 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) } #endif -struct kexec_file_ops kexec_bzImage64_ops = { +const struct kexec_file_ops kexec_bzImage64_ops = { .probe = bzImage64_probe, .load = bzImage64_load, .cleanup = bzImage64_cleanup, diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 7867417cfaff..5b2300b818af 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void) static void __init kvm_smp_prepare_cpus(unsigned int max_cpus) { native_smp_prepare_cpus(max_cpus); - if (kvm_para_has_hint(KVM_HINTS_DEDICATED)) + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) static_branch_disable(&virt_spin_lock_key); } @@ -553,7 +553,7 @@ static void __init kvm_guest_init(void) } if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_DEDICATED) && + !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; @@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void) int cpu; if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_DEDICATED) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), @@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; - if (kvm_para_has_hint(KVM_HINTS_DEDICATED)) + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) return; __pv_init_lock_hash(); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 26d713ecad34..c9b14020f4dd 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -145,6 +145,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; + pgprot_t pte_prot; pte_t pte, *ptep; va = (unsigned long)ldt_slot_va(slot) + offset; @@ -163,7 +164,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) * target via some kernel interface which misses a * permission check. */ - pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL)); + pte_prot = __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL); + /* Filter out unsuppored __PAGE_KERNEL* bits: */ + pgprot_val(pte_prot) &= __supported_pte_mask; + pte = pfn_pte(pfn, pte_prot); set_pte_at(mm, va, ptep, pte); pte_unmap_unlock(ptep, ptl); } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 93bd4fb603d1..a5e55d832d0a 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -30,8 +30,9 @@ #include <asm/set_memory.h> #ifdef CONFIG_KEXEC_FILE -static struct kexec_file_ops *kexec_file_loaders[] = { +const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_bzImage64_ops, + NULL }; #endif @@ -364,27 +365,6 @@ void arch_crash_save_vmcoreinfo(void) /* arch-dependent functionality related to kexec file-based syscall */ #ifdef CONFIG_KEXEC_FILE -int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len) -{ - int i, ret = -ENOEXEC; - struct kexec_file_ops *fops; - - for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) { - fops = kexec_file_loaders[i]; - if (!fops || !fops->probe) - continue; - - ret = fops->probe(buf, buf_len); - if (!ret) { - image->fops = fops; - return ret; - } - } - - return ret; -} - void *arch_kexec_kernel_image_load(struct kimage *image) { vfree(image->arch.elf_headers); @@ -399,88 +379,53 @@ void *arch_kexec_kernel_image_load(struct kimage *image) image->cmdline_buf_len); } -int arch_kimage_file_post_load_cleanup(struct kimage *image) -{ - if (!image->fops || !image->fops->cleanup) - return 0; - - return image->fops->cleanup(image->image_loader_data); -} - -#ifdef CONFIG_KEXEC_VERIFY_SIG -int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, - unsigned long kernel_len) -{ - if (!image->fops || !image->fops->verify_sig) { - pr_debug("kernel loader does not support signature verification."); - return -EKEYREJECTED; - } - - return image->fops->verify_sig(kernel, kernel_len); -} -#endif - /* * Apply purgatory relocations. * - * ehdr: Pointer to elf headers - * sechdrs: Pointer to section headers. - * relsec: section index of SHT_RELA section. + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtabsec: Corresponding symtab. * * TODO: Some of the code belongs to generic code. Move that in kexec.c. */ -int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, - Elf64_Shdr *sechdrs, unsigned int relsec) +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, const Elf_Shdr *relsec, + const Elf_Shdr *symtabsec) { unsigned int i; Elf64_Rela *rel; Elf64_Sym *sym; void *location; - Elf64_Shdr *section, *symtabsec; unsigned long address, sec_base, value; const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; - /* - * ->sh_offset has been modified to keep the pointer to section - * contents in memory - */ - rel = (void *)sechdrs[relsec].sh_offset; - - /* Section to which relocations apply */ - section = &sechdrs[sechdrs[relsec].sh_info]; - - pr_debug("Applying relocate section %u to %u\n", relsec, - sechdrs[relsec].sh_info); - - /* Associated symbol table */ - symtabsec = &sechdrs[sechdrs[relsec].sh_link]; - - /* String table */ - if (symtabsec->sh_link >= ehdr->e_shnum) { - /* Invalid strtab section number */ - pr_err("Invalid string table section index %d\n", - symtabsec->sh_link); - return -ENOEXEC; - } + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtabsec->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; - strtab = (char *)sechdrs[symtabsec->sh_link].sh_offset; + rel = (void *)pi->ehdr + relsec->sh_offset; - /* section header string table */ - shstrtab = (char *)sechdrs[ehdr->e_shstrndx].sh_offset; + pr_debug("Applying relocate section %s to %u\n", + shstrtab + relsec->sh_name, relsec->sh_info); - for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { + for (i = 0; i < relsec->sh_size / sizeof(*rel); i++) { /* * rel[i].r_offset contains byte offset from beginning * of section to the storage unit affected. * - * This is location to update (->sh_offset). This is temporary - * buffer where section is currently loaded. This will finally - * be loaded to a different address later, pointed to by + * This is location to update. This is temporary buffer + * where section is currently loaded. This will finally be + * loaded to a different address later, pointed to by * ->sh_addr. kexec takes care of moving it * (kexec_load_segment()). */ - location = (void *)(section->sh_offset + rel[i].r_offset); + location = pi->purgatory_buf; + location += section->sh_offset; + location += rel[i].r_offset; /* Final address of the location */ address = section->sh_addr + rel[i].r_offset; @@ -491,8 +436,8 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, * to apply. ELF64_R_SYM() and ELF64_R_TYPE() macros get * these respectively. */ - sym = (Elf64_Sym *)symtabsec->sh_offset + - ELF64_R_SYM(rel[i].r_info); + sym = (void *)pi->ehdr + symtabsec->sh_offset; + sym += ELF64_R_SYM(rel[i].r_info); if (sym->st_name) name = strtab + sym->st_name; @@ -515,12 +460,12 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr, if (sym->st_shndx == SHN_ABS) sec_base = 0; - else if (sym->st_shndx >= ehdr->e_shnum) { + else if (sym->st_shndx >= pi->ehdr->e_shnum) { pr_err("Invalid section %d for symbol %s\n", sym->st_shndx, name); return -ENOEXEC; } else - sec_base = sechdrs[sym->st_shndx].sh_addr; + sec_base = pi->sechdrs[sym->st_shndx].sh_addr; value = sym->st_value; value += sec_base; diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c deleted file mode 100644 index ac7ea3a8242f..000000000000 --- a/arch/x86/kernel/pci-nommu.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Fallback functions when the main IOMMU code is not compiled in. This - code is roughly equivalent to i386. */ -#include <linux/dma-direct.h> -#include <linux/scatterlist.h> -#include <linux/string.h> -#include <linux/gfp.h> -#include <linux/pci.h> -#include <linux/mm.h> - -#include <asm/processor.h> -#include <asm/iommu.h> -#include <asm/dma.h> - -#define NOMMU_MAPPING_ERROR 0 - -static int -check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) -{ - if (hwdev && !dma_capable(hwdev, bus, size)) { - if (*hwdev->dma_mask >= DMA_BIT_MASK(32)) - printk(KERN_ERR - "nommu_%s: overflow %Lx+%zu of device mask %Lx\n", - name, (long long)bus, size, - (long long)*hwdev->dma_mask); - return 0; - } - return 1; -} - -static dma_addr_t nommu_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t bus = phys_to_dma(dev, page_to_phys(page)) + offset; - WARN_ON(size == 0); - if (!check_addr("map_single", dev, bus, size)) - return NOMMU_MAPPING_ERROR; - return bus; -} - -/* Map a set of buffers described by scatterlist in streaming - * mode for DMA. This is the scatter-gather version of the - * above pci_map_single interface. Here the scatter gather list - * elements are each tagged with the appropriate dma address - * and length. They are obtained via sg_dma_{address,length}(SG). - * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * - * Device ownership issues as mentioned above for pci_map_single are - * the same here. - */ -static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - unsigned long attrs) -{ - struct scatterlist *s; - int i; - - WARN_ON(nents == 0 || sg[0].length == 0); - - for_each_sg(sg, s, nents, i) { - BUG_ON(!sg_page(s)); - s->dma_address = sg_phys(s); - if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) - return 0; - s->dma_length = s->length; - } - return nents; -} - -static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return dma_addr == NOMMU_MAPPING_ERROR; -} - -const struct dma_map_ops nommu_dma_ops = { - .alloc = dma_generic_alloc_coherent, - .free = dma_generic_free_coherent, - .map_sg = nommu_map_sg, - .map_page = nommu_map_page, - .is_phys = 1, - .mapping_error = nommu_mapping_error, - .dma_supported = x86_dma_supported, -}; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6285697b6e56..5c623dfe39d1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> #include <linux/dma-contiguous.h> +#include <xen/xen.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void) high = true; } + if (xen_pv_domain()) { + pr_info("Ignoring crashkernel for a Xen PV domain\n"); + return; + } + /* 0 means: find the address automatically */ if (crash_base <= 0) { /* diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index df92605d8724..14c057f29979 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -26,7 +26,7 @@ static inline void signal_compat_build_tests(void) * new fields are handled in copy_siginfo_to_user32()! */ BUILD_BUG_ON(NSIGILL != 11); - BUILD_BUG_ON(NSIGFPE != 14); + BUILD_BUG_ON(NSIGFPE != 15); BUILD_BUG_ON(NSIGSEGV != 7); BUILD_BUG_ON(NSIGBUS != 5); BUILD_BUG_ON(NSIGTRAP != 4); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ff99e2b6fc54..0f1cbb042f49 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,8 @@ #include <asm/i8259.h> #include <asm/misc.h> #include <asm/qspinlock.h> +#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -390,15 +392,47 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } +/* + * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs. + * + * These are Intel CPUs that enumerate an LLC that is shared by + * multiple NUMA nodes. The LLC on these systems is shared for + * off-package data access but private to the NUMA node (half + * of the package) for on-package access. + * + * CPUID (the source of the information about the LLC) can only + * enumerate the cache as being shared *or* unshared, but not + * this particular configuration. The CPU in this case enumerates + * the cache to be shared across the entire package (spanning both + * NUMA nodes). + */ + +static const struct x86_cpu_id snc_cpu[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X }, + {} +}; + static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) - return topology_sane(c, o, "llc"); + /* Do not match if we do not have a valid APICID for cpu: */ + if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID) + return false; - return false; + /* Do not match if LLC id does not match: */ + if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2)) + return false; + + /* + * Allow the SNC topology without warning. Return of false + * means 'c' does not share the LLC of 'o'. This will be + * reflected to userspace. + */ + if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu)) + return false; + + return topology_sane(c, o, "llc"); } /* @@ -456,7 +490,8 @@ static struct sched_domain_topology_level x86_topology[] = { /* * Set if a package/die has multiple NUMA nodes inside. - * AMD Magny-Cours and Intel Cluster-on-Die have this. + * AMD Magny-Cours, Intel Cluster-on-Die, and Intel + * Sub-NUMA Clustering have this. */ static bool x86_has_numa_in_package; @@ -1536,6 +1571,8 @@ static inline void mwait_play_dead(void) void *mwait_ptr; int i; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return; if (!this_cpu_has(X86_FEATURE_MWAIT)) return; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ef32297ff17e..74392d9d51e0 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -317,7 +317,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); - do_div(deltatsc, tmp); + deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } @@ -1067,6 +1067,7 @@ static struct clocksource clocksource_tsc_early = { .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, + .list = LIST_HEAD_INIT(clocksource_tsc_early.list), }; /* @@ -1086,6 +1087,7 @@ static struct clocksource clocksource_tsc = { .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, + .list = LIST_HEAD_INIT(clocksource_tsc.list), }; void mark_tsc_unstable(char *reason) @@ -1098,13 +1100,9 @@ void mark_tsc_unstable(char *reason) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); - /* Change only the rating, when not registered */ - if (clocksource_tsc.mult) { - clocksource_mark_unstable(&clocksource_tsc); - } else { - clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; - clocksource_tsc.rating = 0; - } + + clocksource_mark_unstable(&clocksource_tsc_early); + clocksource_mark_unstable(&clocksource_tsc); } EXPORT_SYMBOL_GPL(mark_tsc_unstable); @@ -1244,7 +1242,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Don't bother refining TSC on unstable systems */ if (tsc_unstable) - return; + goto unreg; /* * Since the work is started early in boot, we may be @@ -1297,11 +1295,12 @@ static void tsc_refine_calibration_work(struct work_struct *work) out: if (tsc_unstable) - return; + goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); +unreg: clocksource_unregister(&clocksource_tsc_early); } @@ -1311,8 +1310,8 @@ static int __init init_tsc_clocksource(void) if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz) return 0; - if (check_tsc_unstable()) - return 0; + if (tsc_unstable) + goto unreg; if (tsc_clocksource_reliable) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; @@ -1328,6 +1327,7 @@ static int __init init_tsc_clocksource(void) if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; clocksource_register_khz(&clocksource_tsc, tsc_khz); +unreg: clocksource_unregister(&clocksource_tsc_early); return 0; } |
