diff options
Diffstat (limited to 'arch/x86')
85 files changed, 1210 insertions, 401 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 90b562a34d65..c1f9b3cf437c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -14,7 +14,6 @@ config X86_32 select ARCH_WANT_IPC_PARSE_VERSION select CLKSRC_I8253 select CLONE_BACKWARDS - select HAVE_GENERIC_DMA_COHERENT select MODULES_USE_ELF_REL select OLD_SIGACTION diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 9c5a67d1b9c1..2d8b9d8ca4f8 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -187,7 +187,6 @@ cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc, cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1) # does binutils support specific instructions? -asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1) asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1) avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) @@ -217,6 +216,11 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) + # Additionally, avoid generating expensive indirect jumps which + # are subject to retpolines for small number of switch cases. + # clang turns off jump table generation by default when under + # retpoline builds, however, gcc does not for x86. + KBUILD_CFLAGS += $(call cc-option,--param=case-values-threshold=20) endif archscripts: scripts_basic diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 9b5adae9cc40..e2839b5c246c 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -100,7 +100,7 @@ $(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE AFLAGS_header.o += -I$(objtree)/$(obj) $(obj)/header.o: $(obj)/zoffset.h -LDFLAGS_setup.elf := -T +LDFLAGS_setup.elf := -m elf_i386 -T $(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f0515ac895a4..6b84afdd7538 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -84,6 +84,8 @@ ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/pgtable_64.o endif +vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o + $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \ diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c new file mode 100644 index 000000000000..0ef4ad55b29b --- /dev/null +++ b/arch/x86/boot/compressed/acpi.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: GPL-2.0 +#define BOOT_CTYPE_H +#include "misc.h" +#include "error.h" +#include "../string.h" + +#include <linux/numa.h> +#include <linux/efi.h> +#include <asm/efi.h> + +/* + * Longest parameter of 'acpi=' is 'copy_dsdt', plus an extra '\0' + * for termination. + */ +#define MAX_ACPI_ARG_LENGTH 10 + +/* + * Immovable memory regions representation. Max amount of memory regions is + * MAX_NUMNODES*2. + */ +struct mem_vector immovable_mem[MAX_NUMNODES*2]; + +/* + * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex + * digits, and '\0' for termination. + */ +#define MAX_ADDR_LEN 19 + +static acpi_physical_address get_acpi_rsdp(void) +{ + acpi_physical_address addr = 0; + +#ifdef CONFIG_KEXEC + char val[MAX_ADDR_LEN] = { }; + int ret; + + ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); + if (ret < 0) + return 0; + + if (kstrtoull(val, 16, &addr)) + return 0; +#endif + return addr; +} + +/* Search EFI system tables for RSDP. */ +static acpi_physical_address efi_get_rsdp_addr(void) +{ + acpi_physical_address rsdp_addr = 0; + +#ifdef CONFIG_EFI + unsigned long systab, systab_tables, config_tables; + unsigned int nr_tables; + struct efi_info *ei; + bool efi_64; + int size, i; + char *sig; + + ei = &boot_params->efi_info; + sig = (char *)&ei->efi_loader_signature; + + if (!strncmp(sig, EFI64_LOADER_SIGNATURE, 4)) { + efi_64 = true; + } else if (!strncmp(sig, EFI32_LOADER_SIGNATURE, 4)) { + efi_64 = false; + } else { + debug_putstr("Wrong EFI loader signature.\n"); + return 0; + } + + /* Get systab from boot params. */ +#ifdef CONFIG_X86_64 + systab = ei->efi_systab | ((__u64)ei->efi_systab_hi << 32); +#else + if (ei->efi_systab_hi || ei->efi_memmap_hi) { + debug_putstr("Error getting RSDP address: EFI system table located above 4GB.\n"); + return 0; + } + systab = ei->efi_systab; +#endif + if (!systab) + error("EFI system table not found."); + + /* Handle EFI bitness properly */ + if (efi_64) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)systab; + + config_tables = stbl->tables; + nr_tables = stbl->nr_tables; + size = sizeof(efi_config_table_64_t); + } else { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)systab; + + config_tables = stbl->tables; + nr_tables = stbl->nr_tables; + size = sizeof(efi_config_table_32_t); + } + + if (!config_tables) + error("EFI config tables not found."); + + /* Get EFI tables from systab. */ + for (i = 0; i < nr_tables; i++) { + acpi_physical_address table; + efi_guid_t guid; + + config_tables += size; + + if (efi_64) { + efi_config_table_64_t *tbl = (efi_config_table_64_t *)config_tables; + + guid = tbl->guid; + table = tbl->table; + + if (!IS_ENABLED(CONFIG_X86_64) && table >> 32) { + debug_putstr("Error getting RSDP address: EFI config table located above 4GB.\n"); + return 0; + } + } else { + efi_config_table_32_t *tbl = (efi_config_table_32_t *)config_tables; + + guid = tbl->guid; + table = tbl->table; + } + + if (!(efi_guidcmp(guid, ACPI_TABLE_GUID))) + rsdp_addr = table; + else if (!(efi_guidcmp(guid, ACPI_20_TABLE_GUID))) + return table; + } +#endif + return rsdp_addr; +} + +static u8 compute_checksum(u8 *buffer, u32 length) +{ + u8 *end = buffer + length; + u8 sum = 0; + + while (buffer < end) + sum += *(buffer++); + + return sum; +} + +/* Search a block of memory for the RSDP signature. */ +static u8 *scan_mem_for_rsdp(u8 *start, u32 length) +{ + struct acpi_table_rsdp *rsdp; + u8 *address, *end; + + end = start + length; + + /* Search from given start address for the requested length */ + for (address = start; address < end; address += ACPI_RSDP_SCAN_STEP) { + /* + * Both RSDP signature and checksum must be correct. + * Note: Sometimes there exists more than one RSDP in memory; + * the valid RSDP has a valid checksum, all others have an + * invalid checksum. + */ + rsdp = (struct acpi_table_rsdp *)address; + + /* BAD Signature */ + if (!ACPI_VALIDATE_RSDP_SIG(rsdp->signature)) + continue; + + /* Check the standard checksum */ + if (compute_checksum((u8 *)rsdp, ACPI_RSDP_CHECKSUM_LENGTH)) + continue; + + /* Check extended checksum if table version >= 2 */ + if ((rsdp->revision >= 2) && + (compute_checksum((u8 *)rsdp, ACPI_RSDP_XCHECKSUM_LENGTH))) + continue; + + /* Signature and checksum valid, we have found a real RSDP */ + return address; + } + return NULL; +} + +/* Search RSDP address in EBDA. */ +static acpi_physical_address bios_get_rsdp_addr(void) +{ + unsigned long address; + u8 *rsdp; + + /* Get the location of the Extended BIOS Data Area (EBDA) */ + address = *(u16 *)ACPI_EBDA_PTR_LOCATION; + address <<= 4; + + /* + * Search EBDA paragraphs (EBDA is required to be a minimum of + * 1K length) + */ + if (address > 0x400) { + rsdp = scan_mem_for_rsdp((u8 *)address, ACPI_EBDA_WINDOW_SIZE); + if (rsdp) + return (acpi_physical_address)(unsigned long)rsdp; + } + + /* Search upper memory: 16-byte boundaries in E0000h-FFFFFh */ + rsdp = scan_mem_for_rsdp((u8 *) ACPI_HI_RSDP_WINDOW_BASE, + ACPI_HI_RSDP_WINDOW_SIZE); + if (rsdp) + return (acpi_physical_address)(unsigned long)rsdp; + + return 0; +} + +/* Return RSDP address on success, otherwise 0. */ +acpi_physical_address get_rsdp_addr(void) +{ + acpi_physical_address pa; + + pa = get_acpi_rsdp(); + + if (!pa) + pa = boot_params->acpi_rsdp_addr; + + if (!pa) + pa = efi_get_rsdp_addr(); + + if (!pa) + pa = bios_get_rsdp_addr(); + + return pa; +} + +#if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE) +/* Compute SRAT address from RSDP. */ +static unsigned long get_acpi_srat_table(void) +{ + unsigned long root_table, acpi_table; + struct acpi_table_header *header; + struct acpi_table_rsdp *rsdp; + u32 num_entries, size, len; + char arg[10]; + u8 *entry; + + rsdp = (struct acpi_table_rsdp *)(long)boot_params->acpi_rsdp_addr; + if (!rsdp) + return 0; + + /* Get ACPI root table from RSDP.*/ + if (!(cmdline_find_option("acpi", arg, sizeof(arg)) == 4 && + !strncmp(arg, "rsdt", 4)) && + rsdp->xsdt_physical_address && + rsdp->revision > 1) { + root_table = rsdp->xsdt_physical_address; + size = ACPI_XSDT_ENTRY_SIZE; + } else { + root_table = rsdp->rsdt_physical_address; + size = ACPI_RSDT_ENTRY_SIZE; + } + + if (!root_table) + return 0; + + header = (struct acpi_table_header *)root_table; + len = header->length; + if (len < sizeof(struct acpi_table_header) + size) + return 0; + + num_entries = (len - sizeof(struct acpi_table_header)) / size; + entry = (u8 *)(root_table + sizeof(struct acpi_table_header)); + + while (num_entries--) { + if (size == ACPI_RSDT_ENTRY_SIZE) + acpi_table = *(u32 *)entry; + else + acpi_table = *(u64 *)entry; + + if (acpi_table) { + header = (struct acpi_table_header *)acpi_table; + + if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_SRAT)) + return acpi_table; + } + entry += size; + } + return 0; +} + +/** + * count_immovable_mem_regions - Parse SRAT and cache the immovable + * memory regions into the immovable_mem array. + * + * Return the number of immovable memory regions on success, 0 on failure: + * + * - Too many immovable memory regions + * - ACPI off or no SRAT found + * - No immovable memory region found. + */ +int count_immovable_mem_regions(void) +{ + unsigned long table_addr, table_end, table; + struct acpi_subtable_header *sub_table; + struct acpi_table_header *table_header; + char arg[MAX_ACPI_ARG_LENGTH]; + int num = 0; + + if (cmdline_find_option("acpi", arg, sizeof(arg)) == 3 && + !strncmp(arg, "off", 3)) + return 0; + + table_addr = get_acpi_srat_table(); + if (!table_addr) + return 0; + + table_header = (struct acpi_table_header *)table_addr; + table_end = table_addr + table_header->length; + table = table_addr + sizeof(struct acpi_table_srat); + + while (table + sizeof(struct acpi_subtable_header) < table_end) { + sub_table = (struct acpi_subtable_header *)table; + if (sub_table->type == ACPI_SRAT_TYPE_MEMORY_AFFINITY) { + struct acpi_srat_mem_affinity *ma; + + ma = (struct acpi_srat_mem_affinity *)sub_table; + if (!(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && ma->length) { + immovable_mem[num].start = ma->base_address; + immovable_mem[num].size = ma->length; + num++; + } + + if (num >= MAX_NUMNODES*2) { + debug_putstr("Too many immovable memory regions, aborting.\n"); + return 0; + } + } + table += sub_table->length; + } + return num; +} +#endif /* CONFIG_RANDOMIZE_BASE && CONFIG_MEMORY_HOTREMOVE */ diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index af6cda0b7900..f1add5d85da9 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" -#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE || CONFIG_X86_5LEVEL - static unsigned long fs; static inline void set_fs(unsigned long seg) { @@ -30,5 +28,3 @@ int cmdline_find_option_bool(const char *option) { return __cmdline_find_option_bool(get_cmd_line_ptr(), option); } - -#endif diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f62e347862cc..fafb75c6c592 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -358,8 +358,11 @@ ENTRY(startup_64) * paging_prepare() sets up the trampoline and checks if we need to * enable 5-level paging. * - * Address of the trampoline is returned in RAX. - * Non zero RDX on return means we need to enable 5-level paging. + * paging_prepare() returns a two-quadword structure which lands + * into RDX:RAX: + * - Address of the trampoline is returned in RAX. + * - Non zero RDX means trampoline needs to enable 5-level + * paging. * * RSI holds real mode data and needs to be preserved across * this function call. @@ -565,7 +568,7 @@ adjust_got: * * RDI contains the return address (might be above 4G). * ECX contains the base address of the trampoline memory. - * Non zero RDX on return means we need to enable 5-level paging. + * Non zero RDX means trampoline needs to enable 5-level paging. */ ENTRY(trampoline_32bit_src) /* Set up data and stack segments */ @@ -655,8 +658,6 @@ no_longmode: .data gdt64: .word gdt_end - gdt - .long 0 - .word 0 .quad 0 gdt: .word gdt_end - gdt diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 9ed9709d9947..2e53c056ba20 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -87,10 +87,6 @@ static unsigned long get_boot_seed(void) #define KASLR_COMPRESSED_BOOT #include "../../lib/kaslr.c" -struct mem_vector { - unsigned long long start; - unsigned long long size; -}; /* Only supporting at most 4 unusable memmap regions with kaslr */ #define MAX_MEMMAP_REGIONS 4 @@ -101,6 +97,8 @@ static bool memmap_too_large; /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ static unsigned long long mem_limit = ULLONG_MAX; +/* Number of immovable memory regions */ +static int num_immovable_mem; enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, @@ -417,6 +415,9 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* Mark the memmap regions we need to avoid */ handle_mem_options(); + /* Enumerate the immovable memory regions */ + num_immovable_mem = count_immovable_mem_regions(); + #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ add_identity_map(0, PMD_SIZE); @@ -572,9 +573,9 @@ static unsigned long slots_fetch_random(void) return 0; } -static void process_mem_region(struct mem_vector *entry, - unsigned long minimum, - unsigned long image_size) +static void __process_mem_region(struct mem_vector *entry, + unsigned long minimum, + unsigned long image_size) { struct mem_vector region, overlap; unsigned long start_orig, end; @@ -650,6 +651,56 @@ static void process_mem_region(struct mem_vector *entry, } } +static bool process_mem_region(struct mem_vector *region, + unsigned long long minimum, + unsigned long long image_size) +{ + int i; + /* + * If no immovable memory found, or MEMORY_HOTREMOVE disabled, + * use @region directly. + */ + if (!num_immovable_mem) { + __process_mem_region(region, minimum, image_size); + + if (slot_area_index == MAX_SLOT_AREA) { + debug_putstr("Aborted e820/efi memmap scan (slot_areas full)!\n"); + return 1; + } + return 0; + } + +#if defined(CONFIG_MEMORY_HOTREMOVE) && defined(CONFIG_ACPI) + /* + * If immovable memory found, filter the intersection between + * immovable memory and @region. + */ + for (i = 0; i < num_immovable_mem; i++) { + unsigned long long start, end, entry_end, region_end; + struct mem_vector entry; + + if (!mem_overlaps(region, &immovable_mem[i])) + continue; + + start = immovable_mem[i].start; + end = start + immovable_mem[i].size; + region_end = region->start + region->size; + + entry.start = clamp(region->start, start, end); + entry_end = clamp(region_end, start, end); + entry.size = entry_end - entry.start; + + __process_mem_region(&entry, minimum, image_size); + + if (slot_area_index == MAX_SLOT_AREA) { + debug_putstr("Aborted e820/efi memmap scan when walking immovable regions(slot_areas full)!\n"); + return 1; + } + } +#endif + return 0; +} + #ifdef CONFIG_EFI /* * Returns true if mirror region found (and must have been processed @@ -715,11 +766,8 @@ process_efi_entries(unsigned long minimum, unsigned long image_size) region.start = md->phys_addr; region.size = md->num_pages << EFI_PAGE_SHIFT; - process_mem_region(®ion, minimum, image_size); - if (slot_area_index == MAX_SLOT_AREA) { - debug_putstr("Aborted EFI scan (slot_areas full)!\n"); + if (process_mem_region(®ion, minimum, image_size)) break; - } } return true; } @@ -746,11 +794,8 @@ static void process_e820_entries(unsigned long minimum, continue; region.start = entry->addr; region.size = entry->size; - process_mem_region(®ion, minimum, image_size); - if (slot_area_index == MAX_SLOT_AREA) { - debug_putstr("Aborted e820 scan (slot_areas full)!\n"); + if (process_mem_region(®ion, minimum, image_size)) break; - } } } diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 8dd1d5ccae58..c0d6c560df69 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -351,6 +351,9 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, /* Clear flags intended for solely in-kernel use. */ boot_params->hdr.loadflags &= ~KASLR_FLAG; + /* Save RSDP address for later use. */ + boot_params->acpi_rsdp_addr = get_rsdp_addr(); + sanitize_boot_params(boot_params); if (boot_params->screen_info.orig_video_mode == 7) { diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index a1d5918765f3..fd13655e0f9b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -25,6 +25,9 @@ #include <asm/bootparam.h> #include <asm/bootparam_utils.h> +#define BOOT_CTYPE_H +#include <linux/acpi.h> + #define BOOT_BOOT_H #include "../ctype.h" @@ -63,12 +66,14 @@ static inline void debug_puthex(const char *s) #endif -#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE /* cmdline.c */ int cmdline_find_option(const char *option, char *buffer, int bufsize); int cmdline_find_option_bool(const char *option); -#endif +struct mem_vector { + unsigned long long start; + unsigned long long size; +}; #if CONFIG_RANDOMIZE_BASE /* kaslr.c */ @@ -116,3 +121,17 @@ static inline void console_init(void) void set_sev_encryption_mask(void); #endif + +/* acpi.c */ +#ifdef CONFIG_ACPI +acpi_physical_address get_rsdp_addr(void); +#else +static inline acpi_physical_address get_rsdp_addr(void) { return 0; } +#endif + +#if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE) && defined(CONFIG_ACPI) +extern struct mem_vector immovable_mem[MAX_NUMNODES*2]; +int count_immovable_mem_regions(void); +#else +static inline int count_immovable_mem_regions(void) { return 0; } +#endif diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 9e2157371491..f8debf7aeb4c 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,5 +1,7 @@ +#include <linux/efi.h> #include <asm/e820/types.h> #include <asm/processor.h> +#include <asm/efi.h> #include "pgtable.h" #include "../string.h" @@ -37,9 +39,10 @@ int cmdline_find_option_bool(const char *option); static unsigned long find_trampoline_placement(void) { - unsigned long bios_start, ebda_start; + unsigned long bios_start = 0, ebda_start = 0; unsigned long trampoline_start; struct boot_e820_entry *entry; + char *signature; int i; /* @@ -47,8 +50,18 @@ static unsigned long find_trampoline_placement(void) * This code is based on reserve_bios_regions(). */ - ebda_start = *(unsigned short *)0x40e << 4; - bios_start = *(unsigned short *)0x413 << 10; + /* + * EFI systems may not provide legacy ROM. The memory may not be mapped + * at all. + * + * Only look for values in the legacy ROM for non-EFI system. + */ + signature = (char *)&boot_params->efi_info.efi_loader_signature; + if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && + strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) { + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; + } if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) bios_start = BIOS_START_MAX; diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index f491bbde8493..508cfa6828c5 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <asm-generic/vmlinux.lds.h> -OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) +OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT) #undef i386 diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 96a6c7563538..0149e41d42c2 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -3,7 +3,7 @@ * * Linker script for the i386 setup code */ -OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386") +OUTPUT_FORMAT("elf32-i386") OUTPUT_ARCH(i386) ENTRY(_start) diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index c4428a176973..315a67b8896b 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -13,10 +13,14 @@ */ #include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> #include <asm/asm.h> #include "ctype.h" #include "string.h" +#define KSTRTOX_OVERFLOW (1U << 31) + /* * Undef these macros so that the functions that we provide * here will have the correct names regardless of how string.h @@ -187,3 +191,140 @@ char *strchr(const char *s, int c) return NULL; return (char *)s; } + +static inline u64 __div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) +{ + union { + u64 v64; + u32 v32[2]; + } d = { dividend }; + u32 upper; + + upper = d.v32[1]; + d.v32[1] = 0; + if (upper >= divisor) { + d.v32[1] = upper / divisor; + upper %= divisor; + } + asm ("divl %2" : "=a" (d.v32[0]), "=d" (*remainder) : + "rm" (divisor), "0" (d.v32[0]), "1" (upper)); + return d.v64; +} + +static inline u64 __div_u64(u64 dividend, u32 divisor) +{ + u32 remainder; + + return __div_u64_rem(dividend, divisor, &remainder); +} + +static inline char _tolower(const char c) +{ + return c | 0x20; +} + +static const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) +{ + if (*base == 0) { + if (s[0] == '0') { + if (_tolower(s[1]) == 'x' && isxdigit(s[2])) + *base = 16; + else + *base = 8; + } else + *base = 10; + } + if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x') + s += 2; + return s; +} + +/* + * Convert non-negative integer string representation in explicitly given radix + * to an integer. + * Return number of characters consumed maybe or-ed with overflow bit. + * If overflow occurs, result integer (incorrect) is still returned. + * + * Don't you dare use this function. + */ +static unsigned int _parse_integer(const char *s, + unsigned int base, + unsigned long long *p) +{ + unsigned long long res; + unsigned int rv; + + res = 0; + rv = 0; + while (1) { + unsigned int c = *s; + unsigned int lc = c | 0x20; /* don't tolower() this line */ + unsigned int val; + + if ('0' <= c && c <= '9') + val = c - '0'; + else if ('a' <= lc && lc <= 'f') + val = lc - 'a' + 10; + else + break; + + if (val >= base) + break; + /* + * Check for overflow only if we are within range of + * it in the max base we support (16) + */ + if (unlikely(res & (~0ull << 60))) { + if (res > __div_u64(ULLONG_MAX - val, base)) + rv |= KSTRTOX_OVERFLOW; + } + res = res * base + val; + rv++; + s++; + } + *p = res; + return rv; +} + +static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) +{ + unsigned long long _res; + unsigned int rv; + + s = _parse_integer_fixup_radix(s, &base); + rv = _parse_integer(s, base, &_res); + if (rv & KSTRTOX_OVERFLOW) + return -ERANGE; + if (rv == 0) + return -EINVAL; + s += rv; + if (*s == '\n') + s++; + if (*s) + return -EINVAL; + *res = _res; + return 0; +} + +/** + * kstrtoull - convert a string to an unsigned long long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign, but not a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Used as a replacement for the obsolete simple_strtoull. Return code must + * be checked. + */ +int kstrtoull(const char *s, unsigned int base, unsigned long long *res) +{ + if (s[0] == '+') + s++; + return _kstrtoull(s, base, res); +} diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 3d78e27077f4..38d8f2f5e47e 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -29,4 +29,5 @@ extern unsigned int atou(const char *s); extern unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); +int kstrtoull(const char *s, unsigned int base, unsigned long long *res); #endif /* BOOT_STRING_H */ diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 4bb95d7ad947..9f908112bbb9 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -287,7 +287,6 @@ CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_PRINTK_TIME=y -# CONFIG_ENABLE_WARN_DEPRECATED is not set CONFIG_FRAME_WARN=1024 CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set @@ -310,3 +309,5 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_CRYPTO_AES_586=y # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_EFI_STUB=y +CONFIG_ACPI_BGRT=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 0fed049422a8..1d3badfda09e 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -286,7 +286,6 @@ CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_PRINTK_TIME=y -# CONFIG_ENABLE_WARN_DEPRECATED is not set CONFIG_MAGIC_SYSRQ=y # CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_KERNEL=y @@ -308,3 +307,6 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y # CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_EFI_STUB=y +CONFIG_EFI_MIXED=y +CONFIG_ACPI_BGRT=y diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 955ab6a3b61f..8da78595d69d 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -429,3 +429,6 @@ 421 i386 rt_sigtimedwait_time64 sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait_time64 422 i386 futex_time64 sys_futex __ia32_sys_futex 423 i386 sched_rr_get_interval_time64 sys_sched_rr_get_interval __ia32_sys_sched_rr_get_interval +425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup +426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter +427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 2ae92fddb6d5..c768447f97ec 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,9 @@ 334 common rseq __x64_sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry +425 common io_uring_setup __x64_sys_io_uring_setup +426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index b684f0294f35..e2b1447192a8 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1995,7 +1995,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) */ static void free_fake_cpuc(struct cpu_hw_events *cpuc) { - kfree(cpuc->shared_regs); + intel_cpuc_finish(cpuc); kfree(cpuc); } @@ -2007,14 +2007,11 @@ static struct cpu_hw_events *allocate_fake_cpuc(void) cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); if (!cpuc) return ERR_PTR(-ENOMEM); - - /* only needed, if we have extra_regs */ - if (x86_pmu.extra_regs) { - cpuc->shared_regs = allocate_shared_regs(cpu); - if (!cpuc->shared_regs) - goto error; - } cpuc->is_fake = 1; + + if (intel_cpuc_prepare(cpuc, cpu)) + goto error; + return cpuc; error: free_fake_cpuc(cpuc); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 17096d3cd616..35102ecdfc8d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2000,6 +2000,39 @@ static void intel_pmu_nhm_enable_all(int added) intel_pmu_enable_all(added); } +static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on) +{ + u64 val = on ? MSR_TFA_RTM_FORCE_ABORT : 0; + + if (cpuc->tfa_shadow != val) { + cpuc->tfa_shadow = val; + wrmsrl(MSR_TSX_FORCE_ABORT, val); + } +} + +static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + /* + * We're going to use PMC3, make sure TFA is set before we touch it. + */ + if (cntr == 3 && !cpuc->is_fake) + intel_set_tfa(cpuc, true); +} + +static void intel_tfa_pmu_enable_all(int added) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + /* + * If we find PMC3 is no longer used when we enable the PMU, we can + * clear TFA. + */ + if (!test_bit(3, cpuc->active_mask)) + intel_set_tfa(cpuc, false); + + intel_pmu_enable_all(added); +} + static void enable_counter_freeze(void) { update_debugctlmsr(get_debugctlmsr() | @@ -2770,6 +2803,35 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) } static struct event_constraint * +dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx) +{ + WARN_ON_ONCE(!cpuc->constraint_list); + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { + struct event_constraint *cx; + + /* + * grab pre-allocated constraint entry + */ + cx = &cpuc->constraint_list[idx]; + + /* + * initialize dynamic constraint + * with static constraint + */ + *cx = *c; + + /* + * mark constraint as dynamic + */ + cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; + } + + return c; +} + +static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { @@ -2799,27 +2861,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * only needed when constraint has not yet * been cloned (marked dynamic) */ - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - struct event_constraint *cx; - - /* - * grab pre-allocated constraint entry - */ - cx = &cpuc->constraint_list[idx]; - - /* - * initialize dynamic constraint - * with static constraint - */ - *cx = *c; - - /* - * mark constraint as dynamic, so we - * can free it later on - */ - cx->flags |= PERF_X86_EVENT_DYNAMIC; - c = cx; - } + c = dyn_constraint(cpuc, c, idx); /* * From here on, the constraint is dynamic. @@ -3357,6 +3399,26 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx, return c; } +static bool allow_tsx_force_abort = true; + +static struct event_constraint * +tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c = hsw_get_event_constraints(cpuc, idx, event); + + /* + * Without TFA we must not use PMC3. + */ + if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) { + c = dyn_constraint(cpuc, c, idx); + c->idxmsk64 &= ~(1ULL << 3); + c->weight--; + } + + return c; +} + /* * Broadwell: * @@ -3410,7 +3472,7 @@ ssize_t intel_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } -struct intel_shared_regs *allocate_shared_regs(int cpu) +static struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; int i; @@ -3442,23 +3504,24 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) return c; } -static int intel_pmu_cpu_prepare(int cpu) -{ - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); +int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) +{ if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) goto err; } - if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) { size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); - cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); + cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); if (!cpuc->constraint_list) goto err_shared_regs; + } + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { cpuc->excl_cntrs = allocate_excl_cntrs(cpu); if (!cpuc->excl_cntrs) goto err_constraint_list; @@ -3480,6 +3543,11 @@ err: return -ENOMEM; } +static int intel_pmu_cpu_prepare(int cpu) +{ + return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu); +} + static void flip_smm_bit(void *data) { unsigned long set = *(unsigned long *)data; @@ -3554,9 +3622,8 @@ static void intel_pmu_cpu_starting(int cpu) } } -static void free_excl_cntrs(int cpu) +static void free_excl_cntrs(struct cpu_hw_events *cpuc) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_excl_cntrs *c; c = cpuc->excl_cntrs; @@ -3564,9 +3631,10 @@ static void free_excl_cntrs(int cpu) if (c->core_id == -1 || --c->refcnt == 0) kfree(c); cpuc->excl_cntrs = NULL; - kfree(cpuc->constraint_list); - cpuc->constraint_list = NULL; } + + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; } static void intel_pmu_cpu_dying(int cpu) @@ -3577,9 +3645,8 @@ static void intel_pmu_cpu_dying(int cpu) disable_counter_freeze(); } -static void intel_pmu_cpu_dead(int cpu) +void intel_cpuc_finish(struct cpu_hw_events *cpuc) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; pc = cpuc->shared_regs; @@ -3589,7 +3656,12 @@ static void intel_pmu_cpu_dead(int cpu) cpuc->shared_regs = NULL; } - free_excl_cntrs(cpu); + free_excl_cntrs(cpuc); +} + +static void intel_pmu_cpu_dead(int cpu) +{ + intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu)); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -4107,8 +4179,11 @@ static struct attribute *intel_pmu_caps_attrs[] = { NULL }; +DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort); + static struct attribute *intel_pmu_attrs[] = { &dev_attr_freeze_on_smi.attr, + NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */ NULL, }; @@ -4220,6 +4295,8 @@ __init int intel_pmu_init(void) case INTEL_FAM6_CORE2_MEROM: x86_add_quirk(intel_clovertown_quirk); + /* fall through */ + case INTEL_FAM6_CORE2_MEROM_L: case INTEL_FAM6_CORE2_PENRYN: case INTEL_FAM6_CORE2_DUNNINGTON: @@ -4605,6 +4682,15 @@ __init int intel_pmu_init(void) tsx_attr = hsw_tsx_events_attrs; intel_pmu_pebs_data_source_skl( boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); + + if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) { + x86_pmu.flags |= PMU_FL_TFA; + x86_pmu.get_event_constraints = tfa_get_event_constraints; + x86_pmu.enable_all = intel_tfa_pmu_enable_all; + x86_pmu.commit_scheduling = intel_tfa_commit_scheduling; + intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr; + } + pr_cont("Skylake events, "); name = "skylake"; break; @@ -4756,7 +4842,7 @@ static __init int fixup_ht_bug(void) hardlockup_detector_perf_restart(); for_each_online_cpu(c) - free_excl_cntrs(c); + free_excl_cntrs(&per_cpu(cpu_hw_events, c)); cpus_read_unlock(); pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index c88ed39582a1..580c1b91c454 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -931,6 +931,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) ret = X86_BR_ZERO_CALL; break; } + /* fall through */ case 0x9a: /* call far absolute */ ret = X86_BR_CALL; break; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d516161c00c4..9fe64c01a2e5 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -732,6 +732,7 @@ static int uncore_pmu_event_init(struct perf_event *event) /* fixed counters have event field hardcoded to zero */ hwc->config = 0ULL; } else if (is_freerunning_event(event)) { + hwc->config = event->attr.config; if (!check_valid_freerunning_event(box, event)) return -EINVAL; event->hw.idx = UNCORE_PMC_IDX_FREERUNNING; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index cb46d602a6b8..853a49a8ccf6 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -292,8 +292,8 @@ static inline unsigned int uncore_freerunning_counter(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); - unsigned int idx = uncore_freerunning_idx(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); + unsigned int idx = uncore_freerunning_idx(event->hw.config); struct intel_uncore_pmu *pmu = box->pmu; return pmu->type->freerunning[type].counter_base + @@ -377,7 +377,7 @@ static inline unsigned int uncore_freerunning_bits(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); return box->pmu->type->freerunning[type].bits; } @@ -385,7 +385,7 @@ unsigned int uncore_freerunning_bits(struct intel_uncore_box *box, static inline int uncore_num_freerunning(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); return box->pmu->type->freerunning[type].num_counters; } @@ -399,8 +399,8 @@ static inline int uncore_num_freerunning_types(struct intel_uncore_box *box, static inline bool check_valid_freerunning_event(struct intel_uncore_box *box, struct perf_event *event) { - unsigned int type = uncore_freerunning_type(event->attr.config); - unsigned int idx = uncore_freerunning_idx(event->attr.config); + unsigned int type = uncore_freerunning_type(event->hw.config); + unsigned int idx = uncore_freerunning_idx(event->hw.config); return (type < uncore_num_freerunning_types(box, event)) && (idx < uncore_num_freerunning(box, event)); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index b12517fae77a..13493f43b247 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -442,9 +442,11 @@ static int snb_uncore_imc_event_init(struct perf_event *event) /* must be done before validate_group */ event->hw.event_base = base; - event->hw.config = cfg; event->hw.idx = idx; + /* Convert to standard encoding format for freerunning counters */ + event->hw.config = ((cfg - 1) << 8) | 0x10ff; + /* no group validation needed, we have free running counters */ return 0; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 7e75f474b076..b04ae6c8775e 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -243,6 +243,11 @@ struct cpu_hw_events { int excl_thread_id; /* 0 or 1 */ /* + * SKL TSX_FORCE_ABORT shadow + */ + u64 tfa_shadow; + + /* * AMD specific bits */ struct amd_nb *amd_nb; @@ -682,6 +687,7 @@ do { \ #define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ +#define PMU_FL_TFA 0x20 /* deal with TSX force abort */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -890,7 +896,8 @@ struct event_constraint * x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event); -struct intel_shared_regs *allocate_shared_regs(int cpu); +extern int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu); +extern void intel_cpuc_finish(struct cpu_hw_events *cpuc); int intel_pmu_init(void); @@ -1026,9 +1033,13 @@ static inline int intel_pmu_init(void) return 0; } -static inline struct intel_shared_regs *allocate_shared_regs(int cpu) +static inline int intel_cpuc_prepare(struct cpu_hw_event *cpuc, int cpu) +{ + return 0; +} + +static inline void intel_cpuc_finish(struct cpu_hw_event *cpuc) { - return NULL; } static inline int is_ht_workaround_enabled(void) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 7abb09e2eeb8..6461a16b4559 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -96,6 +96,7 @@ void __percpu **hyperv_pcpu_input_arg; EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); u32 hv_max_vp_index; +EXPORT_SYMBOL_GPL(hv_max_vp_index); static int hv_cpu_init(unsigned int cpu) { @@ -406,6 +407,13 @@ void hyperv_cleanup(void) /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); + /* + * Reset hypercall page reference before reset the page, + * let hypercall operations fail safely rather than + * panic the kernel for using invalid hypercall page + */ + hv_hypercall_pg = NULL; + /* Reset the hypercall page */ hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 1908214b9125..ce92c4acc913 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -7,7 +7,6 @@ #include <asm-generic/asm-prototypes.h> -#include <asm/page.h> #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6d6122524711..981ff9479648 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -344,6 +344,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index fa2c93cb42a2..fb04a3ded7dd 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -137,37 +137,25 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) + else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - /* See comment in copy_fxregs_to_kernel() below. */ - return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); } static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - if (IS_ENABLED(CONFIG_X86_32)) { + if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - } else { - if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - } else { - /* See comment in copy_fxregs_to_kernel() below. */ - kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); - } - } + else + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) + else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in copy_fxregs_to_kernel() below. */ - return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); } static inline void copy_kernel_to_fregs(struct fregs_state *fx) @@ -184,34 +172,8 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); - else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) + else asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); - else { - /* Using "rex64; fxsave %0" is broken because, if the memory - * operand uses any extended registers for addressing, a second - * REX prefix will be generated (to the assembler, rex64 - * followed by semicolon is a separate instruction), and hence - * the 64-bitness is lost. - * - * Using "fxsaveq %0" would be the ideal choice, but is only - * supported starting with gas 2.16. - * - * Using, as a workaround, the properly prefixed form below - * isn't accepted by any binutils version so far released, - * complaining that the same type of prefix is used twice if - * an extended register is needed for addressing (fix submitted - * to mainline 2005-11-21). - * - * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave)); - * - * This, however, we can work around by forcing the compiler to - * select an addressing mode that doesn't require extended - * registers. - */ - asm volatile( "rex64/fxsave (%[fx])" - : "=m" (fpu->state.fxsave) - : [fx] "R" (&fpu->state.fxsave)); - } } /* These macros all use (%edi)/(%rdi) as the single memory argument. */ @@ -414,6 +376,13 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); + + /* + * AVX512 state is tracked here because its use is + * known to slow the max clock speed of the core. + */ + if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) + fpu->avx512_timestamp = jiffies; return 1; } diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 202c53918ecf..2e32e178e064 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -303,6 +303,13 @@ struct fpu { unsigned char initialized; /* + * @avx512_timestamp: + * + * Records the timestamp of AVX512 use during last context switch. + */ + unsigned long avx512_timestamp; + + /* * @state: * * In-memory copy of all FPU registers that we save/restore diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c1a812bd5a27..22d05e3835f0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -48,6 +48,7 @@ #define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */ #define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */ +#define MCI_STATUS_SCRUB BIT_ULL(40) /* Error detected during scrub operation */ /* * McaX field if set indicates a given bank supports MCA extensions: @@ -307,11 +308,17 @@ enum smca_bank_types { SMCA_FP, /* Floating Point */ SMCA_L3_CACHE, /* L3 Cache */ SMCA_CS, /* Coherent Slave */ + SMCA_CS_V2, /* Coherent Slave */ SMCA_PIE, /* Power, Interrupts, etc. */ SMCA_UMC, /* Unified Memory Controller */ SMCA_PB, /* Parameter Block */ SMCA_PSP, /* Platform Security Processor */ + SMCA_PSP_V2, /* Platform Security Processor */ SMCA_SMU, /* System Management Unit */ + SMCA_SMU_V2, /* System Management Unit */ + SMCA_MP5, /* Microprocessor 5 Unit */ + SMCA_NBIO, /* Northbridge IO Unit */ + SMCA_PCIE, /* PCI Express Unit */ N_SMCA_BANK_TYPES }; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 8e40c2446fd1..ca5bc0eacb95 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -666,6 +666,12 @@ #define MSR_IA32_TSC_DEADLINE 0x000006E0 + +#define MSR_TSX_FORCE_ABORT 0x0000010F + +#define MSR_TFA_RTM_FORCE_ABORT_BIT 0 +#define MSR_TFA_RTM_FORCE_ABORT BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT) + /* P4/Xeon+ specific */ #define MSR_IA32_MCG_EAX 0x00000180 #define MSR_IA32_MCG_EBX 0x00000181 diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 0ce558a8150d..8f657286d599 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,11 +7,7 @@ #endif #ifdef CONFIG_KASAN -#ifdef CONFIG_KASAN_EXTRA -#define KASAN_STACK_ORDER 2 -#else #define KASAN_STACK_ORDER 1 -#endif #else #define KASAN_STACK_ORDER 0 #endif diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 9c85b54bf03c..0bb566315621 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -259,8 +259,7 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted -static inline bool gup_fast_permitted(unsigned long start, int nr_pages, - int write) +static inline bool gup_fast_permitted(unsigned long start, int nr_pages) { unsigned long len, end; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 33051436c864..2bb3a648fc12 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -742,7 +742,6 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, extern void enable_sep_cpu(void); extern int sysenter_setup(void); -void early_trap_pf_init(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 62004d22524a..1954dd5552a2 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -34,10 +34,7 @@ static inline void set_fs(mm_segment_t fs) } #define segment_eq(a, b) ((a).seg == (b).seg) - #define user_addr_max() (current->thread.addr_limit.seg) -#define __addr_ok(addr) \ - ((unsigned long __force)(addr) < user_addr_max()) /* * Test whether a block of memory is a valid user space address. diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 1f86e1b0a5cd..499578f7e6d7 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -23,6 +23,12 @@ struct unwind_state { #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; + /* + * If non-NULL: The current frame is incomplete and doesn't contain a + * valid BP. When looking for the next frame, use this instead of the + * non-existent saved BP. + */ + unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index 3f697a9e3f59..8cfccc3cbbf4 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -141,7 +141,6 @@ enum uv_memprotect { */ extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64); extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64); -extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64); extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *, long *); extern s64 uv_bios_freq_base(u64, u64 *); @@ -152,11 +151,7 @@ extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect); extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *); extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus); -#ifdef CONFIG_EFI extern void uv_bios_init(void); -#else -void uv_bios_init(void) { } -#endif extern unsigned long sn_rtc_cycles_per_second; extern int uv_type; diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index ef05bea7010d..de6f0d59a24f 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -332,15 +332,11 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, return _hypercall4(int, update_va_mapping, va, new_val.pte, new_val.pte >> 32, flags); } -extern int __must_check xen_event_channel_op_compat(int, void *); static inline int HYPERVISOR_event_channel_op(int cmd, void *arg) { - int rc = _hypercall2(int, event_channel_op, cmd, arg); - if (unlikely(rc == -ENOSYS)) - rc = xen_event_channel_op_compat(cmd, arg); - return rc; + return _hypercall2(int, event_channel_op, cmd, arg); } static inline int @@ -355,15 +351,10 @@ HYPERVISOR_console_io(int cmd, int count, char *str) return _hypercall3(int, console_io, cmd, count, str); } -extern int __must_check xen_physdev_op_compat(int, void *); - static inline int HYPERVISOR_physdev_op(int cmd, void *arg) { - int rc = _hypercall2(int, physdev_op, cmd, arg); - if (unlikely(rc == -ENOSYS)) - rc = xen_physdev_op_compat(cmd, arg); - return rc; + return _hypercall2(int, physdev_op, cmd, arg); } static inline int diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2624de16cd7a..8dcbf6890714 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -935,6 +935,9 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) #define HPET_RESOURCE_NAME_SIZE 9 hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, SMP_CACHE_BYTES); + if (!hpet_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 0c26b1b44e51..4203d4f0c68d 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -90,7 +90,7 @@ ret_point: .data ALIGN ENTRY(saved_magic) .long 0 -ENTRY(saved_eip) .long 0 +saved_eip: .long 0 # saved registers saved_idt: .long 0,0 diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 50b8ed0317a3..510fa12aab73 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -125,12 +125,12 @@ ENTRY(do_suspend_lowlevel) ENDPROC(do_suspend_lowlevel) .data -ENTRY(saved_rbp) .quad 0 -ENTRY(saved_rsi) .quad 0 -ENTRY(saved_rdi) .quad 0 -ENTRY(saved_rbx) .quad 0 +saved_rbp: .quad 0 +saved_rsi: .quad 0 +saved_rdi: .quad 0 +saved_rbx: .quad 0 -ENTRY(saved_rip) .quad 0 -ENTRY(saved_rsp) .quad 0 +saved_rip: .quad 0 +saved_rsp: .quad 0 ENTRY(saved_magic) .quad 0 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 2953bbf05c08..53aa234a6803 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -812,6 +812,7 @@ static int irq_polarity(int idx) return IOAPIC_POL_HIGH; case MP_IRQPOL_RESERVED: pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); + /* fall through */ case MP_IRQPOL_ACTIVE_LOW: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_POL_LOW; @@ -859,6 +860,7 @@ static int irq_trigger(int idx) return IOAPIC_EDGE; case MP_IRQTRIG_RESERVED: pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); + /* fall through */ case MP_IRQTRIG_LEVEL: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_LEVEL; @@ -2579,6 +2581,8 @@ static struct resource * __init ioapic_setup_resources(void) n *= nr_ioapics; mem = memblock_alloc(n, SMP_CACHE_BYTES); + if (!mem) + panic("%s: Failed to allocate %lu bytes\n", __func__, n); res = (void *)mem; mem += sizeof(struct resource) * nr_ioapics; @@ -2623,6 +2627,9 @@ fake_ioapic_page: #endif ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (!ioapic_phys) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); ioapic_phys = __pa(ioapic_phys); } set_fixmap_nocache(idx, ioapic_phys); diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index c4d1023fb0ab..395d46f78582 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -248,6 +248,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, switch (leaf) { case 1: l1 = &l1i; + /* fall through */ case 0: if (!l1->val) return; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 89298c83de53..e64de5149e50 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -88,11 +88,17 @@ static struct smca_bank_name smca_names[] = { [SMCA_FP] = { "floating_point", "Floating Point Unit" }, [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, [SMCA_CS] = { "coherent_slave", "Coherent Slave" }, + [SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, [SMCA_UMC] = { "umc", "Unified Memory Controller" }, [SMCA_PB] = { "param_block", "Parameter Block" }, [SMCA_PSP] = { "psp", "Platform Security Processor" }, + [SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, [SMCA_SMU] = { "smu", "System Management Unit" }, + [SMCA_SMU_V2] = { "smu", "System Management Unit" }, + [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, + [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, + [SMCA_PCIE] = { "pcie", "PCI Express Unit" }, }; static u32 smca_bank_addrs[MAX_NR_BANKS][NR_BLOCKS] __ro_after_init = @@ -138,30 +144,42 @@ static struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 }, /* ZN Core (HWID=0xB0) MCA types */ - { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF }, + { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, /* HWID 0xB0 MCATYPE 0x4 is Reserved */ - { SMCA_EX, HWID_MCATYPE(0xB0, 0x5), 0x7FF }, + { SMCA_EX, HWID_MCATYPE(0xB0, 0x5), 0xFFF }, { SMCA_FP, HWID_MCATYPE(0xB0, 0x6), 0x7F }, { SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7), 0xFF }, /* Data Fabric MCA types */ { SMCA_CS, HWID_MCATYPE(0x2E, 0x0), 0x1FF }, - { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1), 0xF }, + { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1), 0x1F }, + { SMCA_CS_V2, HWID_MCATYPE(0x2E, 0x2), 0x3FFF }, /* Unified Memory Controller MCA type */ - { SMCA_UMC, HWID_MCATYPE(0x96, 0x0), 0x3F }, + { SMCA_UMC, HWID_MCATYPE(0x96, 0x0), 0xFF }, /* Parameter Block MCA type */ { SMCA_PB, HWID_MCATYPE(0x05, 0x0), 0x1 }, /* Platform Security Processor MCA type */ { SMCA_PSP, HWID_MCATYPE(0xFF, 0x0), 0x1 }, + { SMCA_PSP_V2, HWID_MCATYPE(0xFF, 0x1), 0x3FFFF }, /* System Management Unit MCA type */ { SMCA_SMU, HWID_MCATYPE(0x01, 0x0), 0x1 }, + { SMCA_SMU_V2, HWID_MCATYPE(0x01, 0x1), 0x7FF }, + + /* Microprocessor 5 Unit MCA type */ + { SMCA_MP5, HWID_MCATYPE(0x01, 0x2), 0x3FF }, + + /* Northbridge IO Unit MCA type */ + { SMCA_NBIO, HWID_MCATYPE(0x18, 0x0), 0x1F }, + + /* PCI Express Unit MCA type */ + { SMCA_PCIE, HWID_MCATYPE(0x46, 0x0), 0x1F }, }; struct smca_bank smca_banks[MAX_NR_BANKS]; @@ -545,6 +563,40 @@ out: return offset; } +/* + * Turn off MC4_MISC thresholding banks on all family 0x15 models since + * they're not supported there. + */ +void disable_err_thresholding(struct cpuinfo_x86 *c) +{ + int i; + u64 hwcr; + bool need_toggle; + u32 msrs[] = { + 0x00000413, /* MC4_MISC0 */ + 0xc0000408, /* MC4_MISC1 */ + }; + + if (c->x86 != 0x15) + return; + + rdmsrl(MSR_K7_HWCR, hwcr); + + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); + + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + + /* Clear CntP bit safely */ + for (i = 0; i < ARRAY_SIZE(msrs); i++) + msr_clear_bit(msrs[i], 62); + + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -552,6 +604,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int bank, block, cpu = smp_processor_id(); int offset = -1; + disable_err_thresholding(c); + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) smca_configure(bank, cpu); diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 1d9b3ce662a0..c038e5c00a59 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -64,11 +64,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); #define CPER_CREATOR_MCE \ - UUID_LE(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ - 0x64, 0x90, 0xb8, 0x9d) + GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ + 0x64, 0x90, 0xb8, 0x9d) #define CPER_SECTION_TYPE_MCE \ - UUID_LE(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ - 0x04, 0x4a, 0x38, 0xfc) + GUID_INIT(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ + 0x04, 0x4a, 0x38, 0xfc) /* * CPER specification (in UEFI specification 2.3 appendix N) requires @@ -135,7 +135,7 @@ retry: goto out; /* try to skip other type records in storage */ else if (rc != sizeof(rcd) || - uuid_le_cmp(rcd.hdr.creator_id, CPER_CREATOR_MCE)) + !guid_equal(&rcd.hdr.creator_id, &CPER_CREATOR_MCE)) goto retry; memcpy(m, &rcd.mce, sizeof(*m)); rc = sizeof(*m); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6ce290c506d9..b7fb541a4873 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1612,36 +1612,6 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (c->x86 == 0x15 && c->x86_model <= 0xf) mce_flags.overflow_recov = 1; - /* - * Turn off MC4_MISC thresholding banks on those models since - * they're not supported there. - */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { - int i; - u64 hwcr; - bool need_toggle; - u32 msrs[] = { - 0x00000413, /* MC4_MISC0 */ - 0xc0000408, /* MC4_MISC1 */ - }; - - rdmsrl(MSR_K7_HWCR, hwcr); - - /* McStatusWrEn has to be set */ - need_toggle = !(hwcr & BIT(18)); - - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); - - /* Clear CntP bit safely */ - for (i = 0; i < ARRAY_SIZE(msrs); i++) - msr_clear_bit(msrs[i], 62); - - /* restore old settings */ - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr); - } } if (c->x86_vendor == X86_VENDOR_INTEL) { diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index dc3e26e905a3..65201e180fe0 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -165,6 +165,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), KERNEL ), + MCESEV( + PANIC, "Instruction fetch error in kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e81a2db42df7..3fa238a137d2 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -328,6 +328,18 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; # endif + + /* + * Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic, + * set x2apic destination mode to physcial mode when x2apic is available + * and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs + * have 8-bit APIC id. + */ +# ifdef CONFIG_X86_X2APIC + if (x2apic_supported()) + x2apic_phys = 1; +# endif + #endif } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 3668c5df90c6..5bd011737272 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -296,7 +296,7 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek, unsigned long sizek) { unsigned long hole_basek, hole_sizek; - unsigned long second_basek, second_sizek; + unsigned long second_sizek; unsigned long range0_basek, range0_sizek; unsigned long range_basek, range_sizek; unsigned long chunk_sizek; @@ -304,7 +304,6 @@ range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek, hole_basek = 0; hole_sizek = 0; - second_basek = 0; second_sizek = 0; chunk_sizek = state->chunk_sizek; gran_sizek = state->gran_sizek; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 822b7db634ee..e49b77283924 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -4,6 +4,7 @@ #include <linux/sched.h> #include <linux/kernfs.h> +#include <linux/fs_context.h> #include <linux/jump_label.h> #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -40,6 +41,21 @@ #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) + +struct rdt_fs_context { + struct kernfs_fs_context kfc; + bool enable_cdpl2; + bool enable_cdpl3; + bool enable_mba_mbps; +}; + +static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) +{ + struct kernfs_fs_context *kfc = fc->fs_private; + + return container_of(kfc, struct rdt_fs_context, kfc); +} + DECLARE_STATIC_KEY_FALSE(rdt_enable_key); /** diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 14bed6af8377..604c0e3bcc83 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -34,13 +34,6 @@ #include "pseudo_lock_event.h" /* - * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware - * prefetcher state. Details about this register can be found in the MSR - * tables for specific platforms found in Intel's SDM. - */ -#define MSR_MISC_FEATURE_CONTROL 0x000001a4 - -/* * The bits needed to disable hardware prefetching varies based on the * platform. During initialization we will discover which bits to use. */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 8388adf241b2..399601eda8e4 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -24,6 +24,7 @@ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/fs.h> +#include <linux/fs_parser.h> #include <linux/sysfs.h> #include <linux/kernfs.h> #include <linux/seq_buf.h> @@ -32,6 +33,7 @@ #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/task_work.h> +#include <linux/user_namespace.h> #include <uapi/linux/magic.h> @@ -1858,46 +1860,6 @@ static void cdp_disable_all(void) cdpl2_disable(); } -static int parse_rdtgroupfs_options(char *data) -{ - char *token, *o = data; - int ret = 0; - - while ((token = strsep(&o, ",")) != NULL) { - if (!*token) { - ret = -EINVAL; - goto out; - } - - if (!strcmp(token, "cdp")) { - ret = cdpl3_enable(); - if (ret) - goto out; - } else if (!strcmp(token, "cdpl2")) { - ret = cdpl2_enable(); - if (ret) - goto out; - } else if (!strcmp(token, "mba_MBps")) { - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - ret = set_mba_sc(true); - else - ret = -EINVAL; - if (ret) - goto out; - } else { - ret = -EINVAL; - goto out; - } - } - - return 0; - -out: - pr_err("Invalid mount option \"%s\"\n", token); - - return ret; -} - /* * We don't allow rdtgroup directories to be created anywhere * except the root directory. Thus when looking for the rdtgroup @@ -1969,13 +1931,27 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, struct kernfs_node **mon_data_kn); -static struct dentry *rdt_mount(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data) +static int rdt_enable_ctx(struct rdt_fs_context *ctx) +{ + int ret = 0; + + if (ctx->enable_cdpl2) + ret = cdpl2_enable(); + + if (!ret && ctx->enable_cdpl3) + ret = cdpl3_enable(); + + if (!ret && ctx->enable_mba_mbps) + ret = set_mba_sc(true); + + return ret; +} + +static int rdt_get_tree(struct fs_context *fc) { + struct rdt_fs_context *ctx = rdt_fc2context(fc); struct rdt_domain *dom; struct rdt_resource *r; - struct dentry *dentry; int ret; cpus_read_lock(); @@ -1984,53 +1960,42 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, * resctrl file system can only be mounted once. */ if (static_branch_unlikely(&rdt_enable_key)) { - dentry = ERR_PTR(-EBUSY); + ret = -EBUSY; goto out; } - ret = parse_rdtgroupfs_options(data); - if (ret) { - dentry = ERR_PTR(ret); + ret = rdt_enable_ctx(ctx); + if (ret < 0) goto out_cdp; - } closid_init(); ret = rdtgroup_create_info_dir(rdtgroup_default.kn); - if (ret) { - dentry = ERR_PTR(ret); - goto out_cdp; - } + if (ret < 0) + goto out_mba; if (rdt_mon_capable) { ret = mongroup_create_dir(rdtgroup_default.kn, NULL, "mon_groups", &kn_mongrp); - if (ret) { - dentry = ERR_PTR(ret); + if (ret < 0) goto out_info; - } kernfs_get(kn_mongrp); ret = mkdir_mondata_all(rdtgroup_default.kn, &rdtgroup_default, &kn_mondata); - if (ret) { - dentry = ERR_PTR(ret); + if (ret < 0) goto out_mongrp; - } kernfs_get(kn_mondata); rdtgroup_default.mon.mon_data_kn = kn_mondata; } ret = rdt_pseudo_lock_init(); - if (ret) { - dentry = ERR_PTR(ret); + if (ret) goto out_mondata; - } - dentry = kernfs_mount(fs_type, flags, rdt_root, - RDTGROUP_SUPER_MAGIC, NULL); - if (IS_ERR(dentry)) + ret = kernfs_get_tree(fc); + if (ret < 0) goto out_psl; if (rdt_alloc_capable) @@ -2059,14 +2024,95 @@ out_mongrp: kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); +out_mba: + if (ctx->enable_mba_mbps) + set_mba_sc(false); out_cdp: cdp_disable_all(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); cpus_read_unlock(); + return ret; +} + +enum rdt_param { + Opt_cdp, + Opt_cdpl2, + Opt_mba_mpbs, + nr__rdt_params +}; + +static const struct fs_parameter_spec rdt_param_specs[] = { + fsparam_flag("cdp", Opt_cdp), + fsparam_flag("cdpl2", Opt_cdpl2), + fsparam_flag("mba_mpbs", Opt_mba_mpbs), + {} +}; + +static const struct fs_parameter_description rdt_fs_parameters = { + .name = "rdt", + .specs = rdt_param_specs, +}; + +static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, &rdt_fs_parameters, param, &result); + if (opt < 0) + return opt; - return dentry; + switch (opt) { + case Opt_cdp: + ctx->enable_cdpl3 = true; + return 0; + case Opt_cdpl2: + ctx->enable_cdpl2 = true; + return 0; + case Opt_mba_mpbs: + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -EINVAL; + ctx->enable_mba_mbps = true; + return 0; + } + + return -EINVAL; +} + +static void rdt_fs_context_free(struct fs_context *fc) +{ + struct rdt_fs_context *ctx = rdt_fc2context(fc); + + kernfs_free_fs_context(fc); + kfree(ctx); +} + +static const struct fs_context_operations rdt_fs_context_ops = { + .free = rdt_fs_context_free, + .parse_param = rdt_parse_param, + .get_tree = rdt_get_tree, +}; + +static int rdt_init_fs_context(struct fs_context *fc) +{ + struct rdt_fs_context *ctx; + + ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->kfc.root = rdt_root; + ctx->kfc.magic = RDTGROUP_SUPER_MAGIC; + fc->fs_private = &ctx->kfc; + fc->ops = &rdt_fs_context_ops; + if (fc->user_ns) + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(&init_user_ns); + fc->global = true; + return 0; } static int reset_all_ctrls(struct rdt_resource *r) @@ -2239,9 +2285,10 @@ static void rdt_kill_sb(struct super_block *sb) } static struct file_system_type rdt_fs_type = { - .name = "resctrl", - .mount = rdt_mount, - .kill_sb = rdt_kill_sb, + .name = "resctrl", + .init_fs_context = rdt_init_fs_context, + .parameters = &rdt_fs_parameters, + .kill_sb = rdt_kill_sb, }; static int mon_addfile(struct kernfs_node *parent_kn, const char *name, diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 50895c2f937d..2879e234e193 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/sort.h> +#include <linux/memory_hotplug.h> #include <asm/e820/api.h> #include <asm/setup.h> @@ -671,21 +672,18 @@ __init void e820__reallocate_tables(void) int size; size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries; - n = kmalloc(size, GFP_KERNEL); + n = kmemdup(e820_table, size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820_table, size); e820_table = n; size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_kexec->nr_entries; - n = kmalloc(size, GFP_KERNEL); + n = kmemdup(e820_table_kexec, size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820_table_kexec, size); e820_table_kexec = n; size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries; - n = kmalloc(size, GFP_KERNEL); + n = kmemdup(e820_table_firmware, size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820_table_firmware, size); e820_table_firmware = n; } @@ -778,7 +776,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) { u64 addr; - addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); + addr = memblock_phys_alloc(size, align); if (addr) { e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); @@ -881,6 +879,10 @@ static int __init parse_memopt(char *p) e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); +#ifdef CONFIG_MEMORY_HOTPLUG + max_mem_size = mem_size; +#endif + return 0; } early_param("mem", parse_memopt); @@ -1095,6 +1097,9 @@ void __init e820__reserve_resources(void) res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*res) * e820_table->nr_entries); e820_res = res; for (i = 0; i < e820_table->nr_entries; i++) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 9cc108456d0b..d7432c2b1051 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -669,7 +669,7 @@ static bool is_supported_xstate_size(unsigned int test_xstate_size) return false; } -static int init_xstate_size(void) +static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ unsigned int possible_xstate_size; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3e3789c8f8e1..ef49517f6bb2 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -49,7 +49,7 @@ int ftrace_arch_code_modify_post_process(void) union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { - unsigned char e8; + unsigned char op; int offset; } __attribute__((packed)); }; @@ -59,20 +59,23 @@ static int ftrace_calc_offset(long ip, long addr) return (int)(addr - ip); } -static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +static unsigned char * +ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) { static union ftrace_code_union calc; - calc.e8 = 0xe8; + calc.op = op; calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - /* - * No locking needed, this must be called via kstop_machine - * which in essence is like running on a uniprocessor machine. - */ return calc.code; } +static unsigned char * +ftrace_call_replace(unsigned long ip, unsigned long addr) +{ + return ftrace_text_replace(0xe8, ip, addr); +} + static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -665,22 +668,6 @@ int __init ftrace_dyn_arch_init(void) return 0; } -#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER) -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) -{ - static union ftrace_code_union calc; - - /* Jmp not a call (ignore the .e8) */ - calc.e8 = 0xe9; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - /* - * ftrace external locks synchronize the access to the static variable. - */ - return calc.code; -} -#endif - /* Currently only x86_64 supports dynamic trampolines */ #ifdef CONFIG_X86_64 @@ -892,8 +879,8 @@ static void *addr_from_call(void *ptr) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.e8 != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.e8); + if (WARN_ON_ONCE(calc.op != 0xe8)) { + pr_warn("Expected e8, got %x\n", calc.op); return NULL; } @@ -964,6 +951,11 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +{ + return ftrace_text_replace(0xe9, ip, addr); +} + static int ftrace_mod_jmp(unsigned long ip, void *func) { unsigned char *new; diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 34a5c1715148..ff9bfd40429e 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -261,12 +261,8 @@ static int arch_build_bp_info(struct perf_event *bp, * allow kernel breakpoints at all. */ if (attr->bp_addr >= TASK_SIZE_MAX) { -#ifdef CONFIG_KPROBES if (within_kprobe_blacklist(attr->bp_addr)) return -EINVAL; -#else - return -EINVAL; -#endif } hw->type = X86_BREAKPOINT_EXECUTE; @@ -279,6 +275,7 @@ static int arch_build_bp_info(struct perf_event *bp, hw->len = X86_BREAKPOINT_LEN_X; return 0; } + /* fall through */ default: return -EINVAL; } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 53917a3ebf94..22f60dd26460 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -218,6 +218,9 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, params->screen_info.ext_mem_k = 0; params->alt_mem_k = 0; + /* Always fill in RSDP: it is either 0 or a valid value */ + params->acpi_rsdp_addr = boot_params.acpi_rsdp_addr; + /* Default APM info */ memset(¶ms->apm_bios_info, 0, sizeof(params->apm_bios_info)); @@ -256,7 +259,6 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, setup_efi_state(params, params_load_addr, efi_map_offset, efi_map_sz, efi_setup_data_offset); #endif - /* Setup EDD info */ memcpy(params->eddbuf, boot_params.eddbuf, EDDMAXNR * sizeof(struct edd_info)); @@ -536,9 +538,17 @@ static int bzImage64_cleanup(void *loader_data) #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { - return verify_pefile_signature(kernel, kernel_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_KEXEC_PE_SIGNATURE); + int ret; + + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + if (ret == -ENOKEY && IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING)) { + ret = verify_pefile_signature(kernel, kernel_len, + VERIFY_USE_PLATFORM_KEYRING, + VERIFYING_KEXEC_PE_SIGNATURE); + } + return ret; } #endif diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 5db08425063e..4ff6b4cdb941 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -467,6 +467,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) linux_regs->ip = addr; + /* fall through */ case 'D': case 'k': /* clear the trace bit */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 4c8acdfdc5a7..ceba408ea982 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -352,6 +352,8 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { + u64 sme_mask = sme_me_mask; + VMCOREINFO_NUMBER(phys_base); VMCOREINFO_SYMBOL(init_top_pgt); vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n", @@ -364,6 +366,7 @@ void arch_crash_save_vmcoreinfo(void) vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); + VMCOREINFO_NUMBER(sme_mask); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 13af08827eef..4bf46575568a 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -106,22 +106,22 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, void *ptr; if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from_nopanic(size, align, goal); + ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", cpu, size, __pa(ptr)); } else { - ptr = memblock_alloc_try_nid_nopanic(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, - node); + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, + node); pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", cpu, size, node, __pa(ptr)); } return ptr; #else - return memblock_alloc_from_nopanic(size, align, goal); + return memblock_alloc_from(size, align, goal); #endif } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c91ff9f9fe8a..ce1a67b70168 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -150,7 +150,7 @@ static inline void smpboot_restore_warm_reset_vector(void) */ static void smp_callin(void) { - int cpuid, phys_id; + int cpuid; /* * If waken up by an INIT in an 82489DX configuration @@ -161,11 +161,6 @@ static void smp_callin(void) cpuid = smp_processor_id(); /* - * (This works even if the APIC is not enabled.) - */ - phys_id = read_apic_id(); - - /* * the boot CPU has finished the init stage and is spinning * on callin_map until we finish. We are free to set up this * CPU, first the APIC. (this is probably redundant on most diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index e289ce1332ab..d26f9e9c3d83 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -881,12 +881,12 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { - unsigned long cr0; + unsigned long cr0 = read_cr0(); RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); #ifdef CONFIG_MATH_EMULATION - if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) { + if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) { struct math_emu_info info = { }; cond_local_irq_enable(regs); @@ -898,7 +898,6 @@ do_device_not_available(struct pt_regs *regs, long error_code) #endif /* This should not happen. */ - cr0 = read_cr0(); if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) { /* Try to fix it up and carry on. */ write_cr0(cr0 & ~X86_CR0_TS); diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 3dc26f95d46e..9b9fd4826e7a 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -320,10 +320,14 @@ bool unwind_next_frame(struct unwind_state *state) } /* Get the next frame pointer: */ - if (state->regs) + if (state->next_bp) { + next_bp = state->next_bp; + state->next_bp = NULL; + } else if (state->regs) { next_bp = (unsigned long *)state->regs->bp; - else + } else { next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task, *state->bp); + } /* Move to the next frame if it's safe: */ if (!update_stack_state(state, next_bp)) @@ -398,6 +402,21 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, bp = get_frame_pointer(task, regs); + /* + * If we crash with IP==0, the last successfully executed instruction + * was probably an indirect function call with a NULL function pointer. + * That means that SP points into the middle of an incomplete frame: + * *SP is a return pointer, and *(SP-sizeof(unsigned long)) is where we + * would have written a frame pointer if we hadn't crashed. + * Pretend that the frame is complete and that BP points to it, but save + * the real BP so that we can use it when looking for the next frame. + */ + if (regs && regs->ip == 0 && + (unsigned long *)kernel_stack_pointer(regs) >= first_frame) { + state->next_bp = bp; + bp = ((unsigned long *)kernel_stack_pointer(regs)) - 1; + } + /* Initialize stack info and make sure the frame data is accessible: */ get_stack_info(bp, state->task, &state->stack_info, &state->stack_mask); @@ -410,7 +429,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->bp < first_frame)) + (state->next_bp == NULL && state->bp < first_frame))) unwind_next_frame(state); } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 26038eacf74a..89be1be1790c 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -113,6 +113,20 @@ static struct orc_entry *orc_ftrace_find(unsigned long ip) } #endif +/* + * If we crash with IP==0, the last successfully executed instruction + * was probably an indirect function call with a NULL function pointer, + * and we don't have unwind information for NULL. + * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function + * pointer into its parent and then continue normally from there. + */ +static struct orc_entry null_orc_entry = { + .sp_offset = sizeof(long), + .sp_reg = ORC_REG_SP, + .bp_reg = ORC_REG_UNDEFINED, + .type = ORC_TYPE_CALL +}; + static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; @@ -120,6 +134,9 @@ static struct orc_entry *orc_find(unsigned long ip) if (!orc_init) return NULL; + if (ip == 0) + return &null_orc_entry; + /* For non-init vmlinux addresses, use the fast lookup table: */ if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) { unsigned int idx, start, stop; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 843feb94a950..ccf03416e434 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -745,6 +745,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * OPCODE1() of the "short" jmp which checks the same condition. */ opc1 = OPCODE2(insn) - 0x10; + /* fall through */ default: if (!is_cond_jmp_opcode(opc1)) return -ENOSYS; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 0d618ee634ac..bad8c51fee6e 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -31,7 +31,7 @@ #undef i386 /* in case the preprocessor is a 32bit one */ -OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) +OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT) #ifdef CONFIG_X86_32 OUTPUT_ARCH(i386) @@ -401,7 +401,7 @@ SECTIONS * Per-cpu symbols which need to be offset from __per_cpu_load * for the boot processor. */ -#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load +#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load INIT_PER_CPU(gdt_page); INIT_PER_CPU(irq_stack_union); diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 9119d8e41f1f..cf00ab6c6621 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -179,6 +179,8 @@ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) if (insn->addr_bytes == 2) return -EINVAL; + /* fall through */ + case -EDOM: case offsetof(struct pt_regs, bx): case offsetof(struct pt_regs, si): diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index 12d7e7fb4efd..19c6abf9ea31 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -52,7 +52,7 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); } -static void percpu_setup_debug_store(int cpu) +static void __init percpu_setup_debug_store(int cpu) { #ifdef CONFIG_CPU_SUP_INTEL int npages; diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index e3cdc85ce5b6..ee8f8ab46941 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -444,7 +444,6 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, int i; pud_t *start, *pud_start; pgprotval_t prot, eff; - pud_t *prev_pud = NULL; pud_start = start = (pud_t *)p4d_page_vaddr(addr); @@ -462,7 +461,6 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, } else note_page(m, st, __pgprot(0), 0, 3); - prev_pud = start; start++; } } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9d5c75f02295..667f1da36208 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1031,7 +1031,7 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, - unsigned int fault) + vm_fault_t fault) { struct task_struct *tsk = current; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 462fde83b515..8dc0fc0b1382 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -24,14 +24,16 @@ extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid, bool panic) +static __init void *early_alloc(size_t size, int nid, bool should_panic) { - if (panic) - return memblock_alloc_try_nid(size, size, - __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); - else - return memblock_alloc_try_nid_nopanic(size, size, + void *ptr = memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); + + if (!ptr && should_panic) + panic("%pS: Failed to allocate page, nid=%d from=%lx\n", + (void *)_RET_IP_, nid, __pa(MAX_DMA_ADDRESS)); + + return ptr; } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 12c1b7a83ed7..dfb6c4df639a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -195,15 +195,11 @@ static void __init alloc_node_data(int nid) * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ - nd_pa = memblock_phys_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); if (!nd_pa) { - nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES, - MEMBLOCK_ALLOC_ACCESSIBLE); - if (!nd_pa) { - pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", - nd_size, nid); - return; - } + pr_err("Cannot find %zu bytes in any node (initial node: %d)\n", + nd_size, nid); + return; } nd = __va(nd_pa); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 14e6119838a6..4c570612e24e 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -738,7 +738,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, { unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn; pgprot_t old_prot, new_prot, req_prot, chk_prot; - pte_t new_pte, old_pte, *tmp; + pte_t new_pte, *tmp; enum pg_level level; /* @@ -781,7 +781,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, * Convert protection attributes to 4k-format, as cpa->mask* are set * up accordingly. */ - old_pte = *kpte; + /* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */ req_prot = pgprot_large_2_4k(old_prot); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 999d6d8f0bef..bc4bc7b2f075 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -685,9 +685,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask, * that UV should be updated so that smp_call_function_many(), * etc, are optimal on UV. */ - unsigned int cpu; - - cpu = smp_processor_id(); cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) smp_call_function_many(cpumask, flush_tlb_func_remote, diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 30a5111ae5fd..527e69b12002 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -635,6 +635,22 @@ static void quirk_no_aersid(struct pci_dev *pdev) DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, 8, quirk_no_aersid); +static void quirk_intel_th_dnv(struct pci_dev *dev) +{ + struct resource *r = &dev->resource[4]; + + /* + * Denverton reports 2k of RTIT_BAR (intel_th resource 4), which + * appears to be 4 MB in reality. + */ + if (r->end == r->start + 0x7ff) { + r->start = 0; + r->end = 0x3fffff; + r->flags |= IORESOURCE_UNSET; + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x19e1, quirk_intel_th_dnv); + #ifdef CONFIG_PHYS_ADDR_T_64BIT #define AMD_141b_MMIO_BASE(x) (0x80 + (x) * 0x8) diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index b4ab779f1d47..ac9e7bf49b66 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -141,6 +141,9 @@ void * __init prom_early_alloc(unsigned long size) * wasted bootmem) and hand off chunks of it to callers. */ res = memblock_alloc(chunk_size, SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + chunk_size); BUG_ON(!res); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index eb33432f2f24..ef60d789c76e 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -45,7 +45,7 @@ static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI * callback method, which uses efi_call() directly, with the kernel page tables: */ - if (unlikely(test_bit(EFI_OLD_MEMMAP, &efi.flags))) + if (unlikely(efi_enabled(EFI_OLD_MEMMAP))) ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5); else ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5); @@ -85,18 +85,6 @@ s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, return ret; } -s64 uv_bios_call_reentrant(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, - u64 a4, u64 a5) -{ - s64 ret; - - preempt_disable(); - ret = uv_bios_call(which, a1, a2, a3, a4, a5); - preempt_enable(); - - return ret; -} - long sn_partition_id; EXPORT_SYMBOL_GPL(sn_partition_id); @@ -207,7 +195,6 @@ int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus) } EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target); -#ifdef CONFIG_EFI void uv_bios_init(void) { uv_systab = NULL; @@ -237,4 +224,3 @@ void uv_bios_init(void) } pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision); } -#endif diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index a4130b84d1ff..2c53b0f19329 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -2010,8 +2010,7 @@ static void make_per_cpu_thp(struct bau_control *smaster) int cpu; size_t hpsz = sizeof(struct hub_and_pnode) * num_possible_cpus(); - smaster->thp = kmalloc_node(hpsz, GFP_KERNEL, smaster->osnode); - memset(smaster->thp, 0, hpsz); + smaster->thp = kzalloc_node(hpsz, GFP_KERNEL, smaster->osnode); for_each_present_cpu(cpu) { smaster->thp[cpu].pnode = uv_cpu_hub_info(cpu)->pnode; smaster->thp[cpu].uvhub = uv_cpu_hub_info(cpu)->numa_blade_id; @@ -2135,15 +2134,12 @@ static int __init summarize_uvhub_sockets(int nuvhubs, static int __init init_per_cpu(int nuvhubs, int base_part_pnode) { unsigned char *uvhub_mask; - void *vp; struct uvhub_desc *uvhub_descs; if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub()) timeout_us = calculate_destination_timeout(); - vp = kmalloc_array(nuvhubs, sizeof(struct uvhub_desc), GFP_KERNEL); - uvhub_descs = (struct uvhub_desc *)vp; - memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc)); + uvhub_descs = kcalloc(nuvhubs, sizeof(struct uvhub_desc), GFP_KERNEL); uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL); if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask)) diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 4463fa72db94..f60501a384f9 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -37,8 +37,7 @@ REALMODE_OBJS = $(addprefix $(obj)/,$(realmode-y)) sed-pasyms := -n -r -e 's/^([0-9a-fA-F]+) [ABCDGRSTVW] (.+)$$/pa_\2 = \2;/p' quiet_cmd_pasyms = PASYMS $@ - cmd_pasyms = $(NM) $(filter-out FORCE,$^) | \ - sed $(sed-pasyms) | sort | uniq > $@ + cmd_pasyms = $(NM) $(real-prereqs) | sed $(sed-pasyms) | sort | uniq > $@ targets += pasyms.h $(obj)/pasyms.h: $(REALMODE_OBJS) FORCE @@ -47,7 +46,7 @@ $(obj)/pasyms.h: $(REALMODE_OBJS) FORCE targets += realmode.lds $(obj)/realmode.lds: $(obj)/pasyms.h -LDFLAGS_realmode.elf := --emit-relocs -T +LDFLAGS_realmode.elf := -m elf_i386 --emit-relocs -T CPPFLAGS_realmode.lds += -P -C -I$(objtree)/$(obj) targets += realmode.elf diff --git a/arch/x86/realmode/rm/realmode.lds.S b/arch/x86/realmode/rm/realmode.lds.S index df8e11e26bc3..3bb980800c58 100644 --- a/arch/x86/realmode/rm/realmode.lds.S +++ b/arch/x86/realmode/rm/realmode.lds.S @@ -9,7 +9,7 @@ #undef i386 -OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386") +OUTPUT_FORMAT("elf32-i386") OUTPUT_ARCH(i386) SECTIONS diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 856a85814f00..a21e1734fc1f 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2114,10 +2114,10 @@ void __init xen_relocate_p2m(void) pt = early_memremap(pt_phys, PAGE_SIZE); clear_page(pt); for (idx_pte = 0; - idx_pte < min(n_pte, PTRS_PER_PTE); - idx_pte++) { - set_pte(pt + idx_pte, - pfn_pte(p2m_pfn, PAGE_KERNEL)); + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + pt[idx_pte] = pfn_pte(p2m_pfn, + PAGE_KERNEL); p2m_pfn++; } n_pte -= PTRS_PER_PTE; @@ -2125,8 +2125,7 @@ void __init xen_relocate_p2m(void) make_lowmem_page_readonly(__va(pt_phys)); pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, PFN_DOWN(pt_phys)); - set_pmd(pmd + idx_pt, - __pmd(_PAGE_TABLE | pt_phys)); + pmd[idx_pt] = __pmd(_PAGE_TABLE | pt_phys); pt_phys += PAGE_SIZE; } n_pt -= PTRS_PER_PMD; @@ -2134,7 +2133,7 @@ void __init xen_relocate_p2m(void) make_lowmem_page_readonly(__va(pmd_phys)); pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, PFN_DOWN(pmd_phys)); - set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pud[idx_pmd] = __pud(_PAGE_TABLE | pmd_phys); pmd_phys += PAGE_SIZE; } n_pmd -= PTRS_PER_PUD; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 055e37e43541..95ce9b5be411 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -181,8 +181,15 @@ static void p2m_init_identity(unsigned long *p2m, unsigned long pfn) static void * __ref alloc_p2m_page(void) { - if (unlikely(!slab_is_available())) - return memblock_alloc(PAGE_SIZE, PAGE_SIZE); + if (unlikely(!slab_is_available())) { + void *ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + + if (!ptr) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE); + + return ptr; + } return (void *)__get_free_page(GFP_KERNEL); } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index d5f303c0e656..548d1e0a5ba1 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -12,6 +12,7 @@ #include <linux/memblock.h> #include <linux/cpuidle.h> #include <linux/cpufreq.h> +#include <linux/memory_hotplug.h> #include <asm/elf.h> #include <asm/vdso.h> @@ -589,6 +590,14 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start, if (type == E820_TYPE_RAM) { start = PAGE_ALIGN(start); end &= ~((phys_addr_t)PAGE_SIZE - 1); +#ifdef CONFIG_MEMORY_HOTPLUG + /* + * Don't allow adding memory not in E820 map while booting the + * system. Once the balloon driver is up it will remove that + * restriction again. + */ + max_mem_size = end; +#endif } e820__range_add(start, end - start, type); @@ -748,6 +757,10 @@ char * __init xen_memory_setup(void) memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_XEN_BALLOON) + xen_saved_max_mem_size = max_mem_size; +#endif + op = xen_initial_domain() ? XENMEM_machine_memory_map : XENMEM_memory_map; |