diff options
Diffstat (limited to 'arch/x86')
217 files changed, 5231 insertions, 3536 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index eb3abf8ac44e..586b786b3edf 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -7,6 +7,9 @@ obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support obj-$(CONFIG_XEN) += xen/ +# Hyper-V paravirtualization support +obj-$(CONFIG_HYPERVISOR_GUEST) += hyperv/ + # lguest paravirtualization support obj-$(CONFIG_LGUEST_GUEST) += lguest/ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e487493bbd47..33007aa74111 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -46,6 +46,7 @@ config X86 select ARCH_CLOCKSOURCE_DATA select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER @@ -53,7 +54,10 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MMIO_FLUSH select ARCH_HAS_PMEM_API if X86_64 + select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN + select ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI @@ -105,6 +109,7 @@ config X86 select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_CC_STACKPROTECTOR @@ -309,9 +314,6 @@ config ARCH_SUPPORTS_UPROBES config FIX_EARLYCON_MEM def_bool y -config DEBUG_RODATA - def_bool y - config PGTABLE_LEVELS int default 4 if X86_64 @@ -1070,7 +1072,7 @@ config X86_MCE_THRESHOLD def_bool y config X86_MCE_INJECT - depends on X86_MCE + depends on X86_MCE && X86_LOCAL_APIC tristate "Machine check injector support" ---help--- Provide support for injecting machine checks for testing purposes. @@ -1994,10 +1996,6 @@ config RANDOMIZE_BASE theoretically possible, but the implementations are further limited due to memory layouts. - If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot - time. To enable it, boot with "kaslr" on the kernel command - line (which will also disable hibernation). - If unsure, say N. # Relocation on x86 needs some additional build support diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 67eec55093a5..c4cba00dbdee 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -109,25 +109,6 @@ config DEBUG_WX If in doubt, say "Y". -config DEBUG_SET_MODULE_RONX - bool "Set loadable kernel module data as NX and text as RO" - depends on MODULES - ---help--- - This option helps catch unintended modifications to loadable - kernel module's text and read-only data. It also prevents execution - of module data. Such protection may interfere with run-time code - patching and dynamic kernel tracing - and they might also protect - against certain classes of kernel exploits. - If in doubt, say "N". - -config DEBUG_NX_TEST - tristate "Testcase for the NX non-executable stack feature" - depends on DEBUG_KERNEL && m - ---help--- - This option enables a testcase for the CPU NX capability - and the software setup of this feature. - If in doubt, say "N" - config DOUBLEFAULT default y bool "Enable doublefault exception handler" if EXPERT diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index e5612f3e3b57..9b42b6d1e902 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -333,6 +333,7 @@ size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); size_t strlen(const char *s); +char *strchr(const char *s, int c); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ff01c8fc76f7..801c7a158e55 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -32,160 +32,13 @@ static void setup_boot_services##bits(struct efi_config *c) \ \ table = (typeof(table))sys_table; \ \ + c->runtime_services = table->runtime; \ c->boot_services = table->boottime; \ c->text_output = table->con_out; \ } BOOT_SERVICES(32); BOOT_SERVICES(64); -void efi_char16_printk(efi_system_table_t *, efi_char16_t *); - -static efi_status_t -__file_size32(void *__fh, efi_char16_t *filename_16, - void **handle, u64 *file_sz) -{ - efi_file_handle_32_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - u32 info_sz; - - status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to open file: "); - efi_char16_printk(sys_table, filename_16); - efi_printk(sys_table, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table, "Failed to get file info size\n"); - return status; - } - -grow: - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for file info\n"); - return status; - } - - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_early(free_pool, info); - goto grow; - } - - *file_sz = info->file_size; - efi_call_early(free_pool, info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to get initrd info\n"); - - return status; -} - -static efi_status_t -__file_size64(void *__fh, efi_char16_t *filename_16, - void **handle, u64 *file_sz) -{ - efi_file_handle_64_t *h, *fh = __fh; - efi_file_info_t *info; - efi_status_t status; - efi_guid_t info_guid = EFI_FILE_INFO_ID; - u64 info_sz; - - status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16, - EFI_FILE_MODE_READ, (u64)0); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to open file: "); - efi_char16_printk(sys_table, filename_16); - efi_printk(sys_table, "\n"); - return status; - } - - *handle = h; - - info_sz = 0; - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, NULL); - if (status != EFI_BUFFER_TOO_SMALL) { - efi_printk(sys_table, "Failed to get file info size\n"); - return status; - } - -grow: - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - info_sz, (void **)&info); - if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to alloc mem for file info\n"); - return status; - } - - status = efi_early->call((unsigned long)h->get_info, h, &info_guid, - &info_sz, info); - if (status == EFI_BUFFER_TOO_SMALL) { - efi_call_early(free_pool, info); - goto grow; - } - - *file_sz = info->file_size; - efi_call_early(free_pool, info); - - if (status != EFI_SUCCESS) - efi_printk(sys_table, "Failed to get initrd info\n"); - - return status; -} -efi_status_t -efi_file_size(efi_system_table_t *sys_table, void *__fh, - efi_char16_t *filename_16, void **handle, u64 *file_sz) -{ - if (efi_early->is64) - return __file_size64(__fh, filename_16, handle, file_sz); - - return __file_size32(__fh, filename_16, handle, file_sz); -} - -efi_status_t -efi_file_read(void *handle, unsigned long *size, void *addr) -{ - unsigned long func; - - if (efi_early->is64) { - efi_file_handle_64_t *fh = handle; - - func = (unsigned long)fh->read; - return efi_early->call(func, handle, size, addr); - } else { - efi_file_handle_32_t *fh = handle; - - func = (unsigned long)fh->read; - return efi_early->call(func, handle, size, addr); - } -} - -efi_status_t efi_file_close(void *handle) -{ - if (efi_early->is64) { - efi_file_handle_64_t *fh = handle; - - return efi_early->call((unsigned long)fh->close, handle); - } else { - efi_file_handle_32_t *fh = handle; - - return efi_early->call((unsigned long)fh->close, handle); - } -} - static inline efi_status_t __open_volume32(void *__image, void **__fh) { efi_file_io_interface_t *io; @@ -249,30 +102,8 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh) void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str) { - unsigned long output_string; - size_t offset; - - if (efi_early->is64) { - struct efi_simple_text_output_protocol_64 *out; - u64 *func; - - offset = offsetof(typeof(*out), output_string); - output_string = efi_early->text_output + offset; - out = (typeof(out))(unsigned long)efi_early->text_output; - func = (u64 *)output_string; - - efi_early->call(*func, out, str); - } else { - struct efi_simple_text_output_protocol_32 *out; - u32 *func; - - offset = offsetof(typeof(*out), output_string); - output_string = efi_early->text_output + offset; - out = (typeof(out))(unsigned long)efi_early->text_output; - func = (u32 *)output_string; - - efi_early->call(*func, out, str); - } + efi_call_proto(efi_simple_text_output_protocol, output_string, + efi_early->text_output, str); } static efi_status_t @@ -1157,6 +988,13 @@ struct boot_params *efi_main(struct efi_config *c, else setup_boot_services32(efi_early); + /* + * If the boot loader gave us a value for secure_boot then we use that, + * otherwise we ask the BIOS. + */ + if (boot_params->secure_boot == efi_secureboot_mode_unset) + boot_params->secure_boot = efi_get_secureboot(sys_table); + setup_graphics(boot_params); setup_efi_pci(boot_params); diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index fd0b6a272dd5..d85b9625e836 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -82,7 +82,7 @@ ENTRY(efi_pe_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 32(%eax) + add %esi, 40(%eax) pushl %eax call make_boot_params @@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry) /* Relocate efi_config->call() */ leal efi32_config(%esi), %eax - add %esi, 32(%eax) + add %esi, 40(%eax) pushl %eax 2: call efi_main @@ -264,7 +264,7 @@ relocated: #ifdef CONFIG_EFI_STUB .data efi32_config: - .fill 4,8,0 + .fill 5,8,0 .long efi_call_phys .long 0 .byte 0 diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 4d85e600db78..d2ae1f821e0c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -264,7 +264,7 @@ ENTRY(efi_pe_entry) /* * Relocate efi_config->call(). */ - addq %rbp, efi64_config+32(%rip) + addq %rbp, efi64_config+40(%rip) movq %rax, %rdi call make_boot_params @@ -284,7 +284,7 @@ handover_entry: * Relocate efi_config->call(). */ movq efi_config(%rip), %rax - addq %rbp, 32(%rax) + addq %rbp, 40(%rax) 2: movq efi_config(%rip), %rdi call efi_main @@ -456,14 +456,14 @@ efi_config: #ifdef CONFIG_EFI_MIXED .global efi32_config efi32_config: - .fill 4,8,0 + .fill 5,8,0 .quad efi64_thunk .byte 0 #endif .global efi64_config efi64_config: - .fill 4,8,0 + .fill 5,8,0 .quad efi_call .byte 1 #endif /* CONFIG_EFI_STUB */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index a66854d99ee1..8b7c9e75edcb 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -11,6 +11,7 @@ */ #include "misc.h" #include "error.h" +#include "../boot.h" #include <generated/compile.h> #include <linux/module.h> @@ -52,15 +53,22 @@ static unsigned long get_boot_seed(void) #include "../../lib/kaslr.c" struct mem_vector { - unsigned long start; - unsigned long size; + unsigned long long start; + unsigned long long size; }; +/* Only supporting at most 4 unusable memmap regions with kaslr */ +#define MAX_MEMMAP_REGIONS 4 + +static bool memmap_too_large; + enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, MEM_AVOID_INITRD, MEM_AVOID_CMDLINE, MEM_AVOID_BOOTPARAMS, + MEM_AVOID_MEMMAP_BEGIN, + MEM_AVOID_MEMMAP_END = MEM_AVOID_MEMMAP_BEGIN + MAX_MEMMAP_REGIONS - 1, MEM_AVOID_MAX, }; @@ -77,6 +85,123 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) return true; } +/** + * _memparse - Parse a string with mem suffixes into a number + * @ptr: Where parse begins + * @retptr: (output) Optional pointer to next char after parse completes + * + * Parses a string into a number. The number stored at @ptr is + * potentially suffixed with K, M, G, T, P, E. + */ +static unsigned long long _memparse(const char *ptr, char **retptr) +{ + char *endptr; /* Local pointer to end of parsed string */ + + unsigned long long ret = simple_strtoull(ptr, &endptr, 0); + + switch (*endptr) { + case 'E': + case 'e': + ret <<= 10; + case 'P': + case 'p': + ret <<= 10; + case 'T': + case 't': + ret <<= 10; + case 'G': + case 'g': + ret <<= 10; + case 'M': + case 'm': + ret <<= 10; + case 'K': + case 'k': + ret <<= 10; + endptr++; + default: + break; + } + + if (retptr) + *retptr = endptr; + + return ret; +} + +static int +parse_memmap(char *p, unsigned long long *start, unsigned long long *size) +{ + char *oldp; + + if (!p) + return -EINVAL; + + /* We don't care about this option here */ + if (!strncmp(p, "exactmap", 8)) + return -EINVAL; + + oldp = p; + *size = _memparse(p, &p); + if (p == oldp) + return -EINVAL; + + switch (*p) { + case '@': + /* Skip this region, usable */ + *start = 0; + *size = 0; + return 0; + case '#': + case '$': + case '!': + *start = _memparse(p + 1, &p); + return 0; + } + + return -EINVAL; +} + +static void mem_avoid_memmap(void) +{ + char arg[128]; + int rc; + int i; + char *str; + + /* See if we have any memmap areas */ + rc = cmdline_find_option("memmap", arg, sizeof(arg)); + if (rc <= 0) + return; + + i = 0; + str = arg; + while (str && (i < MAX_MEMMAP_REGIONS)) { + int rc; + unsigned long long start, size; + char *k = strchr(str, ','); + + if (k) + *k++ = 0; + + rc = parse_memmap(str, &start, &size); + if (rc < 0) + break; + str = k; + /* A usable region that should not be skipped */ + if (size == 0) + continue; + + mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start; + mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size; + i++; + } + + /* More than 4 memmaps, fail kaslr */ + if ((i >= MAX_MEMMAP_REGIONS) && str) + memmap_too_large = true; +} + /* * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). * The mem_avoid array is used to store the ranges that need to be avoided @@ -197,6 +322,9 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ + /* Mark the memmap regions we need to avoid */ + mem_avoid_memmap(); + #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ add_identity_map(0, PMD_SIZE); @@ -379,6 +507,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum, int i; unsigned long addr; + /* Check if we had too many memmaps. */ + if (memmap_too_large) { + debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n"); + return 0; + } + /* Make sure minimum is aligned. */ minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN); @@ -456,7 +590,7 @@ void choose_random_location(unsigned long input, /* Walk e820 and find a random address. */ random_addr = find_random_phys_addr(min_addr, output_size); if (!random_addr) { - warn("KASLR disabled: could not find suitable E820 region!"); + warn("Physical KASLR disabled: no suitable memory region!"); } else { /* Update the new physical address location. */ if (*output != random_addr) { diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index cc3bd583dce1..5457b02fc050 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -14,6 +14,7 @@ #include <linux/types.h> #include "ctype.h" +#include "string.h" int memcmp(const void *s1, const void *s2, size_t len) { @@ -155,3 +156,16 @@ char *strstr(const char *s1, const char *s2) } return NULL; } + +/** + * strchr - Find the first occurrence of the character c in the string s. + * @s: the string to be searched + * @c: the character to search for + */ +char *strchr(const char *s, int c) +{ + while (*s != (char)c) + if (*s++ == '\0') + return NULL; + return (char *)s; +} diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 725e820602b1..113588ddb43f 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -18,4 +18,13 @@ int memcmp(const void *s1, const void *s2, size_t len); #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp +extern int strcmp(const char *str1, const char *str2); +extern int strncmp(const char *cs, const char *ct, size_t count); +extern size_t strlen(const char *s); +extern char *strstr(const char *s1, const char *s2); +extern size_t strnlen(const char *s, size_t maxlen); +extern unsigned int atou(const char *s); +extern unsigned long long simple_strtoull(const char *cp, char **endp, + unsigned int base); + #endif /* BOOT_STRING_H */ diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 383a6f84a060..3c465184ff8a 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -46,28 +46,49 @@ #ifdef __x86_64__ -.data +# constants in mergeable sections, linker can reorder and merge +.section .rodata.cst16.gf128mul_x_ble_mask, "aM", @progbits, 16 .align 16 .Lgf128mul_x_ble_mask: .octa 0x00000000000000010000000000000087 +.section .rodata.cst16.POLY, "aM", @progbits, 16 +.align 16 POLY: .octa 0xC2000000000000000000000000000001 +.section .rodata.cst16.TWOONE, "aM", @progbits, 16 +.align 16 TWOONE: .octa 0x00000001000000000000000000000001 -# order of these constants should not change. -# more specifically, ALL_F should follow SHIFT_MASK, -# and ZERO should follow ALL_F - +.section .rodata.cst16.SHUF_MASK, "aM", @progbits, 16 +.align 16 SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F +.section .rodata.cst16.MASK1, "aM", @progbits, 16 +.align 16 MASK1: .octa 0x0000000000000000ffffffffffffffff +.section .rodata.cst16.MASK2, "aM", @progbits, 16 +.align 16 MASK2: .octa 0xffffffffffffffff0000000000000000 -SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 -ALL_F: .octa 0xffffffffffffffffffffffffffffffff -ZERO: .octa 0x00000000000000000000000000000000 +.section .rodata.cst16.ONE, "aM", @progbits, 16 +.align 16 ONE: .octa 0x00000000000000000000000000000001 +.section .rodata.cst16.F_MIN_MASK, "aM", @progbits, 16 +.align 16 F_MIN_MASK: .octa 0xf1f2f3f4f5f6f7f8f9fafbfcfdfeff0 +.section .rodata.cst16.dec, "aM", @progbits, 16 +.align 16 dec: .octa 0x1 +.section .rodata.cst16.enc, "aM", @progbits, 16 +.align 16 enc: .octa 0x2 +# order of these constants should not change. +# more specifically, ALL_F should follow SHIFT_MASK, +# and zero should follow ALL_F +.section .rodata, "a", @progbits +.align 16 +SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 +ALL_F: .octa 0xffffffffffffffffffffffffffffffff + .octa 0x00000000000000000000000000000000 + .text diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index 522ab68d1c88..d664382c6e56 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -122,23 +122,39 @@ #include <linux/linkage.h> #include <asm/inst.h> -.data +# constants in mergeable sections, linker can reorder and merge +.section .rodata.cst16.POLY, "aM", @progbits, 16 .align 16 - POLY: .octa 0xC2000000000000000000000000000001 + +.section .rodata.cst16.POLY2, "aM", @progbits, 16 +.align 16 POLY2: .octa 0xC20000000000000000000001C2000000 -TWOONE: .octa 0x00000001000000000000000000000001 -# order of these constants should not change. -# more specifically, ALL_F should follow SHIFT_MASK, and ZERO should follow ALL_F +.section .rodata.cst16.TWOONE, "aM", @progbits, 16 +.align 16 +TWOONE: .octa 0x00000001000000000000000000000001 +.section .rodata.cst16.SHUF_MASK, "aM", @progbits, 16 +.align 16 SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F -SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 -ALL_F: .octa 0xffffffffffffffffffffffffffffffff -ZERO: .octa 0x00000000000000000000000000000000 + +.section .rodata.cst16.ONE, "aM", @progbits, 16 +.align 16 ONE: .octa 0x00000000000000000000000000000001 + +.section .rodata.cst16.ONEf, "aM", @progbits, 16 +.align 16 ONEf: .octa 0x01000000000000000000000000000000 +# order of these constants should not change. +# more specifically, ALL_F should follow SHIFT_MASK, and zero should follow ALL_F +.section .rodata, "a", @progbits +.align 16 +SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 +ALL_F: .octa 0xffffffffffffffffffffffffffffffff + .octa 0x00000000000000000000000000000000 + .text diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 31c34ee131f3..93de8ea51548 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -740,9 +740,11 @@ static int helper_rfc4106_encrypt(struct aead_request *req) *((__be32 *)(iv+12)) = counter; if (sg_is_last(req->src) && - req->src->offset + req->src->length <= PAGE_SIZE && + (!PageHighMem(sg_page(req->src)) || + req->src->offset + req->src->length <= PAGE_SIZE) && sg_is_last(req->dst) && - req->dst->offset + req->dst->length <= PAGE_SIZE) { + (!PageHighMem(sg_page(req->dst)) || + req->dst->offset + req->dst->length <= PAGE_SIZE)) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); assoc = scatterwalk_map(&src_sg_walk); @@ -822,9 +824,11 @@ static int helper_rfc4106_decrypt(struct aead_request *req) *((__be32 *)(iv+12)) = counter; if (sg_is_last(req->src) && - req->src->offset + req->src->length <= PAGE_SIZE && + (!PageHighMem(sg_page(req->src)) || + req->src->offset + req->src->length <= PAGE_SIZE) && sg_is_last(req->dst) && - req->dst->offset + req->dst->length <= PAGE_SIZE) { + (!PageHighMem(sg_page(req->dst)) || + req->dst->offset + req->dst->length <= PAGE_SIZE)) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); assoc = scatterwalk_map(&src_sg_walk); @@ -1020,7 +1024,8 @@ struct { const char *basename; struct simd_skcipher_alg *simd; } aesni_simd_skciphers2[] = { -#if IS_ENABLED(CONFIG_CRYPTO_PCBC) +#if (defined(MODULE) && IS_ENABLED(CONFIG_CRYPTO_PCBC)) || \ + IS_BUILTIN(CONFIG_CRYPTO_PCBC) { .algname = "pcbc(aes)", .drvname = "pcbc-aes-aesni", @@ -1084,9 +1089,9 @@ static void aesni_free_simds(void) aesni_simd_skciphers[i]; i++) simd_skcipher_free(aesni_simd_skciphers[i]); - for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) && - aesni_simd_skciphers2[i].simd; i++) - simd_skcipher_free(aesni_simd_skciphers2[i].simd); + for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++) + if (aesni_simd_skciphers2[i].simd) + simd_skcipher_free(aesni_simd_skciphers2[i].simd); } static int __init aesni_init(void) @@ -1167,7 +1172,7 @@ static int __init aesni_init(void) simd = simd_skcipher_create_compat(algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) - goto unregister_simds; + continue; aesni_simd_skciphers2[i].simd = simd; } diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index aa9e8bd163f6..f7c495e2863c 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -571,7 +571,9 @@ ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) vmovdqu y6, 14 * 16(rio); \ vmovdqu y7, 15 * 16(rio); -.data + +/* NB: section is mergeable, all elements must be aligned 16-byte blocks */ +.section .rodata.cst16, "aM", @progbits, 16 .align 16 #define SHUFB_BYTES(idx) \ @@ -711,6 +713,7 @@ ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03 /* 4-bit mask */ +.section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 .align 4 .L0f0f0f0f: .long 0x0f0f0f0f diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 16186c18656d..eee5b3982cfd 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -610,20 +610,25 @@ ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) vmovdqu y6, 14 * 32(rio); \ vmovdqu y7, 15 * 32(rio); -.data -.align 32 +.section .rodata.cst32.shufb_16x16b, "aM", @progbits, 32 +.align 32 #define SHUFB_BYTES(idx) \ 0 + (idx), 4 + (idx), 8 + (idx), 12 + (idx) - .Lshufb_16x16b: .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3) .byte SHUFB_BYTES(0), SHUFB_BYTES(1), SHUFB_BYTES(2), SHUFB_BYTES(3) +.section .rodata.cst32.pack_bswap, "aM", @progbits, 32 +.align 32 .Lpack_bswap: .long 0x00010203, 0x04050607, 0x80808080, 0x80808080 .long 0x00010203, 0x04050607, 0x80808080, 0x80808080 +/* NB: section is mergeable, all elements must be aligned 16-byte blocks */ +.section .rodata.cst16, "aM", @progbits, 16 +.align 16 + /* For CTR-mode IV byteswap */ .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 @@ -750,6 +755,7 @@ ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .byte 0x00, 0x0d, 0x0a, 0x07, 0x04, 0x01, 0x0e, 0x0b .byte 0x08, 0x05, 0x02, 0x0f, 0x0c, 0x09, 0x06, 0x03 +.section .rodata.cst4.L0f0f0f0f, "aM", @progbits, 4 .align 4 /* 4-bit mask */ .L0f0f0f0f: diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index 14fa1966bf01..b4a8806234ea 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -195,19 +195,29 @@ vpshufb rmask, x0, x0; \ vpshufb rmask, x1, x1; -.data - +.section .rodata.cst16.bswap_mask, "aM", @progbits, 16 .align 16 .Lbswap_mask: .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12 +.section .rodata.cst16.bswap128_mask, "aM", @progbits, 16 +.align 16 .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 +.section .rodata.cst16.bswap_iv_mask, "aM", @progbits, 16 +.align 16 .Lbswap_iv_mask: .byte 7, 6, 5, 4, 3, 2, 1, 0, 7, 6, 5, 4, 3, 2, 1, 0 + +.section .rodata.cst4.16_mask, "aM", @progbits, 4 +.align 4 .L16_mask: .byte 16, 16, 16, 16 +.section .rodata.cst4.32_mask, "aM", @progbits, 4 +.align 4 .L32_mask: .byte 32, 0, 0, 0 +.section .rodata.cst4.first_mask, "aM", @progbits, 4 +.align 4 .Lfirst_mask: .byte 0x1f, 0, 0, 0 diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index c419389889cd..952d3156a933 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -225,8 +225,7 @@ vpshufb rmask, x2, x2; \ vpshufb rmask, x3, x3; -.data - +.section .rodata.cst16, "aM", @progbits, 16 .align 16 .Lxts_gf128mul_and_shl1_mask: .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 @@ -244,10 +243,19 @@ .byte 12, 13, 14, 15, 8, 9, 10, 11, 7, 6, 5, 4, 3, 2, 1, 0 .Lrkr_dec_QBAR_QBAR_QBAR_QBAR: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 + +.section .rodata.cst4.L16_mask, "aM", @progbits, 4 +.align 4 .L16_mask: .byte 16, 16, 16, 16 + +.section .rodata.cst4.L32_mask, "aM", @progbits, 4 +.align 4 .L32_mask: .byte 32, 0, 0, 0 + +.section .rodata.cst4.first_mask, "aM", @progbits, 4 +.align 4 .Lfirst_mask: .byte 0x1f, 0, 0, 0 diff --git a/arch/x86/crypto/chacha20-avx2-x86_64.S b/arch/x86/crypto/chacha20-avx2-x86_64.S index 16694e625f77..3a2dc3dc6cac 100644 --- a/arch/x86/crypto/chacha20-avx2-x86_64.S +++ b/arch/x86/crypto/chacha20-avx2-x86_64.S @@ -11,13 +11,18 @@ #include <linux/linkage.h> -.data +.section .rodata.cst32.ROT8, "aM", @progbits, 32 .align 32 - ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003 .octa 0x0e0d0c0f0a09080b0605040702010003 + +.section .rodata.cst32.ROT16, "aM", @progbits, 32 +.align 32 ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302 .octa 0x0d0c0f0e09080b0a0504070601000302 + +.section .rodata.cst32.CTRINC, "aM", @progbits, 32 +.align 32 CTRINC: .octa 0x00000003000000020000000100000000 .octa 0x00000007000000060000000500000004 diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 3a33124e9112..3f511a7d73b8 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -11,11 +11,14 @@ #include <linux/linkage.h> -.data +.section .rodata.cst16.ROT8, "aM", @progbits, 16 .align 16 - ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003 +.section .rodata.cst16.ROT16, "aM", @progbits, 16 +.align 16 ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302 +.section .rodata.cst16.CTRINC, "aM", @progbits, 16 +.align 16 CTRINC: .octa 0x00000003000000020000000100000000 .text diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index f910d1d449f0..1e6af1b35f7b 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -11,7 +11,7 @@ #include <crypto/algapi.h> #include <crypto/chacha20.h> -#include <linux/crypto.h> +#include <crypto/internal/skcipher.h> #include <linux/kernel.h> #include <linux/module.h> #include <asm/fpu/api.h> @@ -63,36 +63,37 @@ static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, } } -static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes) +static int chacha20_simd(struct skcipher_request *req) { - u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1]; - struct blkcipher_walk walk; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); + u32 *state, state_buf[16 + 2] __aligned(8); + struct skcipher_walk walk; int err; - if (nbytes <= CHACHA20_BLOCK_SIZE || !may_use_simd()) - return crypto_chacha20_crypt(desc, dst, src, nbytes); + BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16); + state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN); - state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN); + if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd()) + return crypto_chacha20_crypt(req); - blkcipher_walk_init(&walk, dst, src, nbytes); - err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE); + err = skcipher_walk_virt(&walk, req, true); - crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv); + crypto_chacha20_init(state, ctx, walk.iv); kernel_fpu_begin(); while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); - err = blkcipher_walk_done(desc, &walk, - walk.nbytes % CHACHA20_BLOCK_SIZE); + err = skcipher_walk_done(&walk, + walk.nbytes % CHACHA20_BLOCK_SIZE); } if (walk.nbytes) { chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, walk.nbytes); - err = blkcipher_walk_done(desc, &walk, 0); + err = skcipher_walk_done(&walk, 0); } kernel_fpu_end(); @@ -100,27 +101,22 @@ static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst, return err; } -static struct crypto_alg alg = { - .cra_name = "chacha20", - .cra_driver_name = "chacha20-simd", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, - .cra_blocksize = 1, - .cra_type = &crypto_blkcipher_type, - .cra_ctxsize = sizeof(struct chacha20_ctx), - .cra_alignmask = sizeof(u32) - 1, - .cra_module = THIS_MODULE, - .cra_u = { - .blkcipher = { - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .geniv = "seqiv", - .setkey = crypto_chacha20_setkey, - .encrypt = chacha20_simd, - .decrypt = chacha20_simd, - }, - }, +static struct skcipher_alg alg = { + .base.cra_name = "chacha20", + .base.cra_driver_name = "chacha20-simd", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha20_ctx), + .base.cra_alignmask = sizeof(u32) - 1, + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA20_KEY_SIZE, + .max_keysize = CHACHA20_KEY_SIZE, + .ivsize = CHACHA20_IV_SIZE, + .chunksize = CHACHA20_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = chacha20_simd, + .decrypt = chacha20_simd, }; static int __init chacha20_simd_mod_init(void) @@ -133,12 +129,12 @@ static int __init chacha20_simd_mod_init(void) boot_cpu_has(X86_FEATURE_AVX2) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); #endif - return crypto_register_alg(&alg); + return crypto_register_skcipher(&alg); } static void __exit chacha20_simd_mod_fini(void) { - crypto_unregister_alg(&alg); + crypto_unregister_skcipher(&alg); } module_init(chacha20_simd_mod_init); diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index dc05f010ca9b..7a7de27c6f41 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -312,7 +312,7 @@ do_return: ret ENDPROC(crc_pcl) -.section .rodata, "a", %progbits +.section .rodata, "a", @progbits ################################################################ ## jump table Table is 129 entries x 2 bytes each ################################################################ diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S index 35e97569d05f..de04d3e98d8d 100644 --- a/arch/x86/crypto/crct10dif-pcl-asm_64.S +++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S @@ -554,12 +554,11 @@ _only_less_than_2: ENDPROC(crc_t10dif_pcl) -.data - +.section .rodata, "a", @progbits +.align 16 # precomputed constants # these constants are precomputed from the poly: # 0x8bb70000 (0x8bb7 scaled to 32 bits) -.align 16 # Q = 0x18BB70000 # rk1 = 2^(32*3) mod Q << 32 # rk2 = 2^(32*5) mod Q << 32 @@ -613,14 +612,23 @@ rk20: +.section .rodata.cst16.mask1, "aM", @progbits, 16 +.align 16 mask1: .octa 0x80808080808080808080808080808080 + +.section .rodata.cst16.mask2, "aM", @progbits, 16 +.align 16 mask2: .octa 0x00000000FFFFFFFFFFFFFFFFFFFFFFFF +.section .rodata.cst16.SHUF_MASK, "aM", @progbits, 16 +.align 16 SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F +.section .rodata.cst32.pshufb_shf_table, "aM", @progbits, 32 +.align 32 pshufb_shf_table: # use these values for shift constants for the pshufb instruction # different alignments result in values as shown: diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S index 038f6ae87c5e..f3e91647ca27 100644 --- a/arch/x86/crypto/des3_ede-asm_64.S +++ b/arch/x86/crypto/des3_ede-asm_64.S @@ -537,7 +537,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) ret; ENDPROC(des3_ede_x86_64_crypt_blk_3way) -.data +.section .rodata, "a", @progbits .align 16 .L_s1: .quad 0x0010100001010400, 0x0000000000000000 diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index eed55c8cca4f..f94375a8dcd1 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -20,8 +20,7 @@ #include <asm/inst.h> #include <asm/frame.h> -.data - +.section .rodata.cst16.bswap_mask, "aM", @progbits, 16 .align 16 .Lbswap_mask: .octa 0x000102030405060708090a0b0c0d0e0f diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index eff2f414e22b..3b6e70d085da 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -11,11 +11,13 @@ #include <linux/linkage.h> -.data +.section .rodata.cst32.ANMASK, "aM", @progbits, 32 .align 32 - ANMASK: .octa 0x0000000003ffffff0000000003ffffff .octa 0x0000000003ffffff0000000003ffffff + +.section .rodata.cst32.ORMASK, "aM", @progbits, 32 +.align 32 ORMASK: .octa 0x00000000010000000000000001000000 .octa 0x00000000010000000000000001000000 diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index 338c748054ed..c88c670cb5fc 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -11,10 +11,12 @@ #include <linux/linkage.h> -.data +.section .rodata.cst16.ANMASK, "aM", @progbits, 16 .align 16 - ANMASK: .octa 0x0000000003ffffff0000000003ffffff + +.section .rodata.cst16.ORMASK, "aM", @progbits, 16 +.align 16 ORMASK: .octa 0x00000000010000000000000001000000 .text diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S index 8be571808342..2925077f8c6a 100644 --- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S @@ -29,11 +29,12 @@ .file "serpent-avx-x86_64-asm_64.S" -.data +.section .rodata.cst16.bswap128_mask, "aM", @progbits, 16 .align 16 - .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 +.section .rodata.cst16.xts_gf128mul_and_shl1_mask, "aM", @progbits, 16 +.align 16 .Lxts_gf128mul_and_shl1_mask: .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S index 97c48add33ed..d67888f2a52a 100644 --- a/arch/x86/crypto/serpent-avx2-asm_64.S +++ b/arch/x86/crypto/serpent-avx2-asm_64.S @@ -20,13 +20,18 @@ .file "serpent-avx2-asm_64.S" -.data +.section .rodata.cst16.bswap128_mask, "aM", @progbits, 16 .align 16 - .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 + +.section .rodata.cst16.xts_gf128mul_and_shl1_mask_0, "aM", @progbits, 16 +.align 16 .Lxts_gf128mul_and_shl1_mask_0: .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 + +.section .rodata.cst16.xts_gf128mul_and_shl1_mask_1, "aM", @progbits, 16 +.align 16 .Lxts_gf128mul_and_shl1_mask_1: .byte 0x0e, 1, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0 diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S index 96df6a39d7e2..93b945597ecf 100644 --- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S @@ -281,11 +281,13 @@ ENTRY(sha1_mb_mgr_get_comp_job_avx2) ret ENDPROC(sha1_mb_mgr_get_comp_job_avx2) -.data - +.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16 .align 16 clear_low_nibble: .octa 0x000000000000000000000000FFFFFFF0 + +.section .rodata.cst8, "aM", @progbits, 8 +.align 8 one: .quad 1 two: diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S index 63a0d9c8e31f..7a93b1c0d69a 100644 --- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S +++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_submit_avx2.S @@ -203,8 +203,7 @@ return_null: ENDPROC(sha1_mb_mgr_submit_avx2) -.data - +.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16 .align 16 clear_low_nibble: .octa 0x000000000000000000000000FFFFFFF0 diff --git a/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S b/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S index c9dae1cd2919..20f77aa633de 100644 --- a/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S +++ b/arch/x86/crypto/sha1-mb/sha1_x8_avx2.S @@ -461,21 +461,32 @@ lloop: ENDPROC(sha1_x8_avx2) -.data - +.section .rodata.cst32.K00_19, "aM", @progbits, 32 .align 32 K00_19: .octa 0x5A8279995A8279995A8279995A827999 .octa 0x5A8279995A8279995A8279995A827999 + +.section .rodata.cst32.K20_39, "aM", @progbits, 32 +.align 32 K20_39: .octa 0x6ED9EBA16ED9EBA16ED9EBA16ED9EBA1 .octa 0x6ED9EBA16ED9EBA16ED9EBA16ED9EBA1 + +.section .rodata.cst32.K40_59, "aM", @progbits, 32 +.align 32 K40_59: .octa 0x8F1BBCDC8F1BBCDC8F1BBCDC8F1BBCDC .octa 0x8F1BBCDC8F1BBCDC8F1BBCDC8F1BBCDC + +.section .rodata.cst32.K60_79, "aM", @progbits, 32 +.align 32 K60_79: .octa 0xCA62C1D6CA62C1D6CA62C1D6CA62C1D6 .octa 0xCA62C1D6CA62C1D6CA62C1D6CA62C1D6 + +.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32 +.align 32 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x0c0d0e0f08090a0b0405060700010203 .octa 0x0c0d0e0f08090a0b0405060700010203 diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S index 874a651b9e7d..ebbdba72ae07 100644 --- a/arch/x86/crypto/sha1_ni_asm.S +++ b/arch/x86/crypto/sha1_ni_asm.S @@ -293,10 +293,12 @@ ENTRY(sha1_ni_transform) ret ENDPROC(sha1_ni_transform) -.data - -.align 64 +.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 +.align 16 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x000102030405060708090a0b0c0d0e0f + +.section .rodata.cst16.UPPER_WORD_MASK, "aM", @progbits, 16 +.align 16 UPPER_WORD_MASK: .octa 0xFFFFFFFF000000000000000000000000 diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 92b3b5d75ba9..e08888a1a5f2 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -463,7 +463,7 @@ done_hash: ret ENDPROC(sha256_transform_avx) -.data +.section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 K256: .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 @@ -483,14 +483,21 @@ K256: .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 +.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 +.align 16 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x0c0d0e0f08090a0b0405060700010203 +.section .rodata.cst16._SHUF_00BA, "aM", @progbits, 16 +.align 16 # shuffle xBxA -> 00BA _SHUF_00BA: .octa 0xFFFFFFFFFFFFFFFF0b0a090803020100 +.section .rodata.cst16._SHUF_DC00, "aM", @progbits, 16 +.align 16 # shuffle xDxC -> DC00 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF + #endif diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 570ec5ec62d7..89c8f09787d2 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -723,7 +723,7 @@ done_hash: ret ENDPROC(sha256_transform_rorx) -.data +.section .rodata.cst512.K256, "aM", @progbits, 512 .align 64 K256: .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 @@ -759,14 +759,21 @@ K256: .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 +.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32 +.align 32 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x0c0d0e0f08090a0b0405060700010203,0x0c0d0e0f08090a0b0405060700010203 # shuffle xBxA -> 00BA +.section .rodata.cst32._SHUF_00BA, "aM", @progbits, 32 +.align 32 _SHUF_00BA: .octa 0xFFFFFFFFFFFFFFFF0b0a090803020100,0xFFFFFFFFFFFFFFFF0b0a090803020100 # shuffle xDxC -> DC00 +.section .rodata.cst32._SHUF_DC00, "aM", @progbits, 32 +.align 32 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF,0x0b0a090803020100FFFFFFFFFFFFFFFF + #endif diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index a78a0694ddef..8fe6338bcc84 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -284,11 +284,13 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) ret ENDPROC(sha256_mb_mgr_get_comp_job_avx2) -.data - +.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16 .align 16 clear_low_nibble: .octa 0x000000000000000000000000FFFFFFF0 + +.section .rodata.cst8, "aM", @progbits, 8 +.align 8 one: .quad 1 two: diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S index 7ea670e25acc..b36ae7454084 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_submit_avx2.S @@ -208,8 +208,7 @@ return_null: ENDPROC(sha256_mb_mgr_submit_avx2) -.data - +.section .rodata.cst16.clear_low_nibble, "aM", @progbits, 16 .align 16 clear_low_nibble: .octa 0x000000000000000000000000FFFFFFF0 diff --git a/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S index aa21aea4c722..1687c80c5995 100644 --- a/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_x8_avx2.S @@ -437,7 +437,8 @@ Lrounds_16_xx: ret ENDPROC(sha256_x8_avx2) -.data + +.section .rodata.K256_8, "a", @progbits .align 64 K256_8: .octa 0x428a2f98428a2f98428a2f98428a2f98 @@ -568,10 +569,14 @@ K256_8: .octa 0xbef9a3f7bef9a3f7bef9a3f7bef9a3f7 .octa 0xc67178f2c67178f2c67178f2c67178f2 .octa 0xc67178f2c67178f2c67178f2c67178f2 + +.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32 +.align 32 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x0c0d0e0f08090a0b0405060700010203 .octa 0x0c0d0e0f08090a0b0405060700010203 +.section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 .global K256 K256: diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index 2cedc44e8121..39b83c93e7fd 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -474,7 +474,7 @@ done_hash: ret ENDPROC(sha256_transform_ssse3) -.data +.section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 K256: .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 @@ -494,13 +494,19 @@ K256: .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 +.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 +.align 16 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x0c0d0e0f08090a0b0405060700010203 +.section .rodata.cst16._SHUF_00BA, "aM", @progbits, 16 +.align 16 # shuffle xBxA -> 00BA _SHUF_00BA: .octa 0xFFFFFFFFFFFFFFFF0b0a090803020100 +.section .rodata.cst16._SHUF_DC00, "aM", @progbits, 16 +.align 16 # shuffle xDxC -> DC00 _SHUF_DC00: .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S index 748cdf21a938..fb58f58ecfbc 100644 --- a/arch/x86/crypto/sha256_ni_asm.S +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -329,7 +329,7 @@ ENTRY(sha256_ni_transform) ret ENDPROC(sha256_ni_transform) -.data +.section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 K256: .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 @@ -349,5 +349,7 @@ K256: .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 +.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 +.align 16 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x0c0d0e0f08090a0b0405060700010203 diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 565274d6a641..39235fefe6f7 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -370,14 +370,17 @@ ENDPROC(sha512_transform_avx) ######################################################################## ### Binary Data -.data - +.section .rodata.cst16.XMM_QWORD_BSWAP, "aM", @progbits, 16 .align 16 - # Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb. XMM_QWORD_BSWAP: .octa 0x08090a0b0c0d0e0f0001020304050607 +# Mergeable 640-byte rodata section. This allows linker to merge the table +# with other, exactly the same 640-byte fragment of another rodata section +# (if such section exists). +.section .rodata.cst640.K512, "aM", @progbits, 640 +.align 64 # K[t] used in SHA512 hashing K512: .quad 0x428a2f98d728ae22,0x7137449123ef65cd diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 1f20b35d8573..7f5f6c6ec72e 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -684,8 +684,11 @@ ENDPROC(sha512_transform_rorx) ######################################################################## ### Binary Data -.data +# Mergeable 640-byte rodata section. This allows linker to merge the table +# with other, exactly the same 640-byte fragment of another rodata section +# (if such section exists). +.section .rodata.cst640.K512, "aM", @progbits, 640 .align 64 # K[t] used in SHA512 hashing K512: @@ -730,14 +733,17 @@ K512: .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 +.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32 .align 32 - # Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb. PSHUFFLE_BYTE_FLIP_MASK: .octa 0x08090a0b0c0d0e0f0001020304050607 .octa 0x18191a1b1c1d1e1f1011121314151617 +.section .rodata.cst32.MASK_YMM_LO, "aM", @progbits, 32 +.align 32 MASK_YMM_LO: .octa 0x00000000000000000000000000000000 .octa 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF + #endif diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index 9c1bb6d58141..2dd3674b5a1e 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -221,7 +221,7 @@ static struct sha512_hash_ctx *sha512_ctx_mgr_resubmit } static struct sha512_hash_ctx - *sha512_ctx_mgr_get_comp_ctx(struct sha512_ctx_mgr *mgr) + *sha512_ctx_mgr_get_comp_ctx(struct mcryptd_alg_cstate *cstate) { /* * If get_comp_job returns NULL, there are no jobs complete. @@ -233,11 +233,17 @@ static struct sha512_hash_ctx * Otherwise, all jobs currently being managed by the hash_ctx_mgr * still need processing. */ + struct sha512_ctx_mgr *mgr; struct sha512_hash_ctx *ctx; + unsigned long flags; + mgr = cstate->mgr; + spin_lock_irqsave(&cstate->work_lock, flags); ctx = (struct sha512_hash_ctx *) sha512_job_mgr_get_comp_job(&mgr->mgr); - return sha512_ctx_mgr_resubmit(mgr, ctx); + ctx = sha512_ctx_mgr_resubmit(mgr, ctx); + spin_unlock_irqrestore(&cstate->work_lock, flags); + return ctx; } static void sha512_ctx_mgr_init(struct sha512_ctx_mgr *mgr) @@ -246,12 +252,17 @@ static void sha512_ctx_mgr_init(struct sha512_ctx_mgr *mgr) } static struct sha512_hash_ctx - *sha512_ctx_mgr_submit(struct sha512_ctx_mgr *mgr, + *sha512_ctx_mgr_submit(struct mcryptd_alg_cstate *cstate, struct sha512_hash_ctx *ctx, const void *buffer, uint32_t len, int flags) { + struct sha512_ctx_mgr *mgr; + unsigned long irqflags; + + mgr = cstate->mgr; + spin_lock_irqsave(&cstate->work_lock, irqflags); if (flags & (~HASH_ENTIRE)) { /* * User should not pass anything other than FIRST, UPDATE, or @@ -351,20 +362,26 @@ static struct sha512_hash_ctx } } - return sha512_ctx_mgr_resubmit(mgr, ctx); + ctx = sha512_ctx_mgr_resubmit(mgr, ctx); + spin_unlock_irqrestore(&cstate->work_lock, irqflags); + return ctx; } -static struct sha512_hash_ctx *sha512_ctx_mgr_flush(struct sha512_ctx_mgr *mgr) +static struct sha512_hash_ctx *sha512_ctx_mgr_flush(struct mcryptd_alg_cstate *cstate) { + struct sha512_ctx_mgr *mgr; struct sha512_hash_ctx *ctx; + unsigned long flags; + mgr = cstate->mgr; + spin_lock_irqsave(&cstate->work_lock, flags); while (1) { ctx = (struct sha512_hash_ctx *) sha512_job_mgr_flush(&mgr->mgr); /* If flush returned 0, there are no more jobs in flight. */ if (!ctx) - return NULL; + break; /* * If flush returned a job, resubmit the job to finish @@ -378,8 +395,10 @@ static struct sha512_hash_ctx *sha512_ctx_mgr_flush(struct sha512_ctx_mgr *mgr) * the sha512_ctx_mgr still need processing. Loop. */ if (ctx) - return ctx; + break; } + spin_unlock_irqrestore(&cstate->work_lock, flags); + return ctx; } static int sha512_mb_init(struct ahash_request *areq) @@ -439,11 +458,11 @@ static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx, sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(&rctx->areq); kernel_fpu_begin(); - sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, + sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, rctx->walk.data, nbytes, flag); if (!sha_ctx) { if (flush) - sha_ctx = sha512_ctx_mgr_flush(cstate->mgr); + sha_ctx = sha512_ctx_mgr_flush(cstate); } kernel_fpu_end(); if (sha_ctx) @@ -471,11 +490,12 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, struct sha512_hash_ctx *sha_ctx; struct mcryptd_hash_request_ctx *req_ctx; int ret; + unsigned long flags; /* remove from work list */ - spin_lock(&cstate->work_lock); + spin_lock_irqsave(&cstate->work_lock, flags); list_del(&rctx->waiter); - spin_unlock(&cstate->work_lock); + spin_unlock_irqrestore(&cstate->work_lock, flags); if (irqs_disabled()) rctx->complete(&req->base, err); @@ -486,14 +506,14 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, } /* check to see if there are other jobs that are done */ - sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate->mgr); + sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate); while (sha_ctx) { req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx); ret = sha_finish_walk(&req_ctx, cstate, false); if (req_ctx) { - spin_lock(&cstate->work_lock); + spin_lock_irqsave(&cstate->work_lock, flags); list_del(&req_ctx->waiter); - spin_unlock(&cstate->work_lock); + spin_unlock_irqrestore(&cstate->work_lock, flags); req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) @@ -504,7 +524,7 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, local_bh_enable(); } } - sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate->mgr); + sha_ctx = sha512_ctx_mgr_get_comp_ctx(cstate); } return 0; @@ -515,6 +535,7 @@ static void sha512_mb_add_list(struct mcryptd_hash_request_ctx *rctx, { unsigned long next_flush; unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL); + unsigned long flags; /* initialize tag */ rctx->tag.arrival = jiffies; /* tag the arrival time */ @@ -522,9 +543,9 @@ static void sha512_mb_add_list(struct mcryptd_hash_request_ctx *rctx, next_flush = rctx->tag.arrival + delay; rctx->tag.expire = next_flush; - spin_lock(&cstate->work_lock); + spin_lock_irqsave(&cstate->work_lock, flags); list_add_tail(&rctx->waiter, &cstate->work_list); - spin_unlock(&cstate->work_lock); + spin_unlock_irqrestore(&cstate->work_lock, flags); mcryptd_arm_flusher(cstate, delay); } @@ -565,7 +586,7 @@ static int sha512_mb_update(struct ahash_request *areq) sha_ctx = (struct sha512_hash_ctx *) ahash_request_ctx(areq); sha512_mb_add_list(rctx, cstate); kernel_fpu_begin(); - sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, + sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, rctx->walk.data, nbytes, HASH_UPDATE); kernel_fpu_end(); @@ -628,7 +649,7 @@ static int sha512_mb_finup(struct ahash_request *areq) sha512_mb_add_list(rctx, cstate); kernel_fpu_begin(); - sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, + sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, rctx->walk.data, nbytes, flag); kernel_fpu_end(); @@ -677,8 +698,7 @@ static int sha512_mb_final(struct ahash_request *areq) /* flag HASH_FINAL and 0 data size */ sha512_mb_add_list(rctx, cstate); kernel_fpu_begin(); - sha_ctx = sha512_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0, - HASH_LAST); + sha_ctx = sha512_ctx_mgr_submit(cstate, sha_ctx, &data, 0, HASH_LAST); kernel_fpu_end(); /* check if anything is returned */ @@ -940,7 +960,7 @@ static unsigned long sha512_mb_flusher(struct mcryptd_alg_cstate *cstate) break; kernel_fpu_begin(); sha_ctx = (struct sha512_hash_ctx *) - sha512_ctx_mgr_flush(cstate->mgr); + sha512_ctx_mgr_flush(cstate); kernel_fpu_end(); if (!sha_ctx) { pr_err("sha512_mb error: nothing got flushed for" diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S index 3ddba19a0db6..7c629caebc05 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_flush_avx2.S @@ -280,12 +280,18 @@ ENTRY(sha512_mb_mgr_get_comp_job_avx2) pop %rbx ret ENDPROC(sha512_mb_mgr_get_comp_job_avx2) -.data -.align 16 +.section .rodata.cst8.one, "aM", @progbits, 8 +.align 8 one: .quad 1 + +.section .rodata.cst8.two, "aM", @progbits, 8 +.align 8 two: .quad 2 + +.section .rodata.cst8.three, "aM", @progbits, 8 +.align 8 three: .quad 3 diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S index 815f07bdd1f8..4ba709ba78e5 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_submit_avx2.S @@ -209,8 +209,9 @@ return_null: xor job_rax, job_rax jmp return ENDPROC(sha512_mb_mgr_submit_avx2) -.data +/* UNUSED? +.section .rodata.cst16, "aM", @progbits, 16 .align 16 H0: .int 0x6a09e667 H1: .int 0xbb67ae85 @@ -220,3 +221,4 @@ H4: .int 0x510e527f H5: .int 0x9b05688c H6: .int 0x1f83d9ab H7: .int 0x5be0cd19 +*/ diff --git a/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S index 31ab1eff6413..e22e907643a6 100644 --- a/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S +++ b/arch/x86/crypto/sha512-mb/sha512_x4_avx2.S @@ -361,7 +361,7 @@ Lrounds_16_xx: ret ENDPROC(sha512_x4_avx2) -.data +.section .rodata.K512_4, "a", @progbits .align 64 K512_4: .octa 0x428a2f98d728ae22428a2f98d728ae22,\ @@ -525,5 +525,7 @@ K512_4: .octa 0x6c44198c4a4758176c44198c4a475817,\ 0x6c44198c4a4758176c44198c4a475817 +.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32 +.align 32 PSHUFFLE_BYTE_FLIP_MASK: .octa 0x08090a0b0c0d0e0f0001020304050607 .octa 0x18191a1b1c1d1e1f1011121314151617 diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index e610e29cbc81..66bbd9058a90 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -369,14 +369,17 @@ ENDPROC(sha512_transform_ssse3) ######################################################################## ### Binary Data -.data - +.section .rodata.cst16.XMM_QWORD_BSWAP, "aM", @progbits, 16 .align 16 - # Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb. XMM_QWORD_BSWAP: .octa 0x08090a0b0c0d0e0f0001020304050607 +# Mergeable 640-byte rodata section. This allows linker to merge the table +# with other, exactly the same 640-byte fragment of another rodata section +# (if such section exists). +.section .rodata.cst640.K512, "aM", @progbits, 640 +.align 64 # K[t] used in SHA512 hashing K512: .quad 0x428a2f98d728ae22,0x7137449123ef65cd diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index dc66273e610d..b3f49d286348 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -29,11 +29,13 @@ .file "twofish-avx-x86_64-asm_64.S" -.data +.section .rodata.cst16.bswap128_mask, "aM", @progbits, 16 .align 16 - .Lbswap128_mask: .byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0 + +.section .rodata.cst16.xts_gf128mul_and_shl1_mask, "aM", @progbits, 16 +.align 16 .Lxts_gf128mul_and_shl1_mask: .byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 701d29f8e4d3..57f7ec35216e 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -255,23 +255,6 @@ ENTRY(__switch_to_asm) END(__switch_to_asm) /* - * The unwinder expects the last frame on the stack to always be at the same - * offset from the end of the page, which allows it to validate the stack. - * Calling schedule_tail() directly would break that convention because its an - * asmlinkage function so its argument has to be pushed on the stack. This - * wrapper creates a proper "end of stack" frame header before the call. - */ -ENTRY(schedule_tail_wrapper) - FRAME_BEGIN - - pushl %eax - call schedule_tail - popl %eax - - FRAME_END - ret -ENDPROC(schedule_tail_wrapper) -/* * A newly forked process directly context switches into this address. * * eax: prev task we switched from @@ -279,15 +262,24 @@ ENDPROC(schedule_tail_wrapper) * edi: kernel thread arg */ ENTRY(ret_from_fork) - call schedule_tail_wrapper + FRAME_BEGIN /* help unwinder find end of stack */ + + /* + * schedule_tail() is asmlinkage so we have to put its 'prev' argument + * on the stack. + */ + pushl %eax + call schedule_tail + popl %eax testl %ebx, %ebx jnz 1f /* kernel threads are uncommon */ 2: /* When we fork, we trace the syscall return in the child, too. */ - movl %esp, %eax + leal FRAME_OFFSET(%esp), %eax call syscall_return_slowpath + FRAME_END jmp restore_all /* kernel thread */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 5b219707c2f2..044d18ebc43c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,6 +36,7 @@ #include <asm/smap.h> #include <asm/pgtable_types.h> #include <asm/export.h> +#include <asm/frame.h> #include <linux/err.h> .code64 @@ -408,17 +409,19 @@ END(__switch_to_asm) * r12: kernel thread arg */ ENTRY(ret_from_fork) + FRAME_BEGIN /* help unwinder find end of stack */ movq %rax, %rdi - call schedule_tail /* rdi: 'prev' task parameter */ + call schedule_tail /* rdi: 'prev' task parameter */ - testq %rbx, %rbx /* from kernel_thread? */ - jnz 1f /* kernel threads are uncommon */ + testq %rbx, %rbx /* from kernel_thread? */ + jnz 1f /* kernel threads are uncommon */ 2: - movq %rsp, %rdi + leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */ call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ SWAPGS + FRAME_END jmp restore_regs_and_iret 1: diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 10820f6cefbf..572cee3fccff 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -186,7 +186,7 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr) if (IS_ERR(vma)) { ret = PTR_ERR(vma); - do_munmap(mm, text_start, image->size); + do_munmap(mm, text_start, image->size, NULL); } else { current->mm->context.vdso = (void __user *)text_start; current->mm->context.vdso_image = image; diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 1d392c39fe56..b8ccdb5c9244 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,11 +1,4 @@ -obj-y += core.o - -obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o -obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o -obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o -ifdef CONFIG_AMD_IOMMU -obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o -endif - -obj-$(CONFIG_CPU_SUP_INTEL) += msr.o +obj-y += core.o +obj-y += amd/ +obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile new file mode 100644 index 000000000000..b1da46f396e0 --- /dev/null +++ b/arch/x86/events/amd/Makefile @@ -0,0 +1,7 @@ +obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o +obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o +obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o +ifdef CONFIG_AMD_IOMMU +obj-$(CONFIG_CPU_SUP_AMD) += iommu.o +endif + diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 05612a2529c8..496e60391fac 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -1010,7 +1010,7 @@ static __init int amd_ibs_init(void) * all online cpus. */ cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING, - "perf/x86/amd/ibs:STARTING", + "perf/x86/amd/ibs:starting", x86_pmu_amd_ibs_starting_cpu, x86_pmu_amd_ibs_dying_cpu); diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index a0b1bdb3ad42..4d1f7f2d9aff 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -22,13 +22,17 @@ #define NUM_COUNTERS_NB 4 #define NUM_COUNTERS_L2 4 -#define MAX_COUNTERS NUM_COUNTERS_NB +#define NUM_COUNTERS_L3 6 +#define MAX_COUNTERS 6 #define RDPMC_BASE_NB 6 -#define RDPMC_BASE_L2 10 +#define RDPMC_BASE_LLC 10 #define COUNTER_SHIFT 16 +static int num_counters_llc; +static int num_counters_nb; + static HLIST_HEAD(uncore_unused_list); struct amd_uncore { @@ -45,30 +49,30 @@ struct amd_uncore { }; static struct amd_uncore * __percpu *amd_uncore_nb; -static struct amd_uncore * __percpu *amd_uncore_l2; +static struct amd_uncore * __percpu *amd_uncore_llc; static struct pmu amd_nb_pmu; -static struct pmu amd_l2_pmu; +static struct pmu amd_llc_pmu; static cpumask_t amd_nb_active_mask; -static cpumask_t amd_l2_active_mask; +static cpumask_t amd_llc_active_mask; static bool is_nb_event(struct perf_event *event) { return event->pmu->type == amd_nb_pmu.type; } -static bool is_l2_event(struct perf_event *event) +static bool is_llc_event(struct perf_event *event) { - return event->pmu->type == amd_l2_pmu.type; + return event->pmu->type == amd_llc_pmu.type; } static struct amd_uncore *event_to_amd_uncore(struct perf_event *event) { if (is_nb_event(event) && amd_uncore_nb) return *per_cpu_ptr(amd_uncore_nb, event->cpu); - else if (is_l2_event(event) && amd_uncore_l2) - return *per_cpu_ptr(amd_uncore_l2, event->cpu); + else if (is_llc_event(event) && amd_uncore_llc) + return *per_cpu_ptr(amd_uncore_llc, event->cpu); return NULL; } @@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event) return -ENOENT; /* - * NB and L2 counters (MSRs) are shared across all cores that share the - * same NB / L2 cache. Interrupts can be directed to a single target - * core, however, event counts generated by processes running on other - * cores cannot be masked out. So we do not support sampling and - * per-thread events. + * NB and Last level cache counters (MSRs) are shared across all cores + * that share the same NB / Last level cache. Interrupts can be directed + * to a single target core, however, event counts generated by processes + * running on other cores cannot be masked out. So we do not support + * sampling and per-thread events. */ if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) return -EINVAL; - /* NB and L2 counters do not have usr/os/guest/host bits */ + /* NB and Last level cache counters do not have usr/os/guest/host bits */ if (event->attr.exclude_user || event->attr.exclude_kernel || event->attr.exclude_host || event->attr.exclude_guest) return -EINVAL; @@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, if (pmu->type == amd_nb_pmu.type) active_mask = &amd_nb_active_mask; - else if (pmu->type == amd_l2_pmu.type) - active_mask = &amd_l2_active_mask; + else if (pmu->type == amd_llc_pmu.type) + active_mask = &amd_llc_active_mask; else return 0; @@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = { .attrs = amd_uncore_attrs, }; -PMU_FORMAT_ATTR(event, "config:0-7,32-35"); -PMU_FORMAT_ATTR(umask, "config:8-15"); - -static struct attribute *amd_uncore_format_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - NULL, -}; - -static struct attribute_group amd_uncore_format_group = { - .name = "format", - .attrs = amd_uncore_format_attr, +/* + * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based + * on family + */ +#define AMD_FORMAT_ATTR(_dev, _name, _format) \ +static ssize_t \ +_dev##_show##_name(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev); + +/* Used for each uncore counter type */ +#define AMD_ATTRIBUTE(_name) \ +static struct attribute *amd_uncore_format_attr_##_name[] = { \ + &format_attr_event_##_name.attr, \ + &format_attr_umask.attr, \ + NULL, \ +}; \ +static struct attribute_group amd_uncore_format_group_##_name = { \ + .name = "format", \ + .attrs = amd_uncore_format_attr_##_name, \ +}; \ +static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \ + &amd_uncore_attr_group, \ + &amd_uncore_format_group_##_name, \ + NULL, \ }; -static const struct attribute_group *amd_uncore_attr_groups[] = { - &amd_uncore_attr_group, - &amd_uncore_format_group, - NULL, -}; +AMD_FORMAT_ATTR(event, , "config:0-7,32-35"); +AMD_FORMAT_ATTR(umask, , "config:8-15"); +AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60"); +AMD_FORMAT_ATTR(event, _l3, "config:0-7"); +AMD_ATTRIBUTE(df); +AMD_ATTRIBUTE(l3); static struct pmu amd_nb_pmu = { .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_attr_groups, - .name = "amd_nb", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = { .read = amd_uncore_read, }; -static struct pmu amd_l2_pmu = { +static struct pmu amd_llc_pmu = { .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_attr_groups, - .name = "amd_l2", .event_init = amd_uncore_event_init, .add = amd_uncore_add, .del = amd_uncore_del, @@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) static int amd_uncore_cpu_up_prepare(unsigned int cpu) { - struct amd_uncore *uncore_nb = NULL, *uncore_l2; + struct amd_uncore *uncore_nb = NULL, *uncore_llc; if (amd_uncore_nb) { uncore_nb = amd_uncore_alloc(cpu); if (!uncore_nb) goto fail; uncore_nb->cpu = cpu; - uncore_nb->num_counters = NUM_COUNTERS_NB; + uncore_nb->num_counters = num_counters_nb; uncore_nb->rdpmc_base = RDPMC_BASE_NB; uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; uncore_nb->active_mask = &amd_nb_active_mask; @@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu) *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; } - if (amd_uncore_l2) { - uncore_l2 = amd_uncore_alloc(cpu); - if (!uncore_l2) + if (amd_uncore_llc) { + uncore_llc = amd_uncore_alloc(cpu); + if (!uncore_llc) goto fail; - uncore_l2->cpu = cpu; - uncore_l2->num_counters = NUM_COUNTERS_L2; - uncore_l2->rdpmc_base = RDPMC_BASE_L2; - uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL; - uncore_l2->active_mask = &amd_l2_active_mask; - uncore_l2->pmu = &amd_l2_pmu; - uncore_l2->id = -1; - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2; + uncore_llc->cpu = cpu; + uncore_llc->num_counters = num_counters_llc; + uncore_llc->rdpmc_base = RDPMC_BASE_LLC; + uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore_llc->active_mask = &amd_llc_active_mask; + uncore_llc->pmu = &amd_llc_pmu; + uncore_llc->id = -1; + *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc; } return 0; @@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu) *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; } - if (amd_uncore_l2) { + if (amd_uncore_llc) { unsigned int apicid = cpu_data(cpu).apicid; unsigned int nshared; - uncore = *per_cpu_ptr(amd_uncore_l2, cpu); + uncore = *per_cpu_ptr(amd_uncore_llc, cpu); cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); nshared = ((eax >> 14) & 0xfff) + 1; uncore->id = apicid - (apicid % nshared); - uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2); - *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); + *per_cpu_ptr(amd_uncore_llc, cpu) = uncore; } return 0; @@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu) if (amd_uncore_nb) uncore_online(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_online(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_online(cpu, amd_uncore_llc); return 0; } @@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu) if (amd_uncore_nb) uncore_down_prepare(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_down_prepare(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_down_prepare(cpu, amd_uncore_llc); return 0; } @@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu) if (amd_uncore_nb) uncore_dead(cpu, amd_uncore_nb); - if (amd_uncore_l2) - uncore_dead(cpu, amd_uncore_l2); + if (amd_uncore_llc) + uncore_dead(cpu, amd_uncore_llc); return 0; } @@ -492,6 +511,47 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; + switch(boot_cpu_data.x86) { + case 23: + /* Family 17h: */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L3; + /* + * For Family17h, the NorthBridge counters are + * re-purposed as Data Fabric counters. Also, support is + * added for L3 counters. The pmus are exported based on + * family as either L2 or L3 and NB or DF. + */ + amd_nb_pmu.name = "amd_df"; + amd_llc_pmu.name = "amd_l3"; + format_attr_event_df.show = &event_show_df; + format_attr_event_l3.show = &event_show_l3; + break; + case 22: + /* Family 16h - may change: */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + break; + default: + /* + * All prior families have the same number of + * NorthBridge and Last Level Cache counters + */ + num_counters_nb = NUM_COUNTERS_NB; + num_counters_llc = NUM_COUNTERS_L2; + amd_nb_pmu.name = "amd_nb"; + amd_llc_pmu.name = "amd_l2"; + format_attr_event_df = format_attr_event; + format_attr_event_l3 = format_attr_event; + break; + } + amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df; + amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3; + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; @@ -510,16 +570,16 @@ static int __init amd_uncore_init(void) } if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { - amd_uncore_l2 = alloc_percpu(struct amd_uncore *); - if (!amd_uncore_l2) { + amd_uncore_llc = alloc_percpu(struct amd_uncore *); + if (!amd_uncore_llc) { ret = -ENOMEM; - goto fail_l2; + goto fail_llc; } - ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1); if (ret) - goto fail_l2; + goto fail_llc; - pr_info("perf: AMD L2I counters detected\n"); + pr_info("perf: AMD LLC counters detected\n"); ret = 0; } @@ -529,7 +589,7 @@ static int __init amd_uncore_init(void) if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP, "perf/x86/amd/uncore:prepare", amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead)) - goto fail_l2; + goto fail_llc; if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, "perf/x86/amd/uncore:starting", @@ -546,11 +606,11 @@ fail_start: cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING); fail_prep: cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP); -fail_l2: +fail_llc: if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); - if (amd_uncore_l2) - free_percpu(amd_uncore_l2); + if (amd_uncore_llc) + free_percpu(amd_uncore_llc); fail_nb: if (amd_uncore_nb) free_percpu(amd_uncore_nb); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 019c5887b698..1635c0c8df23 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -505,6 +505,10 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; + + /* There's no sense in having PEBS for non sampling events: */ + if (!is_sampling_event(event)) + return -EINVAL; } /* * check that PEBS LBR correction does not conflict with diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 86138267b68a..eb1484c86bb4 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3176,13 +3176,16 @@ static void intel_pmu_cpu_starting(int cpu) if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { for_each_cpu(i, topology_sibling_cpumask(cpu)) { + struct cpu_hw_events *sibling; struct intel_excl_cntrs *c; - c = per_cpu(cpu_hw_events, i).excl_cntrs; + sibling = &per_cpu(cpu_hw_events, i); + c = sibling->excl_cntrs; if (c && c->core_id == core_id) { cpuc->kfree_on_online[1] = cpuc->excl_cntrs; cpuc->excl_cntrs = c; - cpuc->excl_thread_id = 1; + if (!sibling->excl_thread_id) + cpuc->excl_thread_id = 1; break; } } @@ -3987,7 +3990,7 @@ __init int intel_pmu_init(void) x86_pmu.num_counters, INTEL_PMC_MAX_GENERIC); x86_pmu.num_counters = INTEL_PMC_MAX_GENERIC; } - x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; + x86_pmu.intel_ctrl = (1ULL << x86_pmu.num_counters) - 1; if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED) { WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index fec8a461bdef..aff4b5b69d40 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -434,6 +434,7 @@ static struct pmu cstate_core_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static struct pmu cstate_pkg_pmu = { @@ -447,6 +448,7 @@ static struct pmu cstate_pkg_pmu = { .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, }; static const struct cstate_model nhm_cstates __initconst = { @@ -539,6 +541,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates), { }, diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index be202390bbd3..9dfeeeca0ea8 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1389,9 +1389,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) continue; /* log dropped samples number */ - if (error[bit]) + if (error[bit]) { perf_log_lost_samples(event, error[bit]); + if (perf_event_account_interrupt(event)) + x86_pmu_stop(event, 0); + } + if (counts[bit]) { __intel_pmu_pebs_event(event, iregs, base, top, bit, counts[bit]); diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 1c1b9fe705c8..5900471ee508 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = { }; PMU_FORMAT_ATTR(cyc, "config:1" ); +PMU_FORMAT_ATTR(pwr_evt, "config:4" ); +PMU_FORMAT_ATTR(fup_on_ptw, "config:5" ); PMU_FORMAT_ATTR(mtc, "config:9" ); PMU_FORMAT_ATTR(tsc, "config:10" ); PMU_FORMAT_ATTR(noretcomp, "config:11" ); +PMU_FORMAT_ATTR(ptw, "config:12" ); PMU_FORMAT_ATTR(mtc_period, "config:14-17" ); PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" ); PMU_FORMAT_ATTR(psb_period, "config:24-27" ); static struct attribute *pt_formats_attr[] = { &format_attr_cyc.attr, + &format_attr_pwr_evt.attr, + &format_attr_fup_on_ptw.attr, &format_attr_mtc.attr, &format_attr_tsc.attr, &format_attr_noretcomp.attr, + &format_attr_ptw.attr, &format_attr_mtc_period.attr, &format_attr_cyc_thresh.attr, &format_attr_psb_period.attr, diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index bd34124449b0..22054ca49026 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -161,7 +161,13 @@ static u64 rapl_timer_ms; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - return rapl_pmus->pmus[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) @@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event) /* must be done before validate_group */ pmu = cpu_to_rapl_pmu(event->cpu); + if (!pmu) + return -EINVAL; event->cpu = pmu->cpu; event->pmu_private = pmu; event->hw.event_base = msr; @@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu) struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; + if (!pmu) { + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -ENOMEM; + + raw_spin_lock_init(&pmu->lock); + INIT_LIST_HEAD(&pmu->active_list); + pmu->pmu = &rapl_pmus->pmu; + pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + rapl_hrtimer_init(pmu); + + rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; + } + /* * Check if there is an online cpu in the package which collects rapl * events already. @@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu) return 0; } -static int rapl_cpu_prepare(unsigned int cpu) -{ - struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); - - if (pmu) - return 0; - - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); - if (!pmu) - return -ENOMEM; - - raw_spin_lock_init(&pmu->lock); - INIT_LIST_HEAD(&pmu->active_list); - pmu->pmu = &rapl_pmus->pmu; - pmu->timer_interval = ms_to_ktime(rapl_timer_ms); - pmu->cpu = -1; - rapl_hrtimer_init(pmu); - rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; - return 0; -} - static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -697,6 +698,7 @@ static int __init init_rapl_pmus(void) rapl_pmus->pmu.start = rapl_pmu_event_start; rapl_pmus->pmu.stop = rapl_pmu_event_stop; rapl_pmus->pmu.read = rapl_pmu_event_read; + rapl_pmus->pmu.module = THIS_MODULE; return 0; } @@ -769,6 +771,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init), X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, hsx_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init), {}, }; @@ -802,29 +807,21 @@ static int __init rapl_pmu_init(void) /* * Install callbacks. Core will call them for each online cpu. */ - - ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare", - rapl_cpu_prepare, NULL); - if (ret) - goto out; - ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) - goto out1; + goto out; ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); if (ret) - goto out2; + goto out1; rapl_advertise(); return 0; -out2: - cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out1: - cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(); @@ -835,7 +832,6 @@ module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP); perf_pmu_unregister(&rapl_pmus->pmu); cleanup_rapl_pmus(); } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 97c246f84dea..758c1aa5009d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj, struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - return pmu->boxes[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < max_packages ? pmu->boxes[pkgid] : NULL; } u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) @@ -733,6 +739,7 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) .start = uncore_pmu_event_start, .stop = uncore_pmu_event_stop, .read = uncore_pmu_event_read, + .module = THIS_MODULE, }; } else { pmu->pmu = *pmu->type->pmu; @@ -763,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) -{ - struct intel_uncore_pmu *pmu = type->pmus; - struct intel_uncore_box *box; - int i, pkg; - - if (pmu) { - pkg = topology_physical_package_id(cpu); - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box) - uncore_box_exit(box); - } - } -} - -static void uncore_exit_boxes(void *dummy) -{ - struct intel_uncore_type **types; - - for (types = uncore_msr_uncores; *types; types++) - __uncore_exit_boxes(*types++, smp_processor_id()); -} - static void uncore_free_boxes(struct intel_uncore_pmu *pmu) { int pkg; @@ -1057,86 +1040,6 @@ static void uncore_pci_exit(void) } } -static int uncore_cpu_dying(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box && atomic_dec_return(&box->refcnt) == 0) - uncore_box_exit(box); - } - } - return 0; -} - -static int first_init; - -static int uncore_cpu_starting(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg, ncpus = 1; - - if (first_init) { - /* - * On init we get the number of online cpus in the package - * and set refcount for all of them. - */ - ncpus = cpumask_weight(topology_core_cpumask(cpu)); - } - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (!box) - continue; - /* The first cpu on a package activates the box */ - if (atomic_add_return(ncpus, &box->refcnt) == ncpus) - uncore_box_init(box); - } - } - - return 0; -} - -static int uncore_cpu_prepare(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - if (pmu->boxes[pkg]) - continue; - /* First cpu of a package allocates the box */ - box = uncore_alloc_box(type, cpu_to_node(cpu)); - if (!box) - return -ENOMEM; - box->pmu = pmu; - box->pkgid = pkg; - pmu->boxes[pkg] = box; - } - } - return 0; -} - static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu, int new_cpu) { @@ -1176,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores, static int uncore_event_cpu_offline(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, pkg, target; /* Check if exiting cpu is used for collecting uncore events */ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) - return 0; - + goto unref; /* Find a new cpu to collect uncore events */ target = cpumask_any_but(topology_core_cpumask(cpu), cpu); @@ -1193,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu) uncore_change_context(uncore_msr_uncores, cpu, target); uncore_change_context(uncore_pci_uncores, cpu, target); + +unref: + /* Clear the references */ + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); + } + } return 0; } +static int allocate_boxes(struct intel_uncore_type **types, + unsigned int pkg, unsigned int cpu) +{ + struct intel_uncore_box *box, *tmp; + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + LIST_HEAD(allocated); + int i; + + /* Try to allocate all required boxes */ + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[pkg]) + continue; + box = uncore_alloc_box(type, cpu_to_node(cpu)); + if (!box) + goto cleanup; + box->pmu = pmu; + box->pkgid = pkg; + list_add(&box->active_list, &allocated); + } + } + /* Install them in the pmus */ + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + box->pmu->boxes[pkg] = box; + } + return 0; + +cleanup: + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + kfree(box); + } + return -ENOMEM; +} + static int uncore_event_cpu_online(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, ret, pkg, target; + + pkg = topology_logical_package_id(cpu); + ret = allocate_boxes(types, pkg, cpu); + if (ret) + return ret; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box && atomic_inc_return(&box->refcnt) == 1) + uncore_box_init(box); + } + } /* * Check if there is an online cpu in the package @@ -1353,6 +1328,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init), X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init), + X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init), {}, }; @@ -1388,38 +1365,16 @@ static int __init intel_uncore_init(void) if (cret && pret) return -ENODEV; - /* - * Install callbacks. Core will call them for each online cpu. - * - * The first online cpu of each package allocates and takes - * the refcounts for all other online cpus in that package. - * If msrs are not enabled no allocation is required and - * uncore_cpu_prepare() is not called for each online cpu. - */ - if (!cret) { - ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - if (ret) - goto err; - } else { - cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - } - first_init = 1; - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING, - "perf/x86/uncore:starting", - uncore_cpu_starting, uncore_cpu_dying); - first_init = 0; - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, - "perf/x86/uncore:online", - uncore_event_cpu_online, uncore_event_cpu_offline); + /* Install hotplug callbacks to setup the targets for each package */ + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, + "perf/x86/intel/uncore:online", + uncore_event_cpu_online, + uncore_event_cpu_offline); + if (ret) + goto err; return 0; err: - /* Undo box->init_box() */ - on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); return ret; @@ -1428,9 +1383,7 @@ module_init(intel_uncore_init); static void __exit intel_uncore_exit(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index e6832be714bc..dae2fedc1601 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2686,7 +2686,7 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { void hswep_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(0); + int pkg = boot_cpu_data.logical_proc_id; if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile new file mode 100644 index 000000000000..171ae09864d7 --- /dev/null +++ b/arch/x86/hyperv/Makefile @@ -0,0 +1 @@ +obj-y := hv_init.o diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c new file mode 100644 index 000000000000..db64baf0e500 --- /dev/null +++ b/arch/x86/hyperv/hv_init.c @@ -0,0 +1,277 @@ +/* + * X86 specific Hyper-V initialization code. + * + * Copyright (C) 2016, Microsoft, Inc. + * + * Author : K. Y. Srinivasan <kys@microsoft.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + */ + +#include <linux/types.h> +#include <asm/hypervisor.h> +#include <asm/hyperv.h> +#include <asm/mshyperv.h> +#include <linux/version.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <linux/clockchips.h> + + +#ifdef CONFIG_X86_64 + +static struct ms_hyperv_tsc_page *tsc_pg; + +static u64 read_hv_clock_tsc(struct clocksource *arg) +{ + u64 current_tick; + + if (tsc_pg->tsc_sequence != 0) { + /* + * Use the tsc page to compute the value. + */ + + while (1) { + u64 tmp; + u32 sequence = tsc_pg->tsc_sequence; + u64 cur_tsc; + u64 scale = tsc_pg->tsc_scale; + s64 offset = tsc_pg->tsc_offset; + + rdtscll(cur_tsc); + /* current_tick = ((cur_tsc *scale) >> 64) + offset */ + asm("mulq %3" + : "=d" (current_tick), "=a" (tmp) + : "a" (cur_tsc), "r" (scale)); + + current_tick += offset; + if (tsc_pg->tsc_sequence == sequence) + return current_tick; + + if (tsc_pg->tsc_sequence != 0) + continue; + /* + * Fallback using MSR method. + */ + break; + } + } + rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); + return current_tick; +} + +static struct clocksource hyperv_cs_tsc = { + .name = "hyperv_clocksource_tsc_page", + .rating = 400, + .read = read_hv_clock_tsc, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; +#endif + +static u64 read_hv_clock_msr(struct clocksource *arg) +{ + u64 current_tick; + /* + * Read the partition counter to get the current tick count. This count + * is set to 0 when the partition is created and is incremented in + * 100 nanosecond units. + */ + rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); + return current_tick; +} + +static struct clocksource hyperv_cs_msr = { + .name = "hyperv_clocksource_msr", + .rating = 400, + .read = read_hv_clock_msr, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static void *hypercall_pg; +struct clocksource *hyperv_cs; +EXPORT_SYMBOL_GPL(hyperv_cs); + +/* + * This function is to be invoked early in the boot sequence after the + * hypervisor has been detected. + * + * 1. Setup the hypercall page. + * 2. Register Hyper-V specific clocksource. + */ +void hyperv_init(void) +{ + u64 guest_id; + union hv_x64_msr_hypercall_contents hypercall_msr; + + if (x86_hyper != &x86_hyper_ms_hyperv) + return; + + /* + * Setup the hypercall page and enable hypercalls. + * 1. Register the guest ID + * 2. Enable the hypercall and register the hypercall page + */ + guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); + wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); + + hypercall_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX); + if (hypercall_pg == NULL) { + wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); + return; + } + + rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hypercall_msr.enable = 1; + hypercall_msr.guest_physical_address = vmalloc_to_pfn(hypercall_pg); + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + /* + * Register Hyper-V specific clocksource. + */ +#ifdef CONFIG_X86_64 + if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) { + union hv_x64_msr_hypercall_contents tsc_msr; + + tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); + if (!tsc_pg) + goto register_msr_cs; + + hyperv_cs = &hyperv_cs_tsc; + + rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); + + tsc_msr.enable = 1; + tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg); + + wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); + clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); + return; + } +#endif + /* + * For 32 bit guests just use the MSR based mechanism for reading + * the partition counter. + */ + +register_msr_cs: + hyperv_cs = &hyperv_cs_msr; + if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) + clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); +} + +/* + * This routine is called before kexec/kdump, it does the required cleanup. + */ +void hyperv_cleanup(void) +{ + union hv_x64_msr_hypercall_contents hypercall_msr; + + /* Reset our OS id */ + wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); + + /* Reset the hypercall page */ + hypercall_msr.as_uint64 = 0; + wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + /* Reset the TSC page */ + hypercall_msr.as_uint64 = 0; + wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); +} +EXPORT_SYMBOL_GPL(hyperv_cleanup); + +/* + * hv_do_hypercall- Invoke the specified hypercall + */ +u64 hv_do_hypercall(u64 control, void *input, void *output) +{ + u64 input_address = (input) ? virt_to_phys(input) : 0; + u64 output_address = (output) ? virt_to_phys(output) : 0; +#ifdef CONFIG_X86_64 + u64 hv_status = 0; + + if (!hypercall_pg) + return (u64)ULLONG_MAX; + + __asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8"); + __asm__ __volatile__("call *%3" : "=a" (hv_status) : + "c" (control), "d" (input_address), + "m" (hypercall_pg)); + + return hv_status; + +#else + + u32 control_hi = control >> 32; + u32 control_lo = control & 0xFFFFFFFF; + u32 hv_status_hi = 1; + u32 hv_status_lo = 1; + u32 input_address_hi = input_address >> 32; + u32 input_address_lo = input_address & 0xFFFFFFFF; + u32 output_address_hi = output_address >> 32; + u32 output_address_lo = output_address & 0xFFFFFFFF; + + if (!hypercall_pg) + return (u64)ULLONG_MAX; + + __asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi), + "=a"(hv_status_lo) : "d" (control_hi), + "a" (control_lo), "b" (input_address_hi), + "c" (input_address_lo), "D"(output_address_hi), + "S"(output_address_lo), "m" (hypercall_pg)); + + return hv_status_lo | ((u64)hv_status_hi << 32); +#endif /* !x86_64 */ +} +EXPORT_SYMBOL_GPL(hv_do_hypercall); + +void hyperv_report_panic(struct pt_regs *regs) +{ + static bool panic_reported; + + /* + * We prefer to report panic on 'die' chain as we have proper + * registers to report, but if we miss it (e.g. on BUG()) we need + * to report it on 'panic'. + */ + if (panic_reported) + return; + panic_reported = true; + + wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip); + wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax); + wrmsrl(HV_X64_MSR_CRASH_P2, regs->bx); + wrmsrl(HV_X64_MSR_CRASH_P3, regs->cx); + wrmsrl(HV_X64_MSR_CRASH_P4, regs->dx); + + /* + * Let Hyper-V know there is crash data available + */ + wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY); +} +EXPORT_SYMBOL_GPL(hyperv_report_panic); + +bool hv_is_hypercall_page_setup(void) +{ + union hv_x64_msr_hypercall_contents hypercall_msr; + + /* Check if the hypercall page is setup */ + hypercall_msr.as_uint64 = 0; + rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + + if (!hypercall_msr.enable) + return false; + + return true; +} +EXPORT_SYMBOL_GPL(hv_is_hypercall_page_setup); diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 2b892e2313a9..5d6a53fd7521 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += clkdev.h -generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 0c5fbc68e82d..eff8e36aaf72 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -195,7 +195,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v) static inline void native_apic_msr_eoi_write(u32 reg, u32 v) { - wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); + __wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0); } static inline u32 native_apic_msr_read(u32 reg) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index eafee3161d1c..4e7772387c6e 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -100,7 +100,7 @@ #define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ #define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ @@ -186,7 +186,7 @@ * * Reuse free bits when adding new feature flags! */ - +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ @@ -288,6 +288,7 @@ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ @@ -320,5 +321,4 @@ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ - #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 12080d87da3b..cb8f9149f6c8 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -177,16 +177,8 @@ static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) struct desc_struct *d = get_cpu_gdt_table(cpu); tss_desc tss; - /* - * sizeof(unsigned long) coming from an extra "long" at the end - * of the iobitmap. See tss_struct definition in processor.h - * - * -1? seg base+limit should be pointing to the address of the - * last valid byte - */ set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, - IO_BITMAP_OFFSET + IO_BITMAP_BYTES + - sizeof(unsigned long) - 1); + __KERNEL_TSS_LIMIT); write_gdt_entry(d, entry, &tss, DESC_TSS); } @@ -213,6 +205,54 @@ static inline void native_load_tr_desc(void) asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); } +static inline void force_reload_TR(void) +{ + struct desc_struct *d = get_cpu_gdt_table(smp_processor_id()); + tss_desc tss; + + memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); + + /* + * LTR requires an available TSS, and the TSS is currently + * busy. Make it be available so that LTR will work. + */ + tss.type = DESC_TSS; + write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); + + load_TR_desc(); +} + +DECLARE_PER_CPU(bool, need_tr_refresh); + +static inline void refresh_TR(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(this_cpu_read(need_tr_refresh))) { + force_reload_TR(); + this_cpu_write(need_tr_refresh, false); + } +} + +/* + * If you do something evil that corrupts the cached TSS limit (I'm looking + * at you, VMX exits), call this function. + * + * The optimization here is that the TSS limit only matters for Linux if the + * IO bitmap is in use. If the TSS limit gets forced to its minimum value, + * everything works except that IO bitmap will be ignored and all CPL 3 IO + * instructions will #GP, which is exactly what we want for normal tasks. + */ +static inline void invalidate_tss_limit(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) + force_reload_TR(); + else + this_cpu_write(need_tr_refresh, true); +} + static inline void native_load_gdt(const struct desc_ptr *dtr) { asm volatile("lgdt %0"::"m" (*dtr)); diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index ced283ac79df..af95c47d5c9e 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -59,6 +59,17 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) } #define div_u64_rem div_u64_rem +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + u32 high, low; + + asm ("mull %[b]" : "=a" (low), "=d" (high) + : [a] "a" (a), [b] "rm" (b) ); + + return low | ((u64)high) << 32; +} +#define mul_u32_u32 mul_u32_u32 + #else # include <asm-generic/div64.h> #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index ec23d8e1297c..67313f3a9874 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -30,8 +30,6 @@ extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype); extern void update_e820(void); extern void e820_setup_gap(void); -extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr); struct setup_data; extern void parse_e820_ext(u64 phys_addr, u32 data_len); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index e99675b9c861..2f77bcefe6b4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -191,6 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map( struct efi_config { u64 image_handle; u64 table; + u64 runtime_services; u64 boot_services; u64 text_output; efi_status_t (*call)(unsigned long, ...); @@ -226,6 +227,10 @@ static inline bool efi_is_64bit(void) #define __efi_call_early(f, ...) \ __efi_early()->call((unsigned long)f, __VA_ARGS__); +#define efi_call_runtime(f, ...) \ + __efi_early()->call(efi_table_attr(efi_runtime_services, f, \ + __efi_early()->runtime_services), __VA_ARGS__) + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index e7f155c3045e..9d49c18b5ea9 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -258,6 +258,15 @@ extern int force_personality32; #define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) +extern u32 elf_hwcap2; + +/* + * HWCAP2 supplies mask with kernel enabled CPU features, so that + * the application can discover that it can safely use them. + * The bits are defined in uapi/asm/hwcap2.h. + */ +#define ELF_HWCAP2 (elf_hwcap2) + /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in intent than poking at uname or /proc/cpuinfo. diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index d4a684997497..255645f60ca2 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -87,6 +87,16 @@ extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif + +static inline void fpstate_init_xstate(struct xregs_state *xsave) +{ + /* + * XRSTORS requires these bits set in xcomp_bv, or it will + * trigger #GP: + */ + xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask; +} + static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 34a46dc076d3..8167fdb67ae8 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -57,7 +57,7 @@ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ #define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 49da9f497b90..fe04491130ae 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -27,7 +27,6 @@ extern void intel_mid_pwr_power_off(void); extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev); extern int get_gpio_by_name(const char *name); -extern void intel_scu_device_register(struct platform_device *pdev); extern int __init sfi_parse_mrtc(struct sfi_table_header *table); extern int __init sfi_parse_mtmr(struct sfi_table_header *table); extern int sfi_mrtc_num; @@ -42,10 +41,8 @@ struct devs_id { char name[SFI_NAME_LEN + 1]; u8 type; u8 delay; + u8 msic; void *(*get_platform_data)(void *info); - /* Custom handler for devices */ - void (*device_handler)(struct sfi_device_table_entry *pentry, - struct devs_id *dev); }; #define sfi_device(i) \ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index d34bd370074b..7afb0e2f07f4 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -164,6 +164,17 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) #define virt_to_bus virt_to_phys #define bus_to_virt phys_to_virt +/* + * The default ioremap() behavior is non-cached; if you need something + * else, you probably want one of the following. + */ +extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); +#define ioremap_uc ioremap_uc + +extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); + /** * ioremap - map bus memory into CPU space * @offset: bus address of the memory @@ -178,17 +189,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) * If the area you are trying to map is a PCI BAR you should have a * look at pci_iomap(). */ -extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); -extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); -#define ioremap_uc ioremap_uc - -extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); -extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, - unsigned long prot_val); - -/* - * The default ioremap() behavior is non-cached: - */ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) { return ioremap_nocache(offset, size); @@ -207,18 +207,42 @@ extern void set_iounmap_nonlazy(void); */ #define xlate_dev_kmem_ptr(p) p +/** + * memset_io Set a range of I/O memory to a constant value + * @addr: The beginning of the I/O-memory range to set + * @val: The value to set the memory to + * @count: The number of bytes to set + * + * Set a range of I/O memory to a given value. + */ static inline void memset_io(volatile void __iomem *addr, unsigned char val, size_t count) { memset((void __force *)addr, val, count); } +/** + * memcpy_fromio Copy a block of data from I/O memory + * @dst: The (RAM) destination for the copy + * @src: The (I/O memory) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data from I/O memory. + */ static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count) { memcpy(dst, (const void __force *)src, count); } +/** + * memcpy_toio Copy a block of data into I/O memory + * @dst: The (I/O memory) destination for the copy + * @src: The (RAM) source for the data + * @count: The number of bytes to copy + * + * Copy a block of data to I/O memory. + */ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, size_t count) { diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index e9cd7befcb76..3e8c287090e4 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -441,5 +441,6 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq); void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt); void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt); +bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt); #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a7066dc1a7e9..74ef58c8ff53 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -55,7 +55,6 @@ #define KVM_REQ_TRIPLE_FAULT 10 #define KVM_REQ_MMU_SYNC 11 #define KVM_REQ_CLOCK_UPDATE 12 -#define KVM_REQ_DEACTIVATE_FPU 13 #define KVM_REQ_EVENT 14 #define KVM_REQ_APF_HALT 15 #define KVM_REQ_STEAL_UPDATE 16 @@ -115,7 +114,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 -#define KVM_MMU_HASH_SHIFT 10 +#define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 @@ -208,6 +207,13 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting + * with the SVE bit in EPT PTEs. + */ +#define SPTE_SPECIAL_MASK (1ULL << 62) + /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -668,6 +674,9 @@ struct kvm_vcpu_arch { int pending_ioapic_eoi; int pending_external_vector; + + /* GPA available (AMD only) */ + bool gpa_available; }; struct kvm_lpage_info { @@ -716,6 +725,12 @@ struct kvm_hv { HV_REFERENCE_TSC_PAGE tsc_ref; }; +enum kvm_irqchip_mode { + KVM_IRQCHIP_NONE, + KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ + KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -788,7 +803,7 @@ struct kvm_arch { u64 disabled_quirks; - bool irqchip_split; + enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; bool disabled_lapic_found; @@ -815,6 +830,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong max_mmu_page_hash_collisions; }; struct kvm_vcpu_stat { @@ -844,6 +860,7 @@ struct kvm_vcpu_stat { u64 hypercalls; u64 irq_injections; u64 nmi_injections; + u64 req_event; }; struct x86_instruction_info; @@ -918,8 +935,6 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); u32 (*get_pkru)(struct kvm_vcpu *vcpu); - void (*fpu_activate)(struct kvm_vcpu *vcpu); - void (*fpu_deactivate)(struct kvm_vcpu *vcpu); void (*tlb_flush)(struct kvm_vcpu *vcpu); @@ -951,7 +966,7 @@ struct kvm_x86_ops { void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); - void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); + int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*get_tdp_level)(void); u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); @@ -1050,7 +1065,8 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask); + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, + u64 acc_track_mask); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h new file mode 100644 index 000000000000..f260bef63591 --- /dev/null +++ b/arch/x86/include/asm/kvmclock.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_KVM_CLOCK_H +#define _ASM_X86_KVM_CLOCK_H + +extern struct clocksource kvm_clock; + +#endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 5132f2a6c0a2..e63873683d4a 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -97,10 +97,6 @@ #define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ -/* Software defined banks */ -#define MCE_EXTENDED_BANK 128 -#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0) - #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" @@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; extern struct mca_msr_regs msr_ops; + +enum mce_notifier_prios { + MCE_PRIO_SRAO = INT_MAX, + MCE_PRIO_EXTLOG = INT_MAX - 1, + MCE_PRIO_NFIT = INT_MAX - 2, + MCE_PRIO_EDAC = INT_MAX - 3, + MCE_PRIO_LOWEST = 0, +}; + extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void); void intel_init_thermal(struct cpuinfo_x86 *c); -void mce_log_therm_throt_event(__u64 status); - /* Interrupt Handler for core thermal thresholds */ extern int (*platform_thermal_notify)(__u64 msr_val); @@ -362,12 +365,13 @@ struct smca_hwid { unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ u32 hwid_mcatype; /* (hwid,mcatype) tuple */ u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */ + u8 count; /* Number of instances. */ }; struct smca_bank { struct smca_hwid *hwid; - /* Instance ID */ - u32 id; + u32 id; /* Value of MCA_IPID[InstanceId]. */ + u8 sysfs_id; /* Value used for sysfs name. */ }; extern struct smca_bank smca_banks[MAX_NR_BANKS]; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 38711df3bcb5..daadeeea00b1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -7,18 +7,17 @@ #define native_rdmsr(msr, val1, val2) \ do { \ - u64 __val = native_read_msr((msr)); \ + u64 __val = __rdmsr((msr)); \ (void)((val1) = (u32)__val); \ (void)((val2) = (u32)(__val >> 32)); \ } while (0) #define native_wrmsr(msr, low, high) \ - native_write_msr(msr, low, high) + __wrmsr(msr, low, high) #define native_wrmsrl(msr, val) \ - native_write_msr((msr), \ - (u32)((u64)(val)), \ - (u32)((u64)(val) >> 32)) + __wrmsr((msr), (u32)((u64)(val)), \ + (u32)((u64)(val) >> 32)) struct ucode_patch { struct list_head plist; @@ -140,6 +139,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); +extern bool initrd_gone; #else static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 3e3e20be829a..3d57009e168b 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -54,6 +54,4 @@ static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } void reload_ucode_amd(void) {} #endif - -extern bool check_current_patch_level(u32 *rev, bool early); #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 195becc6f780..e793fc9a9b20 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -52,6 +52,21 @@ struct extended_sigtable { #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) +static inline u32 intel_get_microcode_revision(void) +{ + u32 rev, dummy; + + native_wrmsrl(MSR_IA32_UCODE_REV, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + native_cpuid_eax(1); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev); + + return rev; +} + #ifdef CONFIG_MICROCODE_INTEL extern void __init load_ucode_intel_bsp(void); extern void load_ucode_intel_ap(void); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index aaf59b7da98a..7c9c895432a9 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -3,8 +3,28 @@ #include <linux/types.h> #include <linux/interrupt.h> +#include <linux/clocksource.h> #include <asm/hyperv.h> +/* + * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent + * is set by CPUID(HVCPUID_VERSION_FEATURES). + */ +enum hv_cpuid_function { + HVCPUID_VERSION_FEATURES = 0x00000001, + HVCPUID_VENDOR_MAXFUNCTION = 0x40000000, + HVCPUID_INTERFACE = 0x40000001, + + /* + * The remaining functions depend on the value of + * HVCPUID_INTERFACE + */ + HVCPUID_VERSION = 0x40000002, + HVCPUID_FEATURES = 0x40000003, + HVCPUID_ENLIGHTENMENT_INFO = 0x40000004, + HVCPUID_IMPLEMENTATION_LIMITS = 0x40000005, +}; + struct ms_hyperv_info { u32 features; u32 misc_features; @@ -13,6 +33,128 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; +/* + * Declare the MSR used to setup pages used to communicate with the hypervisor. + */ +union hv_x64_msr_hypercall_contents { + u64 as_uint64; + struct { + u64 enable:1; + u64 reserved:11; + u64 guest_physical_address:52; + }; +}; + +/* + * TSC page layout. + */ + +struct ms_hyperv_tsc_page { + volatile u32 tsc_sequence; + u32 reserved1; + volatile u64 tsc_scale; + volatile s64 tsc_offset; + u64 reserved2[509]; +}; + +/* + * The guest OS needs to register the guest ID with the hypervisor. + * The guest ID is a 64 bit entity and the structure of this ID is + * specified in the Hyper-V specification: + * + * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx + * + * While the current guideline does not specify how Linux guest ID(s) + * need to be generated, our plan is to publish the guidelines for + * Linux and other guest operating systems that currently are hosted + * on Hyper-V. The implementation here conforms to this yet + * unpublished guidelines. + * + * + * Bit(s) + * 63 - Indicates if the OS is Open Source or not; 1 is Open Source + * 62:56 - Os Type; Linux is 0x100 + * 55:48 - Distro specific identification + * 47:16 - Linux kernel version number + * 15:0 - Distro specific identification + * + * + */ + +#define HV_LINUX_VENDOR_ID 0x8100 + +/* + * Generate the guest ID based on the guideline described above. + */ + +static inline __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version, + __u64 d_info2) +{ + __u64 guest_id = 0; + + guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48); + guest_id |= (d_info1 << 48); + guest_id |= (kernel_version << 16); + guest_id |= d_info2; + + return guest_id; +} + + +/* Free the message slot and signal end-of-message if required */ +static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) +{ + /* + * On crash we're reading some other CPU's message page and we need + * to be careful: this other CPU may already had cleared the header + * and the host may already had delivered some other message there. + * In case we blindly write msg->header.message_type we're going + * to lose it. We can still lose a message of the same type but + * we count on the fact that there can only be one + * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages + * on crash. + */ + if (cmpxchg(&msg->header.message_type, old_msg_type, + HVMSG_NONE) != old_msg_type) + return; + + /* + * Make sure the write to MessageType (ie set to + * HVMSG_NONE) happens before we read the + * MessagePending and EOMing. Otherwise, the EOMing + * will not deliver any more messages since there is + * no empty slot + */ + mb(); + + if (msg->header.message_flags.msg_pending) { + /* + * This will cause message queue rescan to + * possibly deliver another msg from the + * hypervisor + */ + wrmsrl(HV_X64_MSR_EOM, 0); + } +} + +#define hv_get_current_tick(tick) rdmsrl(HV_X64_MSR_TIME_REF_COUNT, tick) +#define hv_init_timer(timer, tick) wrmsrl(timer, tick) +#define hv_init_timer_config(config, val) wrmsrl(config, val) + +#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val) +#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val) + +#define hv_get_siefp(val) rdmsrl(HV_X64_MSR_SIEFP, val) +#define hv_set_siefp(val) wrmsrl(HV_X64_MSR_SIEFP, val) + +#define hv_get_synic_state(val) rdmsrl(HV_X64_MSR_SCONTROL, val) +#define hv_set_synic_state(val) wrmsrl(HV_X64_MSR_SCONTROL, val) + +#define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index) + +#define hv_get_synint_state(int_num, val) rdmsrl(int_num, val) +#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val) + void hyperv_callback_vector(void); #ifdef CONFIG_TRACING #define trace_hyperv_callback_vector hyperv_callback_vector @@ -25,4 +167,13 @@ void hv_setup_kexec_handler(void (*handler)(void)); void hv_remove_kexec_handler(void); void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); void hv_remove_crash_handler(void); + +#if IS_ENABLED(CONFIG_HYPERV) +extern struct clocksource *hyperv_cs; + +void hyperv_init(void); +void hyperv_report_panic(struct pt_regs *regs); +bool hv_is_hypercall_page_setup(void); +void hyperv_cleanup(void); +#endif #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 710273c617b8..00293a94ffaf 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -543,6 +543,11 @@ #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) +/* MISC_FEATURE_ENABLES non-architectural features */ +#define MSR_MISC_FEATURE_ENABLES 0x00000140 + +#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1 + #define MSR_IA32_TSC_DEADLINE 0x000006E0 /* P4/Xeon+ specific */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index db0b90c3b03e..898dba2e2e2c 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -80,7 +80,14 @@ static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {} static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} #endif -static inline unsigned long long native_read_msr(unsigned int msr) +/* + * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR + * accessors and should not have any tracing or other functionality piggybacking + * on them - those are *purely* for accessing MSRs and nothing more. So don't even + * think of extending them - you will be slapped with a stinking trout or a frozen + * shark will reach you, wherever you are! You've been warned. + */ +static inline unsigned long long notrace __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -88,11 +95,30 @@ static inline unsigned long long native_read_msr(unsigned int msr) "2:\n" _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe) : EAX_EDX_RET(val, low, high) : "c" (msr)); - if (msr_tracepoint_active(__tracepoint_read_msr)) - do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); + return EAX_EDX_VAL(val, low, high); } +static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +{ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) + : : "c" (msr), "a"(low), "d" (high) : "memory"); +} + +static inline unsigned long long native_read_msr(unsigned int msr) +{ + unsigned long long val; + + val = __rdmsr(msr); + + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, val, 0); + + return val; +} + static inline unsigned long long native_read_msr_safe(unsigned int msr, int *err) { @@ -116,29 +142,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, /* Can be uninlined because referenced by paravirt */ static inline void notrace -__native_write_msr_notrace(unsigned int msr, u32 low, u32 high) -{ - asm volatile("1: wrmsr\n" - "2:\n" - _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) - : : "c" (msr), "a"(low), "d" (high) : "memory"); -} - -/* Can be uninlined because referenced by paravirt */ -static inline void notrace native_write_msr(unsigned int msr, u32 low, u32 high) { - __native_write_msr_notrace(msr, low, high); + __wrmsr(msr, low, high); + if (msr_tracepoint_active(__tracepoint_write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } -static inline void -wrmsr_notrace(unsigned int msr, u32 low, u32 high) -{ - __native_write_msr_notrace(msr, low, high); -} - /* Can be uninlined because referenced by paravirt */ static inline int notrace native_write_msr_safe(unsigned int msr, u32 low, u32 high) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 1eea6ca40694..0489884fdc44 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -475,6 +475,17 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, native_pmd_val(pmd)); } +static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + if (sizeof(pudval_t) > sizeof(long)) + /* 5 arg words */ + pv_mmu_ops.set_pud_at(mm, addr, pudp, pud); + else + PVOP_VCALL4(pv_mmu_ops.set_pud_at, mm, addr, pudp, + native_pud_val(pud)); +} + static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { pmdval_t val = native_pmd_val(pmd); @@ -673,7 +684,7 @@ static __always_inline void pv_kick(int cpu) PVOP_VCALL1(pv_lock_ops.kick, cpu); } -static __always_inline bool pv_vcpu_is_preempted(int cpu) +static __always_inline bool pv_vcpu_is_preempted(long cpu) { return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu); } diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index bb2de45a60f2..b060f962d581 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -249,6 +249,8 @@ struct pv_mmu_ops { void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmdval); + void (*set_pud_at)(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pudval); void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index fd74a11959de..a8b96e708c2b 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -21,6 +21,10 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) *pmdp = pmd; } +static inline void native_set_pud(pud_t *pudp, pud_t pud) +{ +} + static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); @@ -31,6 +35,10 @@ static inline void native_pmd_clear(pmd_t *pmdp) native_set_pmd(pmdp, __pmd(0)); } +static inline void native_pud_clear(pud_t *pudp) +{ +} + static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp) { @@ -55,6 +63,15 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif +#ifdef CONFIG_SMP +static inline pud_t native_pudp_get_and_clear(pud_t *xp) +{ + return __pud(xchg((pudval_t *)xp, 0)); +} +#else +#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp) +#endif + /* Bit manipulation helper on pte/pgoff entry */ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshift, unsigned long mask, unsigned int leftshift) diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index cdaa58c9b39e..8f50fb3f04e1 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -121,6 +121,12 @@ static inline void native_pmd_clear(pmd_t *pmd) *(tmp + 1) = 0; } +#ifndef CONFIG_SMP +static inline void native_pud_clear(pud_t *pudp) +{ +} +#endif + static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); @@ -176,6 +182,30 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) #endif +#ifdef CONFIG_SMP +union split_pud { + struct { + u32 pud_low; + u32 pud_high; + }; + pud_t pud; +}; + +static inline pud_t native_pudp_get_and_clear(pud_t *pudp) +{ + union split_pud res, *orig = (union split_pud *)pudp; + + /* xchg acts as a barrier before setting of the high bits */ + res.pud_low = xchg(&orig->pud_low, 0); + res.pud_high = orig->pud_high; + orig->pud_high = 0; + + return res.pud; +} +#else +#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp) +#endif + /* Encode and de-code a swap entry */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) #define __swp_type(x) (((x).val) & 0x1f) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 437feb436efa..1cfb36b8c024 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -46,6 +46,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) #define set_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd) +#define set_pud_at(mm, addr, pudp, pud) native_set_pud_at(mm, addr, pudp, pud) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) @@ -128,6 +129,16 @@ static inline int pmd_young(pmd_t pmd) return pmd_flags(pmd) & _PAGE_ACCESSED; } +static inline int pud_dirty(pud_t pud) +{ + return pud_flags(pud) & _PAGE_DIRTY; +} + +static inline int pud_young(pud_t pud) +{ + return pud_flags(pud) & _PAGE_ACCESSED; +} + static inline int pte_write(pte_t pte) { return pte_flags(pte) & _PAGE_RW; @@ -181,6 +192,13 @@ static inline int pmd_trans_huge(pmd_t pmd) return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline int pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; +} +#endif + #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { @@ -192,6 +210,18 @@ static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline int pud_devmap(pud_t pud) +{ + return !!(pud_val(pud) & _PAGE_DEVMAP); +} +#else +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +#endif #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -333,6 +363,65 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE); } +static inline pud_t pud_set_flags(pud_t pud, pudval_t set) +{ + pudval_t v = native_pud_val(pud); + + return __pud(v | set); +} + +static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) +{ + pudval_t v = native_pud_val(pud); + + return __pud(v & ~clear); +} + +static inline pud_t pud_mkold(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_ACCESSED); +} + +static inline pud_t pud_mkclean(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_DIRTY); +} + +static inline pud_t pud_wrprotect(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_RW); +} + +static inline pud_t pud_mkdirty(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); +} + +static inline pud_t pud_mkdevmap(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_DEVMAP); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_PSE); +} + +static inline pud_t pud_mkyoung(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_ACCESSED); +} + +static inline pud_t pud_mkwrite(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_RW); +} + +static inline pud_t pud_mknotpresent(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE); +} + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { @@ -344,6 +433,11 @@ static inline int pmd_soft_dirty(pmd_t pmd) return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } +static inline int pud_soft_dirty(pud_t pud) +{ + return pud_flags(pud) & _PAGE_SOFT_DIRTY; +} + static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); @@ -354,6 +448,11 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pud_t pud_mksoft_dirty(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_SOFT_DIRTY); +} + static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); @@ -364,6 +463,11 @@ static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pud_t pud_clear_soft_dirty(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); +} + #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* @@ -392,6 +496,12 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) massage_pgprot(pgprot)); } +static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) +{ + return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot)); +} + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte); @@ -771,6 +881,14 @@ static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) return res; } +static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) +{ + pud_t res = *pudp; + + native_pud_clear(pudp); + return res; +} + static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep , pte_t pte) { @@ -783,6 +901,12 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr, native_set_pmd(pmdp, pmd); } +static inline void native_set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + native_set_pud(pudp, pud); +} + #ifndef CONFIG_PARAVIRT /* * Rules for using pte_update - it must be called after any PTE update which @@ -861,10 +985,15 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); +extern int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, @@ -884,6 +1013,13 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long return native_pmdp_get_and_clear(pmdp); } +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + return native_pudp_get_and_clear(pudp); +} + #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -932,6 +1068,10 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index b6c0b404898a..fbc73360aea0 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -27,6 +27,7 @@ struct vm_area_struct; extern pgd_t swapper_pg_dir[1024]; extern pgd_t initial_page_table[1024]; +extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } @@ -75,4 +76,35 @@ do { \ #define kern_addr_valid(kaddr) (0) #endif +/* + * This is how much memory in addition to the memory covered up to + * and including _end we need mapped initially. + * We need: + * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) + * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) + * + * Modulo rounding, each megabyte assigned here requires a kilobyte of + * memory, which is currently unreclaimed. + * + * This should be a multiple of a page. + * + * KERNEL_IMAGE_SIZE should be greater than pa(_end) + * and small than max_low_pfn, otherwise will waste some page table entries + */ +#if PTRS_PER_PMD > 1 +#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) +#else +#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) +#endif + +/* + * Number of possible pages in the lowmem region. + * + * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a + * gas warning about overflowing shift count when gas has been compiled + * with only a host target support using a 32-bit type for internal + * representation. + */ +#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) + #endif /* _ASM_X86_PGTABLE_32_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 62b775926045..73c7ccc38912 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -106,6 +106,21 @@ static inline void native_pud_clear(pud_t *pud) native_set_pud(pud, native_make_pud(0)); } +static inline pud_t native_pudp_get_and_clear(pud_t *xp) +{ +#ifdef CONFIG_SMP + return native_make_pud(xchg(&xp->pud, 0)); +#else + /* native_local_pudp_get_and_clear, + * but duplicated because of cyclic dependency + */ + pud_t ret = *xp; + + native_pud_clear(xp); + return ret; +#endif +} + static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { *pgdp = pgd; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index eaf100508c36..f385eca5407a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -104,6 +104,7 @@ struct cpuinfo_x86 { __u8 x86_phys_bits; /* CPUID returned core id bits: */ __u8 x86_coreid_bits; + __u8 cu_id; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ @@ -219,6 +220,24 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, : "memory"); } +#define native_cpuid_reg(reg) \ +static inline unsigned int native_cpuid_##reg(unsigned int op) \ +{ \ + unsigned int eax = op, ebx, ecx = 0, edx; \ + \ + native_cpuid(&eax, &ebx, &ecx, &edx); \ + \ + return reg; \ +} + +/* + * Native CPUID functions returning a single datum. + */ +native_cpuid_reg(eax) +native_cpuid_reg(ebx) +native_cpuid_reg(ecx) +native_cpuid_reg(edx) + static inline void load_cr3(pgd_t *pgdir) { write_cr3(__pa(pgdir)); @@ -285,7 +304,7 @@ struct x86_hw_tss { u16 reserved5; u16 io_bitmap_base; -} __attribute__((packed)) ____cacheline_aligned; +} __attribute__((packed)); #endif /* @@ -323,6 +342,16 @@ struct tss_struct { DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +/* + * sizeof(unsigned long) coming from an extra "long" at the end + * of the iobitmap. + * + * -1? seg base+limit should be pointing to the address of the + * last valid byte + */ +#define __KERNEL_TSS_LIMIT \ + (IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1) + #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); #endif diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index c343ab52579f..48a706f641f2 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -34,7 +34,7 @@ static inline void queued_spin_unlock(struct qspinlock *lock) } #define vcpu_is_preempted vcpu_is_preempted -static inline bool vcpu_is_preempted(int cpu) +static inline bool vcpu_is_preempted(long cpu) { return pv_vcpu_is_preempted(cpu); } diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 921bea7a2708..6d391909e864 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -23,9 +23,6 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) -extern struct static_key paravirt_ticketlocks_enabled; -static __always_inline bool static_key_false(struct static_key *key); - #include <asm/qspinlock.h> /* diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index a3269c897ec5..2e41c50ddf47 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -58,7 +58,7 @@ get_frame_pointer(struct task_struct *task, struct pt_regs *regs) if (task == current) return __builtin_frame_address(0); - return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; + return &((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long * diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 5cb436acd463..fcc5cd387fd1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -36,7 +36,10 @@ static inline void prepare_switch_to(struct task_struct *prev, asmlinkage void ret_from_fork(void); -/* data that is pointed to by thread.sp */ +/* + * This is the structure pointed to by thread.sp for an inactive task. The + * order of the fields must match the code in __switch_to_asm(). + */ struct inactive_task_frame { #ifdef CONFIG_X86_64 unsigned long r15; @@ -48,6 +51,11 @@ struct inactive_task_frame { unsigned long di; #endif unsigned long bx; + + /* + * These two fields must be together. They form a stack frame header, + * needed by get_frame_pointer(). + */ unsigned long bp; unsigned long ret_addr; }; diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 062921ef34e9..6686820feae9 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -10,6 +10,7 @@ struct mm_struct; extern enum uv_system_type get_uv_system_type(void); extern int is_uv_system(void); +extern int is_uv_hubless(void); extern void uv_cpu_init(void); extern void uv_nmi_init(void); extern void uv_system_init(void); @@ -23,6 +24,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } static inline int is_uv_system(void) { return 0; } +static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } static inline const struct cpumask * diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 097b80c989c4..72e8300b1e8a 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -772,6 +772,7 @@ static inline int uv_num_possible_blades(void) /* Per Hub NMI support */ extern void uv_nmi_setup(void); +extern void uv_nmi_setup_hubless(void); /* BMC sets a bit this MMR non-zero before sending an NMI */ #define UVH_NMI_MMR UVH_SCRATCH5 @@ -799,6 +800,8 @@ struct uv_hub_nmi_s { atomic_t read_mmr_count; /* count of MMR reads */ atomic_t nmi_count; /* count of true UV NMIs */ unsigned long nmi_value; /* last value read from NMI MMR */ + bool hub_present; /* false means UV hubless system */ + bool pch_owner; /* indicates this hub owns PCH */ }; struct uv_cpu_nmi_s { diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2b5b2d4b924e..cc54b7026567 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -467,8 +467,16 @@ enum vmcs_field { #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull #define VMX_EPT_IPAT_BIT (1ull << 6) -#define VMX_EPT_ACCESS_BIT (1ull << 8) -#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_ACCESS_BIT (1ull << 8) +#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \ + VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) +#define VMX_EPT_MT_MASK (7ull << VMX_EPT_MT_EPTE_SHIFT) + +/* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */ +#define VMX_EPT_MISCONFIG_WX_VALUE (VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) #define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul @@ -500,6 +508,22 @@ struct vmx_msr_entry { #define ENTRY_FAIL_VMCS_LINK_PTR 4 /* + * Exit Qualifications for EPT Violations + */ +#define EPT_VIOLATION_ACC_READ_BIT 0 +#define EPT_VIOLATION_ACC_WRITE_BIT 1 +#define EPT_VIOLATION_ACC_INSTR_BIT 2 +#define EPT_VIOLATION_READABLE_BIT 3 +#define EPT_VIOLATION_WRITABLE_BIT 4 +#define EPT_VIOLATION_EXECUTABLE_BIT 5 +#define EPT_VIOLATION_ACC_READ (1 << EPT_VIOLATION_ACC_READ_BIT) +#define EPT_VIOLATION_ACC_WRITE (1 << EPT_VIOLATION_ACC_WRITE_BIT) +#define EPT_VIOLATION_ACC_INSTR (1 << EPT_VIOLATION_ACC_INSTR_BIT) +#define EPT_VIOLATION_READABLE (1 << EPT_VIOLATION_READABLE_BIT) +#define EPT_VIOLATION_WRITABLE (1 << EPT_VIOLATION_WRITABLE_BIT) +#define EPT_VIOLATION_EXECUTABLE (1 << EPT_VIOLATION_EXECUTABLE_BIT) + +/* * VM-instruction error numbers */ enum vm_instruction_error_number { diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a12a047184ee..f6d20f6cca12 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -472,6 +472,13 @@ HYPERVISOR_xenpmu_op(unsigned int op, void *arg) return _hypercall2(int, xenpmu_op, op, arg); } +static inline int +HYPERVISOR_dm_op( + domid_t dom, unsigned int nr_bufs, void *bufs) +{ + return _hypercall3(int, dm_op, dom, nr_bufs, bufs); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index b10bf319ed20..5138dacf8bb8 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -135,7 +135,8 @@ struct boot_params { __u8 eddbuf_entries; /* 0x1e9 */ __u8 edd_mbr_sig_buf_entries; /* 0x1ea */ __u8 kbd_status; /* 0x1eb */ - __u8 _pad5[3]; /* 0x1ec */ + __u8 secure_boot; /* 0x1ec */ + __u8 _pad5[2]; /* 0x1ed */ /* * The sentinel is set to a nonzero value (0xff) in header.S. * diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h new file mode 100644 index 000000000000..0bd2be5c7617 --- /dev/null +++ b/arch/x86/include/uapi/asm/hwcap2.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_HWCAP2_H +#define _ASM_X86_HWCAP2_H + +/* MONITOR/MWAIT enabled in Ring 3 */ +#define HWCAP2_RING3MWAIT (1 << 0) + +#endif diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 9b1a91834ac8..3a20ccf787b8 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -73,6 +73,9 @@ */ #define HV_X64_MSR_STAT_PAGES_AVAILABLE (1 << 8) +/* Crash MSR available */ +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) + /* * Feature identification: EBX indicates which flags were specified at * partition creation. The format is the same as the partition creation @@ -144,6 +147,11 @@ */ #define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) +/* + * Crash notification flag. + */ +#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63) + /* MSR used to identify the guest OS. */ #define HV_X64_MSR_GUEST_OS_ID 0x40000000 diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 1421a6585126..cff0bb6556f8 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -50,6 +50,15 @@ struct kvm_steal_time { __u32 pad[11]; }; +#define KVM_CLOCK_PAIRING_WALLCLOCK 0 +struct kvm_clock_pairing { + __s64 sec; + __s64 nsec; + __u64 tsc; + __u32 flags; + __u32 pad[9]; +}; + #define KVM_STEAL_ALIGNMENT_BITS 5 #define KVM_STEAL_VALID_BITS ((-1ULL << (KVM_STEAL_ALIGNMENT_BITS + 1))) #define KVM_STEAL_RESERVED_MASK (((1 << KVM_STEAL_ALIGNMENT_BITS) - 1 ) << 1) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 581386c7e429..bdcdb3b3a219 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -101,7 +101,6 @@ obj-$(CONFIG_APB_TIMER) += apb_timer.o obj-$(CONFIG_AMD_NB) += amd_nb.o obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o -obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 64422f850e95..ae32838cac5f 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -35,6 +35,7 @@ #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <linux/efi-bgrt.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> @@ -723,11 +724,12 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) return 0; } -int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, + int *pcpu) { int cpu; - cpu = acpi_register_lapic(physid, U32_MAX, ACPI_MADT_ENABLED); + cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); return cpu; @@ -1557,6 +1559,12 @@ int __init early_acpi_boot_init(void) return 0; } +static int __init acpi_parse_bgrt(struct acpi_table_header *table) +{ + efi_bgrt_init(table); + return 0; +} + int __init acpi_boot_init(void) { /* those are executed after early-quirks are executed */ @@ -1581,6 +1589,8 @@ int __init acpi_boot_init(void) acpi_process_madt(); acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index af15f4444330..8233a630280f 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -12,7 +12,6 @@ #include <linux/sched.h> #include <acpi/processor.h> -#include <asm/acpi.h> #include <asm/mwait.h> #include <asm/special_insns.h> @@ -89,7 +88,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) retval = 0; /* If the HW does not support any sub-states in this C-state */ if (num_cstate_subtype == 0) { - pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part); + pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", + cx->address, edx_part); retval = -1; goto out; } @@ -104,8 +104,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) if (!mwait_supported[cstate_type]) { mwait_supported[cstate_type] = 1; printk(KERN_DEBUG - "Monitor-Mwait will be used to enter C-%d " - "state\n", cx->type); + "Monitor-Mwait will be used to enter C-%d state\n", + cx->type); } snprintf(cx->desc, ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x", @@ -166,6 +166,7 @@ EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter); static int __init ffh_cstate_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + if (c->x86_vendor != X86_VENDOR_INTEL) return -1; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 5b7e43eff139..8567c851172c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -529,18 +529,19 @@ static void lapic_timer_broadcast(const struct cpumask *mask) * The local apic timer can be used for any function which is CPU local. */ static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | - CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP - | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_state_shutdown = lapic_timer_shutdown, - .set_state_periodic = lapic_timer_set_periodic, - .set_state_oneshot = lapic_timer_set_oneshot, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP + | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_state_shutdown = lapic_timer_shutdown, + .set_state_periodic = lapic_timer_set_periodic, + .set_state_oneshot = lapic_timer_set_oneshot, + .set_state_oneshot_stopped = lapic_timer_shutdown, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); @@ -1245,7 +1246,7 @@ static void lapic_setup_esr(void) /** * setup_local_APIC - setup the local APIC * - * Used to setup local APIC while initializing BSP or bringin up APs. + * Used to setup local APIC while initializing BSP or bringing up APs. * Always called with preemption disabled. */ void setup_local_APIC(void) @@ -2028,8 +2029,8 @@ void disconnect_bsp_APIC(int virt_wire_setup) /* * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated * contiguously, it equals to current allocated max logical CPU ID plus 1. - * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of - * nr_logical_cpuids is nr_cpu_ids. + * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range, + * so the maximum of nr_logical_cpuids is nr_cpu_ids. * * NOTE: Reserve 0 for BSP. */ @@ -2094,7 +2095,7 @@ int __generic_processor_info(int apicid, int version, bool enabled) * Since fixing handling of boot_cpu_physical_apicid requires * another discussion and tests on each platform, we leave it * for now and here we use read_apic_id() directly in this - * function, generic_processor_info(). + * function, __generic_processor_info(). */ if (disabled_cpu_apicid != BAD_APICID && disabled_cpu_apicid != read_apic_id() && diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 945e512a112a..347bb9f65737 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1107,12 +1107,12 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info) ioapic = mp_find_ioapic(gsi); if (ioapic < 0) - return -1; + return -ENODEV; pin = mp_find_ioapic_pin(ioapic, gsi); idx = find_irq_entry(ioapic, pin, mp_INT); if ((flags & IOAPIC_MAP_CHECK) && idx < 0) - return -1; + return -ENODEV; return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info); } @@ -1875,6 +1875,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ack_level, .irq_set_affinity = ioapic_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -1886,6 +1887,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ir_ack_level, .irq_set_affinity = ioapic_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -2115,6 +2117,7 @@ static inline void __init check_timer(void) if (idx != -1 && irq_trigger(idx)) unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2136,6 +2139,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 015bbf30e3e3..c61aec7e65f4 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -82,7 +82,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (domain == NULL) return -ENOSYS; - return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); + return msi_domain_alloc_irqs(domain, &dev->dev, nvec); } void native_teardown_msi_irq(unsigned int irq) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 35690a168cf7..e9f8f8cdd570 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -41,40 +41,44 @@ DEFINE_PER_CPU(int, x2apic_extra_bits); -#define PR_DEVEL(fmt, args...) pr_devel("%s: " fmt, __func__, args) - -static enum uv_system_type uv_system_type; -static u64 gru_start_paddr, gru_end_paddr; -static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr; -static u64 gru_dist_lmask, gru_dist_umask; -static union uvh_apicid uvh_apicid; - -/* info derived from CPUID */ +static enum uv_system_type uv_system_type; +static bool uv_hubless_system; +static u64 gru_start_paddr, gru_end_paddr; +static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr; +static u64 gru_dist_lmask, gru_dist_umask; +static union uvh_apicid uvh_apicid; + +/* Information derived from CPUID: */ static struct { unsigned int apicid_shift; unsigned int apicid_mask; unsigned int socketid_shift; /* aka pnode_shift for UV1/2/3 */ unsigned int pnode_mask; unsigned int gpa_shift; + unsigned int gnode_shift; } uv_cpuid; int uv_min_hub_revision_id; EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); + unsigned int uv_apicid_hibits; EXPORT_SYMBOL_GPL(uv_apicid_hibits); static struct apic apic_x2apic_uv_x; static struct uv_hub_info_s uv_hub_info_node0; -/* Set this to use hardware error handler instead of kernel panic */ +/* Set this to use hardware error handler instead of kernel panic: */ static int disable_uv_undefined_panic = 1; + unsigned long uv_undefined(char *str) { if (likely(!disable_uv_undefined_panic)) panic("UV: error: undefined MMR: %s\n", str); else pr_crit("UV: error: undefined MMR: %s\n", str); - return ~0ul; /* cause a machine fault */ + + /* Cause a machine fault: */ + return ~0ul; } EXPORT_SYMBOL(uv_undefined); @@ -85,18 +89,19 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr) mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr)); val = *mmr; early_iounmap(mmr, sizeof(*mmr)); + return val; } static inline bool is_GRU_range(u64 start, u64 end) { if (gru_dist_base) { - u64 su = start & gru_dist_umask; /* upper (incl pnode) bits */ - u64 sl = start & gru_dist_lmask; /* base offset bits */ + u64 su = start & gru_dist_umask; /* Upper (incl pnode) bits */ + u64 sl = start & gru_dist_lmask; /* Base offset bits */ u64 eu = end & gru_dist_umask; u64 el = end & gru_dist_lmask; - /* Must reside completely within a single GRU range */ + /* Must reside completely within a single GRU range: */ return (sl == gru_dist_base && el == gru_dist_base && su >= gru_first_node_paddr && su <= gru_last_node_paddr && @@ -133,13 +138,14 @@ static int __init early_get_pnodeid(void) break; case UV4_HUB_PART_NUMBER: uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1; + uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */ break; } uv_hub_info->hub_revision = uv_min_hub_revision_id; uv_cpuid.pnode_mask = (1 << m_n_config.s.n_skt) - 1; pnode = (node_id.s.node_id >> 1) & uv_cpuid.pnode_mask; - uv_cpuid.gpa_shift = 46; /* default unless changed */ + uv_cpuid.gpa_shift = 46; /* Default unless changed */ pr_info("UV: rev:%d part#:%x nodeid:%04x n_skt:%d pnmsk:%x pn:%x\n", node_id.s.revision, node_id.s.part_number, node_id.s.node_id, @@ -147,11 +153,12 @@ static int __init early_get_pnodeid(void) return pnode; } -/* [copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */ -#define SMT_LEVEL 0 /* leaf 0xb SMT level */ -#define INVALID_TYPE 0 /* leaf 0xb sub-leaf types */ -#define SMT_TYPE 1 -#define CORE_TYPE 2 +/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */ + +#define SMT_LEVEL 0 /* Leaf 0xb SMT level */ +#define INVALID_TYPE 0 /* Leaf 0xb sub-leaf types */ +#define SMT_TYPE 1 +#define CORE_TYPE 2 #define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff) #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) @@ -165,11 +172,13 @@ static void set_x2apic_bits(void) pr_info("UV: CPU does not have CPUID.11\n"); return; } + cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) { pr_info("UV: CPUID.11 not implemented\n"); return; } + sid_shift = BITS_SHIFT_NEXT_LEVEL(eax); sub_index = 1; do { @@ -180,8 +189,9 @@ static void set_x2apic_bits(void) } sub_index++; } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); - uv_cpuid.apicid_shift = 0; - uv_cpuid.apicid_mask = (~(-1 << sid_shift)); + + uv_cpuid.apicid_shift = 0; + uv_cpuid.apicid_mask = (~(-1 << sid_shift)); uv_cpuid.socketid_shift = sid_shift; } @@ -192,10 +202,8 @@ static void __init early_get_apic_socketid_shift(void) set_x2apic_bits(); - pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", - uv_cpuid.apicid_shift, uv_cpuid.apicid_mask); - pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", - uv_cpuid.socketid_shift, uv_cpuid.pnode_mask); + pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask); + pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask); } /* @@ -208,10 +216,8 @@ static void __init uv_set_apicid_hibit(void) union uv1h_lb_target_physical_apic_id_mask_u apicid_mask; if (is_uv1_hub()) { - apicid_mask.v = - uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK); - uv_apicid_hibits = - apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK; + apicid_mask.v = uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK); + uv_apicid_hibits = apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK; } } @@ -220,20 +226,26 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) int pnodeid; int uv_apic; - if (strncmp(oem_id, "SGI", 3) != 0) + if (strncmp(oem_id, "SGI", 3) != 0) { + if (strncmp(oem_id, "NSGI", 4) == 0) { + uv_hubless_system = true; + pr_info("UV: OEM IDs %s/%s, HUBLESS\n", + oem_id, oem_table_id); + } return 0; + } if (numa_off) { pr_err("UV: NUMA is off, disabling UV support\n"); return 0; } - /* Setup early hub type field in uv_hub_info for Node 0 */ + /* Set up early hub type field in uv_hub_info for Node 0 */ uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; /* * Determine UV arch type. - * SGI: UV100/1000 + * SGI: UV100/1000 * SGI2: UV2000/3000 * SGI3: UV300 (truncated to 4 chars because of different varieties) * SGI4: UV400 (truncated to 4 chars because of different varieties) @@ -249,31 +261,32 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) pnodeid = early_get_pnodeid(); early_get_apic_socketid_shift(); - x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; + + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; x86_platform.nmi_init = uv_nmi_init; - if (!strcmp(oem_table_id, "UVX")) { /* most common */ + if (!strcmp(oem_table_id, "UVX")) { + /* This is the most common hardware variant: */ uv_system_type = UV_X2APIC; uv_apic = 0; - } else if (!strcmp(oem_table_id, "UVH")) { /* only UV1 systems */ + } else if (!strcmp(oem_table_id, "UVH")) { + /* Only UV1 systems: */ uv_system_type = UV_NON_UNIQUE_APIC; - __this_cpu_write(x2apic_extra_bits, - pnodeid << uvh_apicid.s.pnode_shift); + __this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift); uv_set_apicid_hibit(); uv_apic = 1; - } else if (!strcmp(oem_table_id, "UVL")) { /* only used for */ - uv_system_type = UV_LEGACY_APIC; /* very small systems */ + } else if (!strcmp(oem_table_id, "UVL")) { + /* Only used for very small systems: */ + uv_system_type = UV_LEGACY_APIC; uv_apic = 0; } else { goto badbios; } - pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", - oem_id, oem_table_id, uv_system_type, - uv_min_hub_revision_id, uv_apic); + pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", oem_id, oem_table_id, uv_system_type, uv_min_hub_revision_id, uv_apic); return uv_apic; @@ -294,6 +307,12 @@ int is_uv_system(void) } EXPORT_SYMBOL_GPL(is_uv_system); +int is_uv_hubless(void) +{ + return uv_hubless_system; +} +EXPORT_SYMBOL_GPL(is_uv_hubless); + void **__uv_hub_info_list; EXPORT_SYMBOL_GPL(__uv_hub_info_list); @@ -306,16 +325,18 @@ EXPORT_SYMBOL_GPL(uv_possible_blades); unsigned long sn_rtc_cycles_per_second; EXPORT_SYMBOL(sn_rtc_cycles_per_second); -/* the following values are used for the per node hub info struct */ -static __initdata unsigned short *_node_to_pnode; -static __initdata unsigned short _min_socket, _max_socket; -static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len; -static __initdata struct uv_gam_range_entry *uv_gre_table; -static __initdata struct uv_gam_parameters *uv_gp_table; -static __initdata unsigned short *_socket_to_node; -static __initdata unsigned short *_socket_to_pnode; -static __initdata unsigned short *_pnode_to_socket; -static __initdata struct uv_gam_range_s *_gr_table; +/* The following values are used for the per node hub info struct */ +static __initdata unsigned short *_node_to_pnode; +static __initdata unsigned short _min_socket, _max_socket; +static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len; +static __initdata struct uv_gam_range_entry *uv_gre_table; +static __initdata struct uv_gam_parameters *uv_gp_table; +static __initdata unsigned short *_socket_to_node; +static __initdata unsigned short *_socket_to_pnode; +static __initdata unsigned short *_pnode_to_socket; + +static __initdata struct uv_gam_range_s *_gr_table; + #define SOCK_EMPTY ((unsigned short)~0) extern int uv_hub_info_version(void) @@ -324,7 +345,7 @@ extern int uv_hub_info_version(void) } EXPORT_SYMBOL(uv_hub_info_version); -/* Build GAM range lookup table */ +/* Build GAM range lookup table: */ static __init void build_uv_gr_table(void) { struct uv_gam_range_entry *gre = uv_gre_table; @@ -342,25 +363,24 @@ static __init void build_uv_gr_table(void) for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) { - if (!ram_limit) { /* mark hole between ram/non-ram */ + if (!ram_limit) { + /* Mark hole between RAM/non-RAM: */ ram_limit = last_limit; last_limit = gre->limit; lsid++; continue; } last_limit = gre->limit; - pr_info("UV: extra hole in GAM RE table @%d\n", - (int)(gre - uv_gre_table)); + pr_info("UV: extra hole in GAM RE table @%d\n", (int)(gre - uv_gre_table)); continue; } if (_max_socket < gre->sockid) { - pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n", - gre->sockid, _max_socket, - (int)(gre - uv_gre_table)); + pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n", gre->sockid, _max_socket, (int)(gre - uv_gre_table)); continue; } sid = gre->sockid - _min_socket; - if (lsid < sid) { /* new range */ + if (lsid < sid) { + /* New range: */ grt = &_gr_table[indx]; grt->base = lindx; grt->nasid = gre->nasid; @@ -369,27 +389,32 @@ static __init void build_uv_gr_table(void) lindx = indx++; continue; } - if (lsid == sid && !ram_limit) { /* update range */ - if (grt->limit == last_limit) { /* .. if contiguous */ + /* Update range: */ + if (lsid == sid && !ram_limit) { + /* .. if contiguous: */ + if (grt->limit == last_limit) { grt->limit = last_limit = gre->limit; continue; } } - if (!ram_limit) { /* non-contiguous ram range */ + /* Non-contiguous RAM range: */ + if (!ram_limit) { grt++; grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; continue; } - grt++; /* non-contiguous/non-ram */ - grt->base = grt - _gr_table; /* base is this entry */ + /* Non-contiguous/non-RAM: */ + grt++; + /* base is this entry */ + grt->base = grt - _gr_table; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; lsid++; } - /* shorten table if possible */ + /* Shorten table if possible */ grt++; i = grt - _gr_table; if (i < _gr_table_len) { @@ -403,16 +428,15 @@ static __init void build_uv_gr_table(void) } } - /* display resultant gam range table */ + /* Display resultant GAM range table: */ for (i = 0, grt = _gr_table; i < _gr_table_len; i++, grt++) { + unsigned long start, end; int gb = grt->base; - unsigned long start = gb < 0 ? 0 : - (unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT; - unsigned long end = - (unsigned long)grt->limit << UV_GAM_RANGE_SHFT; - pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n", - i, grt->nasid, start, end, gb); + start = gb < 0 ? 0 : (unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT; + end = (unsigned long)grt->limit << UV_GAM_RANGE_SHFT; + + pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n", i, grt->nasid, start, end, gb); } } @@ -423,16 +447,19 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) pnode = uv_apicid_to_pnode(phys_apicid); phys_apicid |= uv_apicid_hibits; + val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_INIT; + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) | ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) | APIC_DM_STARTUP; + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); return 0; @@ -566,7 +593,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .apic_id_registered = uv_apic_id_registered, .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 0, /* physical */ + .irq_dest_mode = 0, /* Physical */ .target_cpus = online_target_cpus, .disable_esr = 0, @@ -627,23 +654,22 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) switch (i) { case 0: m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR; - m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR; + m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR; break; case 1: m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR; - m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR; + m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR; break; case 2: m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR; - m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR; + m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR; break; } alias.v = uv_read_local_mmr(m_overlay); if (alias.s.enable && alias.s.base == 0) { *size = (1UL << alias.s.m_alias); redirect.v = uv_read_local_mmr(m_redirect); - *base = (unsigned long)redirect.s.dest_base - << DEST_SHIFT; + *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT; return; } } @@ -652,8 +678,7 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) enum map_type {map_wb, map_uc}; -static __init void map_high(char *id, unsigned long base, int pshift, - int bshift, int max_pnode, enum map_type map_type) +static __init void map_high(char *id, unsigned long base, int pshift, int bshift, int max_pnode, enum map_type map_type) { unsigned long bytes, paddr; @@ -678,16 +703,19 @@ static __init void map_gru_distributed(unsigned long c) int nid; gru.v = c; - /* only base bits 42:28 relevant in dist mode */ + + /* Only base bits 42:28 relevant in dist mode */ gru_dist_base = gru.v & 0x000007fff0000000UL; if (!gru_dist_base) { pr_info("UV: Map GRU_DIST base address NULL\n"); return; } + bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1); gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1); gru_dist_base &= gru_dist_lmask; /* Clear bits above M */ + for_each_online_node(nid) { paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) | gru_dist_base; @@ -695,11 +723,12 @@ static __init void map_gru_distributed(unsigned long c) gru_first_node_paddr = min(paddr, gru_first_node_paddr); gru_last_node_paddr = max(paddr, gru_last_node_paddr); } + /* Save upper (63:M) bits of address only for is_GRU_range */ gru_first_node_paddr &= gru_dist_umask; gru_last_node_paddr &= gru_dist_umask; - pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", - gru_dist_base, gru_first_node_paddr, gru_last_node_paddr); + + pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", gru_dist_base, gru_first_node_paddr, gru_last_node_paddr); } static __init void map_gru_high(int max_pnode) @@ -719,6 +748,7 @@ static __init void map_gru_high(int max_pnode) map_gru_distributed(gru.v); return; } + base = (gru.v & mask) >> shift; map_high("GRU", base, shift, shift, max_pnode, map_wb); gru_start_paddr = ((u64)base << shift); @@ -772,8 +802,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) id = mmiohs[index].id; overlay.v = uv_read_local_mmr(mmiohs[index].overlay); - pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", - id, overlay.v, overlay.s3.base, overlay.s3.m_io); + + pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io); if (!overlay.s3.enable) { pr_info("UV: %s disabled\n", id); return; @@ -784,7 +814,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) m_io = overlay.s3.m_io; mmr = mmiohs[index].redirect; n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH; - min_pnode *= 2; /* convert to NASID */ + /* Convert to NASID: */ + min_pnode *= 2; max_pnode *= 2; max_io = lnasid = fi = li = -1; @@ -793,16 +824,18 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) redirect.v = uv_read_local_mmr(mmr + i * 8); nasid = redirect.s3.nasid; + /* Invalid NASID: */ if (nasid < min_pnode || max_pnode < nasid) - nasid = -1; /* invalid NASID */ + nasid = -1; if (nasid == lnasid) { li = i; - if (i != n-1) /* last entry check */ + /* Last entry check: */ + if (i != n-1) continue; } - /* check if we have a cached (or last) redirect to print */ + /* Check if we have a cached (or last) redirect to print: */ if (lnasid != -1 || (i == n-1 && nasid != -1)) { unsigned long addr1, addr2; int f, l; @@ -814,12 +847,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) f = fi; l = li; } - addr1 = (base << shift) + - f * (1ULL << m_io); - addr2 = (base << shift) + - (l + 1) * (1ULL << m_io); - pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", - id, fi, li, lnasid, addr1, addr2); + addr1 = (base << shift) + f * (1ULL << m_io); + addr2 = (base << shift) + (l + 1) * (1ULL << m_io); + pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2); if (max_io < l) max_io = l; } @@ -827,8 +857,7 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode) lnasid = nasid; } - pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", - id, base, shift, m_io, max_io); + pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", id, base, shift, m_io, max_io); if (max_io >= 0) map_high(id, base, shift, m_io, max_io, map_uc); @@ -841,36 +870,35 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode) int shift, enable, m_io, n_io; if (is_uv3_hub() || is_uv4_hub()) { - /* Map both MMIOH Regions */ + /* Map both MMIOH regions: */ map_mmioh_high_uv3(0, min_pnode, max_pnode); map_mmioh_high_uv3(1, min_pnode, max_pnode); return; } if (is_uv1_hub()) { - mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; - shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - mmioh.v = uv_read_local_mmr(mmr); - enable = !!mmioh.s1.enable; - base = mmioh.s1.base; - m_io = mmioh.s1.m_io; - n_io = mmioh.s1.n_io; + mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; + shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s1.enable; + base = mmioh.s1.base; + m_io = mmioh.s1.m_io; + n_io = mmioh.s1.n_io; } else if (is_uv2_hub()) { - mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; - shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; - mmioh.v = uv_read_local_mmr(mmr); - enable = !!mmioh.s2.enable; - base = mmioh.s2.base; - m_io = mmioh.s2.m_io; - n_io = mmioh.s2.n_io; - } else + mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR; + shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT; + mmioh.v = uv_read_local_mmr(mmr); + enable = !!mmioh.s2.enable; + base = mmioh.s2.base; + m_io = mmioh.s2.m_io; + n_io = mmioh.s2.n_io; + } else { return; + } if (enable) { max_pnode &= (1 << n_io) - 1; - pr_info( - "UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", - base, shift, m_io, n_io, max_pnode); + pr_info("UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", base, shift, m_io, n_io, max_pnode); map_high("MMIOH", base, shift, m_io, max_pnode, map_uc); } else { pr_info("UV: MMIOH disabled\n"); @@ -888,16 +916,16 @@ static __init void uv_rtc_init(void) long status; u64 ticks_per_sec; - status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, - &ticks_per_sec); + status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec); + if (status != BIOS_STATUS_SUCCESS || ticks_per_sec < 100000) { - printk(KERN_WARNING - "unable to determine platform RTC clock frequency, " - "guessing.\n"); - /* BIOS gives wrong value for clock freq. so guess */ + pr_warn("UV: unable to determine platform RTC clock frequency, guessing.\n"); + + /* BIOS gives wrong value for clock frequency, so guess: */ sn_rtc_cycles_per_second = 1000000000000UL / 30000UL; - } else + } else { sn_rtc_cycles_per_second = ticks_per_sec; + } } /* @@ -908,19 +936,19 @@ static void uv_heartbeat(unsigned long ignored) struct timer_list *timer = &uv_scir_info->timer; unsigned char bits = uv_scir_info->state; - /* flip heartbeat bit */ + /* Flip heartbeat bit: */ bits ^= SCIR_CPU_HEARTBEAT; - /* is this cpu idle? */ + /* Is this CPU idle? */ if (idle_cpu(raw_smp_processor_id())) bits &= ~SCIR_CPU_ACTIVITY; else bits |= SCIR_CPU_ACTIVITY; - /* update system controller interface reg */ + /* Update system controller interface reg: */ uv_set_scir_bits(bits); - /* enable next timer period */ + /* Enable next timer period: */ mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL); } @@ -935,7 +963,7 @@ static int uv_heartbeat_enable(unsigned int cpu) add_timer_on(timer, cpu); uv_cpu_scir_info(cpu)->enabled = 1; - /* also ensure that boot cpu is enabled */ + /* Also ensure that boot CPU is enabled: */ cpu = 0; } return 0; @@ -968,9 +996,11 @@ static __init int uv_init_heartbeat(void) { int cpu; - if (is_uv_system()) + if (is_uv_system()) { for_each_online_cpu(cpu) uv_heartbeat_enable(cpu); + } + return 0; } @@ -979,14 +1009,10 @@ late_initcall(uv_init_heartbeat); #endif /* !CONFIG_HOTPLUG_CPU */ /* Direct Legacy VGA I/O traffic to designated IOH */ -int uv_set_vga_state(struct pci_dev *pdev, bool decode, - unsigned int command_bits, u32 flags) +int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags) { int domain, bus, rc; - PR_DEVEL("devfn %x decode %d cmd %x flags %d\n", - pdev->devfn, decode, command_bits, flags); - if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) return 0; @@ -997,13 +1023,12 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode, bus = pdev->bus->number; rc = uv_bios_set_legacy_vga_target(decode, domain, bus); - PR_DEVEL("vga decode %d %x:%x, rc: %d\n", decode, domain, bus, rc); return rc; } /* - * Called on each cpu to initialize the per_cpu UV data area. + * Called on each CPU to initialize the per_cpu UV data area. * FIXME: hotplug not supported yet */ void uv_cpu_init(void) @@ -1030,90 +1055,79 @@ static void get_mn(struct mn *mnp) union uvh_rh_gam_config_mmr_u m_n_config; union uv3h_gr0_gam_gr_config_u m_gr_config; - m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR); - mnp->n_val = m_n_config.s.n_skt; + /* Make sure the whole structure is well initialized: */ + memset(mnp, 0, sizeof(*mnp)); + + m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR); + mnp->n_val = m_n_config.s.n_skt; + if (is_uv4_hub()) { - mnp->m_val = 0; - mnp->n_lshift = 0; + mnp->m_val = 0; + mnp->n_lshift = 0; } else if (is_uv3_hub()) { - mnp->m_val = m_n_config.s3.m_skt; - m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG); - mnp->n_lshift = m_gr_config.s3.m_skt; + mnp->m_val = m_n_config.s3.m_skt; + m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG); + mnp->n_lshift = m_gr_config.s3.m_skt; } else if (is_uv2_hub()) { - mnp->m_val = m_n_config.s2.m_skt; - mnp->n_lshift = mnp->m_val == 40 ? 40 : 39; + mnp->m_val = m_n_config.s2.m_skt; + mnp->n_lshift = mnp->m_val == 40 ? 40 : 39; } else if (is_uv1_hub()) { - mnp->m_val = m_n_config.s1.m_skt; - mnp->n_lshift = mnp->m_val; + mnp->m_val = m_n_config.s1.m_skt; + mnp->n_lshift = mnp->m_val; } mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0; } -void __init uv_init_hub_info(struct uv_hub_info_s *hub_info) +void __init uv_init_hub_info(struct uv_hub_info_s *hi) { - struct mn mn = {0}; /* avoid unitialized warnings */ union uvh_node_id_u node_id; + struct mn mn; get_mn(&mn); - hub_info->m_val = mn.m_val; - hub_info->n_val = mn.n_val; - hub_info->m_shift = mn.m_shift; - hub_info->n_lshift = mn.n_lshift ? mn.n_lshift : 0; - - hub_info->hub_revision = uv_hub_info->hub_revision; - hub_info->pnode_mask = uv_cpuid.pnode_mask; - hub_info->min_pnode = _min_pnode; - hub_info->min_socket = _min_socket; - hub_info->pnode_to_socket = _pnode_to_socket; - hub_info->socket_to_node = _socket_to_node; - hub_info->socket_to_pnode = _socket_to_pnode; - hub_info->gr_table_len = _gr_table_len; - hub_info->gr_table = _gr_table; - hub_info->gpa_mask = mn.m_val ? + hi->gpa_mask = mn.m_val ? (1UL << (mn.m_val + mn.n_val)) - 1 : (1UL << uv_cpuid.gpa_shift) - 1; - node_id.v = uv_read_local_mmr(UVH_NODE_ID); - hub_info->gnode_extra = - (node_id.s.node_id & ~((1 << mn.n_val) - 1)) >> 1; - - hub_info->gnode_upper = - ((unsigned long)hub_info->gnode_extra << mn.m_val); + hi->m_val = mn.m_val; + hi->n_val = mn.n_val; + hi->m_shift = mn.m_shift; + hi->n_lshift = mn.n_lshift ? mn.n_lshift : 0; + hi->hub_revision = uv_hub_info->hub_revision; + hi->pnode_mask = uv_cpuid.pnode_mask; + hi->min_pnode = _min_pnode; + hi->min_socket = _min_socket; + hi->pnode_to_socket = _pnode_to_socket; + hi->socket_to_node = _socket_to_node; + hi->socket_to_pnode = _socket_to_pnode; + hi->gr_table_len = _gr_table_len; + hi->gr_table = _gr_table; + + node_id.v = uv_read_local_mmr(UVH_NODE_ID); + uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val); + hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1; + hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val; if (uv_gp_table) { - hub_info->global_mmr_base = uv_gp_table->mmr_base; - hub_info->global_mmr_shift = uv_gp_table->mmr_shift; - hub_info->global_gru_base = uv_gp_table->gru_base; - hub_info->global_gru_shift = uv_gp_table->gru_shift; - hub_info->gpa_shift = uv_gp_table->gpa_shift; - hub_info->gpa_mask = (1UL << hub_info->gpa_shift) - 1; + hi->global_mmr_base = uv_gp_table->mmr_base; + hi->global_mmr_shift = uv_gp_table->mmr_shift; + hi->global_gru_base = uv_gp_table->gru_base; + hi->global_gru_shift = uv_gp_table->gru_shift; + hi->gpa_shift = uv_gp_table->gpa_shift; + hi->gpa_mask = (1UL << hi->gpa_shift) - 1; } else { - hub_info->global_mmr_base = - uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & - ~UV_MMR_ENABLE; - hub_info->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT; + hi->global_mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; + hi->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT; } - get_lowmem_redirect( - &hub_info->lowmem_remap_base, &hub_info->lowmem_remap_top); - - hub_info->apic_pnode_shift = uv_cpuid.socketid_shift; - - /* show system specific info */ - pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n", - hub_info->n_val, hub_info->m_val, - hub_info->m_shift, hub_info->n_lshift); - - pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n", - hub_info->gpa_mask, hub_info->gpa_shift, - hub_info->pnode_mask, hub_info->apic_pnode_shift); + get_lowmem_redirect(&hi->lowmem_remap_base, &hi->lowmem_remap_top); - pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n", - hub_info->global_mmr_base, hub_info->global_mmr_shift, - hub_info->global_gru_base, hub_info->global_gru_shift); + hi->apic_pnode_shift = uv_cpuid.socketid_shift; - pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n", - hub_info->gnode_upper, hub_info->gnode_extra); + /* Show system specific info: */ + pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n", hi->n_val, hi->m_val, hi->m_shift, hi->n_lshift); + pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n", hi->gpa_mask, hi->gpa_shift, hi->pnode_mask, hi->apic_pnode_shift); + pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n", hi->global_mmr_base, hi->global_mmr_shift, hi->global_gru_base, hi->global_gru_shift); + pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n", hi->gnode_upper, hi->gnode_extra); } static void __init decode_gam_params(unsigned long ptr) @@ -1139,12 +1153,9 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", - "Range", "", "Size", "Type", "NASID", - "SID", "PN"); + pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info( - "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, @@ -1162,29 +1173,32 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) if (pnode_max < gre->pnode) pnode_max = gre->pnode; } - _min_socket = sock_min; - _max_socket = sock_max; - _min_pnode = pnode_min; - _max_pnode = pnode_max; - _gr_table_len = index; - pr_info( - "UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n", - index, _min_socket, _max_socket, _min_pnode, _max_pnode); + _min_socket = sock_min; + _max_socket = sock_max; + _min_pnode = pnode_min; + _max_pnode = pnode_max; + _gr_table_len = index; + + pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n", index, _min_socket, _max_socket, _min_pnode, _max_pnode); } -static void __init decode_uv_systab(void) +static int __init decode_uv_systab(void) { struct uv_systab *st; int i; + if (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE) + return 0; /* No extended UVsystab required */ + st = uv_systab; - if ((!st || st->revision < UV_SYSTAB_VERSION_UV4) && !is_uv4_hub()) - return; - if (st->revision != UV_SYSTAB_VERSION_UV4_LATEST) { - pr_crit( - "UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n", - st->revision, UV_SYSTAB_VERSION_UV4_LATEST); - BUG(); + if ((!st) || (st->revision < UV_SYSTAB_VERSION_UV4_LATEST)) { + int rev = st ? st->revision : 0; + + pr_err("UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n", rev, UV_SYSTAB_VERSION_UV4_LATEST); + pr_err("UV: Cannot support UV operations, switching to generic PC\n"); + uv_system_type = UV_NONE; + + return -EINVAL; } for (i = 0; st->entry[i].type != UV_SYSTAB_TYPE_UNUSED; i++) { @@ -1205,10 +1219,11 @@ static void __init decode_uv_systab(void) break; } } + return 0; } /* - * Setup physical blade translations from UVH_NODE_PRESENT_TABLE + * Set up physical blade translations from UVH_NODE_PRESENT_TABLE * .. NB: UVH_NODE_PRESENT_TABLE is going away, * .. being replaced by GAM Range Table */ @@ -1244,14 +1259,13 @@ static void __init build_socket_tables(void) if (!gre) { if (is_uv1_hub() || is_uv2_hub() || is_uv3_hub()) { pr_info("UV: No UVsystab socket table, ignoring\n"); - return; /* not required */ + return; } - pr_crit( - "UV: Error: UVsystab address translations not available!\n"); + pr_crit("UV: Error: UVsystab address translations not available!\n"); BUG(); } - /* build socket id -> node id, pnode */ + /* Build socket id -> node id, pnode */ num = maxsock - minsock + 1; bytes = num * sizeof(_socket_to_node[0]); _socket_to_node = kmalloc(bytes, GFP_KERNEL); @@ -1268,27 +1282,27 @@ static void __init build_socket_tables(void) for (i = 0; i < nump; i++) _pnode_to_socket[i] = SOCK_EMPTY; - /* fill in pnode/node/addr conversion list values */ + /* Fill in pnode/node/addr conversion list values: */ pr_info("UV: GAM Building socket/pnode conversion tables\n"); for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) continue; i = gre->sockid - minsock; + /* Duplicate: */ if (_socket_to_pnode[i] != SOCK_EMPTY) - continue; /* duplicate */ + continue; _socket_to_pnode[i] = gre->pnode; i = gre->pnode - minpnode; _pnode_to_socket[i] = gre->sockid; - pr_info( - "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", + pr_info("UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", gre->sockid, gre->type, gre->nasid, _socket_to_pnode[gre->sockid - minsock], _pnode_to_socket[gre->pnode - minpnode]); } - /* Set socket -> node values */ + /* Set socket -> node values: */ lnid = -1; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); @@ -1304,7 +1318,7 @@ static void __init build_socket_tables(void) sockid, apicid, nid); } - /* Setup physical blade to pnode translation from GAM Range Table */ + /* Set up physical blade to pnode translation from GAM Range Table: */ bytes = num_possible_nodes() * sizeof(_node_to_pnode[0]); _node_to_pnode = kmalloc(bytes, GFP_KERNEL); BUG_ON(!_node_to_pnode); @@ -1314,8 +1328,7 @@ static void __init build_socket_tables(void) for (sockid = minsock; sockid <= maxsock; sockid++) { if (lnid == _socket_to_node[sockid - minsock]) { - _node_to_pnode[lnid] = - _socket_to_pnode[sockid - minsock]; + _node_to_pnode[lnid] = _socket_to_pnode[sockid - minsock]; break; } } @@ -1332,8 +1345,7 @@ static void __init build_socket_tables(void) pr_info("UV: Checking socket->node/pnode for identity maps\n"); if (minsock == 0) { for (i = 0; i < num; i++) - if (_socket_to_node[i] == SOCK_EMPTY || - i != _socket_to_node[i]) + if (_socket_to_node[i] == SOCK_EMPTY || i != _socket_to_node[i]) break; if (i >= num) { kfree(_socket_to_node); @@ -1354,7 +1366,7 @@ static void __init build_socket_tables(void) } } -void __init uv_system_init(void) +static void __init uv_system_init_hub(void) { struct uv_hub_info_s hub_info = {0}; int bytes, cpu, nodeid; @@ -1372,8 +1384,13 @@ void __init uv_system_init(void) map_low_mmrs(); - uv_bios_init(); /* get uv_systab for decoding */ - decode_uv_systab(); + /* Get uv_systab for decoding: */ + uv_bios_init(); + + /* If there's an UVsystab problem then abort UV init: */ + if (decode_uv_systab() < 0) + return; + build_socket_tables(); build_uv_gr_table(); uv_init_hub_info(&hub_info); @@ -1381,14 +1398,10 @@ void __init uv_system_init(void) if (!_node_to_pnode) boot_init_possible_blades(&hub_info); - /* uv_num_possible_blades() is really the hub count */ - pr_info("UV: Found %d hubs, %d nodes, %d cpus\n", - uv_num_possible_blades(), - num_possible_nodes(), - num_possible_cpus()); + /* uv_num_possible_blades() is really the hub count: */ + pr_info("UV: Found %d hubs, %d nodes, %d CPUs\n", uv_num_possible_blades(), num_possible_nodes(), num_possible_cpus()); - uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id, - &sn_region_size, &system_serial_number); + uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id, &sn_region_size, &system_serial_number); hub_info.coherency_domain_number = sn_coherency_id; uv_rtc_init(); @@ -1401,33 +1414,31 @@ void __init uv_system_init(void) struct uv_hub_info_s *new_hub; if (__uv_hub_info_list[nodeid]) { - pr_err("UV: Node %d UV HUB already initialized!?\n", - nodeid); + pr_err("UV: Node %d UV HUB already initialized!?\n", nodeid); BUG(); } /* Allocate new per hub info list */ - new_hub = (nodeid == 0) ? - &uv_hub_info_node0 : - kzalloc_node(bytes, GFP_KERNEL, nodeid); + new_hub = (nodeid == 0) ? &uv_hub_info_node0 : kzalloc_node(bytes, GFP_KERNEL, nodeid); BUG_ON(!new_hub); __uv_hub_info_list[nodeid] = new_hub; new_hub = uv_hub_info_list(nodeid); BUG_ON(!new_hub); *new_hub = hub_info; - /* Use information from GAM table if available */ + /* Use information from GAM table if available: */ if (_node_to_pnode) new_hub->pnode = _node_to_pnode[nodeid]; - else /* Fill in during cpu loop */ + else /* Or fill in during CPU loop: */ new_hub->pnode = 0xffff; + new_hub->numa_blade_id = uv_node_to_blade_id(nodeid); new_hub->memory_nid = -1; new_hub->nr_possible_cpus = 0; new_hub->nr_online_cpus = 0; } - /* Initialize per cpu info */ + /* Initialize per CPU info: */ for_each_possible_cpu(cpu) { int apicid = per_cpu(x86_cpu_to_apicid, cpu); int numa_node_id; @@ -1438,22 +1449,24 @@ void __init uv_system_init(void) pnode = uv_apicid_to_pnode(apicid); uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid); - uv_cpu_info_per(cpu)->blade_cpu_id = - uv_cpu_hub_info(cpu)->nr_possible_cpus++; + uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++; if (uv_cpu_hub_info(cpu)->memory_nid == -1) uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu); - if (nodeid != numa_node_id && /* init memoryless node */ + + /* Init memoryless node: */ + if (nodeid != numa_node_id && uv_hub_info_list(numa_node_id)->pnode == 0xffff) uv_hub_info_list(numa_node_id)->pnode = pnode; else if (uv_cpu_hub_info(cpu)->pnode == 0xffff) uv_cpu_hub_info(cpu)->pnode = pnode; + uv_cpu_scir_info(cpu)->offset = uv_scir_offset(apicid); } for_each_node(nodeid) { unsigned short pnode = uv_hub_info_list(nodeid)->pnode; - /* Add pnode info for pre-GAM list nodes without cpus */ + /* Add pnode info for pre-GAM list nodes without CPUs: */ if (pnode == 0xffff) { unsigned long paddr; @@ -1479,15 +1492,30 @@ void __init uv_system_init(void) uv_scir_register_cpu_notifier(); proc_mkdir("sgi_uv", NULL); - /* register Legacy VGA I/O redirection handler */ + /* Register Legacy VGA I/O redirection handler: */ pci_register_set_vga_state(uv_set_vga_state); /* * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as - * EFI is not enabled in the kdump kernel. + * EFI is not enabled in the kdump kernel: */ if (is_kdump_kernel()) reboot_type = BOOT_ACPI; } +/* + * There is a small amount of UV specific code needed to initialize a + * UV system that does not have a "UV HUB" (referred to as "hubless"). + */ +void __init uv_system_init(void) +{ + if (likely(!is_uv_system() && !is_uv_hubless())) + return; + + if (is_uv_system()) + uv_system_init_hub(); + else + uv_nmi_setup_hubless(); +} + apic_driver(apic_x2apic_uv_x); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 45d44c173cf9..4a7080c84a5a 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev, { static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ - static unsigned int last_stime; /* = 0 */ - cputime_t stime, utime; + static u64 last_stime; /* = 0 */ + u64 stime, utime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = cputime_to_jiffies(stime - last_stime); + idle_percentage = nsecs_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index c62e015b126c..de827d6ac8c2 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -81,6 +81,7 @@ void common(void) { BLANK(); OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_secure_boot, boot_params, secure_boot); OFFSET(BP_loadflags, boot_params, hdr.loadflags); OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); OFFSET(BP_version, boot_params, hdr.version); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 210927ee2e74..99332f550c48 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -13,6 +13,10 @@ static char syscalls_ia32[] = { #include <asm/syscalls_32.h> }; +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#include <asm/kvm_para.h> +#endif + int main(void) { #ifdef CONFIG_PARAVIRT @@ -22,6 +26,11 @@ int main(void) BLANK(); #endif +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_PARAVIRT_SPINLOCKS) + OFFSET(KVM_STEAL_TIME_preempted, kvm_steal_time, preempted); + BLANK(); +#endif + #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 71cae73a5076..4e95b2e0d95f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -312,12 +312,19 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - node_id = ecx & 7; - /* get compute unit information */ - smp_num_siblings = ((ebx >> 8) & 3) + 1; - c->x86_max_cores /= smp_num_siblings; - c->cpu_core_id = ebx & 0xff; + node_id = ecx & 0xff; + smp_num_siblings = ((ebx >> 8) & 0xff) + 1; + + if (c->x86 == 0x15) + c->cu_id = ebx & 0xff; + + if (c->x86 >= 0x17) { + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + } /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -548,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Bit 12 of 8000_0007 edx is accumulated power mechanism. */ diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 1661d8ec9280..2c234a6d94c4 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -1,5 +1,5 @@ -#include <linux/bitops.h> -#include <linux/kernel.h> + +#include <linux/sched.h> #include <asm/cpufeature.h> #include <asm/e820.h> @@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_64 set_cpu_cap(c, X86_FEATURE_SYSENTER32); #endif + + clear_sched_clock_stable(); } static void init_centaur(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index dc1697ca5191..f07005e6f461 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -35,6 +35,7 @@ #include <asm/desc.h> #include <asm/fpu/internal.h> #include <asm/mtrr.h> +#include <asm/hwcap2.h> #include <linux/numa.h> #include <asm/asm.h> #include <asm/bugs.h> @@ -51,6 +52,8 @@ #include "cpu.h" +u32 elf_hwcap2 __read_mostly; + /* all of these masks are initialized in setup_cpu_local_masks() */ cpumask_var_t cpu_initialized_mask; cpumask_var_t cpu_callout_mask; @@ -83,6 +86,7 @@ static void default_init(struct cpuinfo_x86 *c) strcpy(c->x86_model_id, "386"); } #endif + clear_sched_clock_stable(); } static const struct cpu_dev default_cpu = { @@ -655,6 +659,16 @@ void cpu_detect(struct cpuinfo_x86 *c) } } +static void apply_forced_caps(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < NCAPINTS; i++) { + c->x86_capability[i] &= ~cpu_caps_cleared[i]; + c->x86_capability[i] |= cpu_caps_set[i]; + } +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -748,6 +762,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); init_scattered_cpuid_features(c); + + /* + * Clear/Set all flags overridden by options, after probe. + * This needs to happen each time we re-probe, which may happen + * several times during CPU initialization. + */ + apply_forced_caps(c); } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -801,14 +822,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) memset(&c->x86_capability, 0, sizeof c->x86_capability); c->extended_cpuid_level = 0; - if (!have_cpuid_p()) - identify_cpu_without_cpuid(c); - /* cyrix could have cpuid enabled via c_identify()*/ if (have_cpuid_p()) { cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); + setup_force_cpu_cap(X86_FEATURE_CPUID); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -818,6 +837,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); + } else { + identify_cpu_without_cpuid(c); + setup_clear_cpu_cap(X86_FEATURE_CPUID); } setup_force_cpu_cap(X86_FEATURE_ALWAYS); @@ -1015,6 +1037,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; c->x86_coreid_bits = 0; + c->cu_id = 0xff; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1034,10 +1057,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_identify(c); /* Clear/Set all flags overridden by options, after probe */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); #ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -1055,6 +1075,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) */ if (this_cpu->c_init) this_cpu->c_init(c); + else + clear_sched_clock_stable(); /* Disable the PN if appropriate */ squash_the_stupid_serial_number(c); @@ -1096,10 +1118,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overridden by options, need do it * before following smp all cpus cap AND. */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); /* * On SMP, boot_cpu_data holds the common feature set between @@ -1221,7 +1240,7 @@ static __init int setup_disablecpuid(char *arg) { int bit; - if (get_option(&arg, &bit) && bit < NCAPINTS*32) + if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32) setup_clear_cpu_cap(bit); else return 0; diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index bd9dcd6b712d..47416f959a48 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -9,6 +9,7 @@ #include <asm/pci-direct.h> #include <asm/tsc.h> #include <asm/cpufeature.h> +#include <linux/sched.h> #include "cpu.h" @@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); break; } + clear_sched_clock_stable(); } static void init_cyrix(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fcd484d2bb03..017ecd3bb553 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -14,6 +14,9 @@ #include <asm/bugs.h> #include <asm/cpu.h> #include <asm/intel-family.h> +#include <asm/microcode_intel.h> +#include <asm/hwcap2.h> +#include <asm/elf.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -61,6 +64,46 @@ void check_mpx_erratum(struct cpuinfo_x86 *c) } } +static bool ring3mwait_disabled __read_mostly; + +static int __init ring3mwait_disable(char *__unused) +{ + ring3mwait_disabled = true; + return 0; +} +__setup("ring3mwait=disable", ring3mwait_disable); + +static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) +{ + /* + * Ring 3 MONITOR/MWAIT feature cannot be detected without + * cpu model and family comparison. + */ + if (c->x86 != 6) + return; + switch (c->x86_model) { + case INTEL_FAM6_XEON_PHI_KNL: + case INTEL_FAM6_XEON_PHI_KNM: + break; + default: + return; + } + + if (ring3mwait_disabled) { + msr_clear_bit(MSR_MISC_FEATURE_ENABLES, + MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + return; + } + + msr_set_bit(MSR_MISC_FEATURE_ENABLES, + MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT); + + set_cpu_cap(c, X86_FEATURE_RING3MWAIT); + + if (c == &boot_cpu_data) + ELF_HWCAP2 |= HWCAP2_RING3MWAIT; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -78,14 +121,8 @@ static void early_init_intel(struct cpuinfo_x86 *c) (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); - if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) { - unsigned lower_word; - - wrmsr(MSR_IA32_UCODE_REV, 0, 0); - /* Required by the SDM */ - sync_core(); - rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode); - } + if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) + c->microcode = intel_get_microcode_revision(); /* * Atom erratum AAE44/AAF40/AAG38/AAH41: @@ -124,8 +161,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); - if (!check_tsc_unstable()) - set_sched_clock_stable(); + if (check_tsc_unstable()) + clear_sched_clock_stable(); + } else { + clear_sched_clock_stable(); } /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ @@ -565,6 +604,8 @@ static void init_intel(struct cpuinfo_x86 *c) detect_vmx_virtcap(c); init_intel_energy_perf(c); + + probe_xeon_phi_r3mwait(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index 83f1a98d37db..2eee85379689 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) if (severity >= GHES_SEV_RECOVERABLE) m.status |= MCI_STATUS_UC; - if (severity >= GHES_SEV_PANIC) + + if (severity >= GHES_SEV_PANIC) { m.status |= MCI_STATUS_PCC; + m.tsc = rdtsc(); + } m.addr = mem_err->physical_addr; mce_log(&m); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 93d824ec3120..1e5a50c11d3c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void) return new_head.first; } -void mce_gen_pool_process(void) +void mce_gen_pool_process(struct work_struct *__unused) { struct llist_node *head; struct mce_evt_llist *node, *tmp; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 517619ea6498..99165b206df3 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -152,7 +152,6 @@ static void raise_mce(struct mce *m) if (context == MCJ_CTX_RANDOM) return; -#ifdef CONFIG_X86_LOCAL_APIC if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -192,9 +191,7 @@ static void raise_mce(struct mce *m) raise_local(); put_cpu(); put_online_cpus(); - } else -#endif - { + } else { preempt_disable(); raise_local(); preempt_enable(); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index cd74a3f00aea..903043e6a62b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -31,7 +31,7 @@ struct mce_evt_llist { struct mce mce; }; -void mce_gen_pool_process(void); +void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..8e9725c607ea 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -128,7 +128,6 @@ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb) { atomic_inc(&num_notifiers); - /* Ensure SRAO notifier has the highest priority in the decode chain. */ - if (nb != &mce_srao_nb && nb->priority == INT_MAX) - nb->priority -= 1; + WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); } @@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, } static struct notifier_block mce_srao_nb = { .notifier_call = srao_decode_notifier, - .priority = INT_MAX, + .priority = MCE_PRIO_SRAO, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, static struct notifier_block mce_default_nb = { .notifier_call = mce_default_notifier, /* lowest prio, we want it to run last. */ - .priority = 0, + .priority = MCE_PRIO_LOWEST, }; /* @@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_gather_info(&m, NULL); - /* - * m.tsc was set in mce_setup(). Clear it if not requested. - * - * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid - * that dance. - */ - if (!(flags & MCP_TIMESTAMP)) - m.tsc = 0; + if (flags & MCP_TIMESTAMP) + m.tsc = rdtsc(); for (i = 0; i < mca_cfg.banks; i++) { if (!mce_banks[i].ctl || !test_bit(i, *b)) @@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) goto out; mce_gather_info(&m, regs); + m.tsc = rdtsc(); final = this_cpu_ptr(&mces_seen); *final = m; @@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags) #endif /* - * Action optional processing happens here (picking up - * from the list of faulting pages that do_machine_check() - * placed into the genpool). - */ -static void mce_process_work(struct work_struct *dummy) -{ - mce_gen_pool_process(); -} - -#ifdef CONFIG_X86_MCE_INTEL -/*** - * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog - * @cpu: The CPU on which the event occurred. - * @status: Event status information - * - * This function should be called by the thermal interrupt after the - * event has been processed and the decision was made to log the event - * further. - * - * The status parameter will be saved to the 'status' field of 'struct mce' - * and historically has been the register value of the - * MSR_IA32_THERMAL_STATUS (Intel) msr. - */ -void mce_log_therm_throt_event(__u64 status) -{ - struct mce m; - - mce_setup(&m); - m.bank = MCE_THERMAL_BANK; - m.status = status; - mce_log(&m); -} -#endif /* CONFIG_X86_MCE_INTEL */ - -/* * Periodic polling timer for "silent" machine check errors. If the * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). @@ -1373,20 +1330,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1373,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1384,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1731,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1756,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2196,7 +2146,7 @@ int __init mcheck_init(void) mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); - INIT_WORK(&mce_work, mce_process_work); + INIT_WORK(&mce_work, mce_gen_pool_process); init_irq_work(&mce_irq_work, mce_irq_work_cb); return 0; @@ -2566,7 +2516,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2527,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index a5fd137417a2..9e5427df3243 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank) smca_banks[bank].hwid = s_hwid; smca_banks[bank].id = instance_id; + smca_banks[bank].sysfs_id = s_hwid->count++; break; } } @@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) mce_setup(&m); m.status = status; - m.bank = bank; + m.bank = bank; + m.tsc = rdtsc(); if (threshold_err) m.misc = misc; @@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b) return NULL; } + if (smca_banks[bank].hwid->count == 1) + return smca_get_name(bank_type); + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "%s_%x", smca_get_name(bank_type), - smca_banks[bank].id); + smca_banks[bank].sysfs_id); return buf_mcatype; } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 465aca8be009..85469f84c921 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -6,7 +6,7 @@ * * Maintains a counter in /sys that keeps track of the number of thermal * events, such that the user knows how bad the thermal problem might be - * (since the logging to syslog and mcelog is rate limited). + * (since the logging to syslog is rate limited). * * Author: Dmitriy Zavin (dmitriyz@google.com) * @@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = { * IRQ has been acknowledged. * * It will take care of rate limiting and printing messages to the syslog. - * - * Returns: 0 : Event should NOT be further logged, i.e. still in - * "timeout" from previous log message. - * 1 : Event should be logged further, and a message has been - * printed to the syslog. */ -static int therm_throt_process(bool new_event, int event, int level) +static void therm_throt_process(bool new_event, int event, int level) { struct _thermal_state *state; unsigned int this_cpu = smp_processor_id(); @@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level) else if (event == POWER_LIMIT_EVENT) state = &pstate->core_power_limit; else - return 0; + return; } else if (level == PACKAGE_LEVEL) { if (event == THERMAL_THROTTLING_EVENT) state = &pstate->package_throttle; else if (event == POWER_LIMIT_EVENT) state = &pstate->package_power_limit; else - return 0; + return; } else - return 0; + return; old_event = state->new_event; state->new_event = new_event; @@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level) if (time_before64(now, state->next_check) && state->count != state->last_count) - return 0; + return; state->next_check = now + CHECK_INTERVAL; state->last_count = state->count; @@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - return 1; + return; } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - return 1; + return; } - - return 0; } static int thresh_event_valid(int level, int event) @@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void) /* Check for violation of core thermal thresholds*/ notify_thresholds(msr_val); - if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT, - THERMAL_THROTTLING_EVENT, - CORE_LEVEL) != 0) - mce_log_therm_throt_event(msr_val); + therm_throt_process(msr_val & THERM_STATUS_PROCHOT, + THERMAL_THROTTLING_EVENT, + CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..7889ae492af0 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -42,16 +42,19 @@ static struct equiv_cpu_entry *equiv_cpu_table; /* * This points to the current valid container of microcode patches which we will - * save from the initrd/builtin before jettisoning its contents. + * save from the initrd/builtin before jettisoning its contents. @mc is the + * microcode patch we found to match. */ -struct container { - u8 *data; - size_t size; -} cont; +struct cont_desc { + struct microcode_amd *mc; + u32 cpuid_1_eax; + u32 psize; + u8 *data; + size_t size; +}; static u32 ucode_new_rev; static u8 amd_ucode_patch[PATCH_MAX_SIZE]; -static u16 this_equiv_id; /* * Microcode patch container file is prepended to the initrd in cpio @@ -60,57 +63,13 @@ static u16 this_equiv_id; static const char ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin"; -static size_t compute_container_size(u8 *data, u32 total_size) +static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig) { - size_t size = 0; - u32 *header = (u32 *)data; - - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return size; - - size = header[2] + CONTAINER_HDR_SZ; - total_size -= size; - data += size; - - while (total_size) { - u16 patch_size; - - header = (u32 *)data; - - if (header[0] != UCODE_UCODE_TYPE) - break; - - /* - * Sanity-check patch size. - */ - patch_size = header[1]; - if (patch_size > PATCH_MAX_SIZE) - break; - - size += patch_size + SECTION_HDR_SIZE; - data += patch_size + SECTION_HDR_SIZE; - total_size -= patch_size + SECTION_HDR_SIZE; + for (; equiv_table && equiv_table->installed_cpu; equiv_table++) { + if (sig == equiv_table->installed_cpu) + return equiv_table->equiv_cpu; } - return size; -} - -static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, - unsigned int sig) -{ - int i = 0; - - if (!equiv_cpu_table) - return 0; - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (sig == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } return 0; } @@ -118,91 +77,109 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, * This scans the ucode blob for the proper container as we can have multiple * containers glued together. Returns the equivalence ID from the equivalence * table or 0 if none found. + * Returns the amount of bytes consumed while scanning. @desc contains all the + * data we're going to use in later stages of the application. */ -static u16 -find_proper_container(u8 *ucode, size_t size, struct container *ret_cont) +static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc) { - struct container ret = { NULL, 0 }; - u32 eax, ebx, ecx, edx; struct equiv_cpu_entry *eq; - int offset, left; - u16 eq_id = 0; - u32 *header; - u8 *data; + ssize_t orig_size = size; + u32 *hdr = (u32 *)ucode; + u16 eq_id; + u8 *buf; - data = ucode; - left = size; - header = (u32 *)data; + /* Am I looking at an equivalence table header? */ + if (hdr[0] != UCODE_MAGIC || + hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE || + hdr[2] == 0) + return CONTAINER_HDR_SZ; + buf = ucode; - /* find equiv cpu table */ - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return eq_id; + eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ); - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); + /* Find the equivalence ID of our CPU in this table: */ + eq_id = find_equiv_id(eq, desc->cpuid_1_eax); - while (left > 0) { - eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + buf += hdr[2] + CONTAINER_HDR_SZ; + size -= hdr[2] + CONTAINER_HDR_SZ; + + /* + * Scan through the rest of the container to find where it ends. We do + * some basic sanity-checking too. + */ + while (size > 0) { + struct microcode_amd *mc; + u32 patch_size; - ret.data = data; + hdr = (u32 *)buf; - /* Advance past the container header */ - offset = header[2] + CONTAINER_HDR_SZ; - data += offset; - left -= offset; + if (hdr[0] != UCODE_UCODE_TYPE) + break; - eq_id = find_equiv_id(eq, eax); - if (eq_id) { - ret.size = compute_container_size(ret.data, left + offset); + /* Sanity-check patch size. */ + patch_size = hdr[1]; + if (patch_size > PATCH_MAX_SIZE) + break; - /* - * truncate how much we need to iterate over in the - * ucode update loop below - */ - left = ret.size - offset; + /* Skip patch section header: */ + buf += SECTION_HDR_SIZE; + size -= SECTION_HDR_SIZE; - *ret_cont = ret; - return eq_id; + mc = (struct microcode_amd *)buf; + if (eq_id == mc->hdr.processor_rev_id) { + desc->psize = patch_size; + desc->mc = mc; } - /* - * support multiple container files appended together. if this - * one does not have a matching equivalent cpu entry, we fast - * forward to the next container file. - */ - while (left > 0) { - header = (u32 *)data; - - if (header[0] == UCODE_MAGIC && - header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) - break; - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } + buf += patch_size; + size -= patch_size; + } - /* mark where the next microcode container file starts */ - offset = data - (u8 *)ucode; - ucode = data; + /* + * If we have found a patch (desc->mc), it means we're looking at the + * container which has a patch for this CPU so return 0 to mean, @ucode + * already points to the proper container. Otherwise, we return the size + * we scanned so that we can advance to the next container in the + * buffer. + */ + if (desc->mc) { + desc->data = ucode; + desc->size = orig_size - size; + + return 0; } - return eq_id; + return orig_size - size; } -static int __apply_microcode_amd(struct microcode_amd *mc_amd) +/* + * Scan the ucode blob for the proper container as we can have multiple + * containers glued together. + */ +static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc) +{ + ssize_t rem = size; + + while (rem >= 0) { + ssize_t s = parse_container(ucode, rem, desc); + if (!s) + return; + + ucode += s; + rem -= s; + } +} + +static int __apply_microcode_amd(struct microcode_amd *mc) { u32 rev, dummy; - native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); + native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc->hdr.data_code); /* verify patch application was successful */ native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev != mc_amd->hdr.patch_id) + if (rev != mc->hdr.patch_id) return -1; return 0; @@ -217,17 +194,16 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. * - * Returns true if container found (sets @ret_cont), false otherwise. + * Returns true if container found (sets @desc), false otherwise. */ -static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, - struct container *ret_cont) +static bool +apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch) { + struct cont_desc desc = { 0 }; u8 (*patch)[PATCH_MAX_SIZE]; - u32 rev, *header, *new_rev; - struct container ret; - int offset, left; - u16 eq_id = 0; - u8 *data; + struct microcode_amd *mc; + u32 rev, dummy, *new_rev; + bool ret = false; #ifdef CONFIG_X86_32 new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); @@ -237,50 +213,27 @@ static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch, patch = &amd_ucode_patch; #endif - if (check_current_patch_level(&rev, true)) - return false; - - eq_id = find_proper_container(ucode, size, &ret); - if (!eq_id) - return false; - - this_equiv_id = eq_id; - header = (u32 *)ret.data; - - /* We're pointing to an equiv table, skip over it. */ - data = ret.data + header[2] + CONTAINER_HDR_SZ; - left = ret.size - (header[2] + CONTAINER_HDR_SZ); - - while (left > 0) { - struct microcode_amd *mc; - - header = (u32 *)data; - if (header[0] != UCODE_UCODE_TYPE || /* type */ - header[1] == 0) /* size */ - break; + desc.cpuid_1_eax = cpuid_1_eax; - mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); + scan_containers(ucode, size, &desc); - if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { + mc = desc.mc; + if (!mc) + return ret; - if (!__apply_microcode_amd(mc)) { - rev = mc->hdr.patch_id; - *new_rev = rev; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev >= mc->hdr.patch_id) + return ret; - if (save_patch) - memcpy(patch, mc, min_t(u32, header[1], PATCH_MAX_SIZE)); - } - } + if (!__apply_microcode_amd(mc)) { + *new_rev = mc->hdr.patch_id; + ret = true; - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; + if (save_patch) + memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE)); } - if (ret_cont) - *ret_cont = ret; - - return true; + return ret; } static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) @@ -298,10 +251,9 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) #endif } -void __init load_ucode_amd_bsp(unsigned int family) +void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; - u32 eax, ebx, ecx, edx; struct cpio_data cp; const char *path; bool use_pa; @@ -316,183 +268,95 @@ void __init load_ucode_amd_bsp(unsigned int family) use_pa = false; } - if (!get_builtin_microcode(&cp, family)) + if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax))) cp = find_microcode_in_initrd(path, use_pa); - if (!(cp.data && cp.size)) - return; - - /* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */ - eax = 1; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - uci->cpu_sig.sig = eax; + /* Needed in load_microcode_amd() */ + uci->cpu_sig.sig = cpuid_1_eax; - apply_microcode_early_amd(cp.data, cp.size, true, NULL); + *ret = cp; } -#ifdef CONFIG_X86_32 -/* - * On 32-bit, since AP's early load occurs before paging is turned on, we - * cannot traverse cpu_equiv_table and microcode_cache in kernel heap memory. - * So during cold boot, AP will apply_ucode_in_initrd() just like the BSP. - * In save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, - * which is used upon resume from suspend. - */ -void load_ucode_amd_ap(unsigned int family) +void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) { - struct microcode_amd *mc; - struct cpio_data cp; - - mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); - if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { - __apply_microcode_amd(mc); - return; - } - - if (!get_builtin_microcode(&cp, family)) - cp = find_microcode_in_initrd((const char *)__pa_nodebug(ucode_path), true); + struct cpio_data cp = { }; + __load_ucode_amd(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; - /* - * This would set amd_ucode_patch above so that the following APs can - * use it directly instead of going down this path again. - */ - apply_microcode_early_amd(cp.data, cp.size, true, NULL); + apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true); } -#else -void load_ucode_amd_ap(unsigned int family) + +void load_ucode_amd_ap(unsigned int cpuid_1_eax) { - struct equiv_cpu_entry *eq; struct microcode_amd *mc; - u32 rev, eax; - u16 eq_id; - - /* 64-bit runs with paging enabled, thus early==false. */ - if (check_current_patch_level(&rev, false)) - return; - - /* First AP hasn't cached it yet, go through the blob. */ - if (!cont.data) { - struct cpio_data cp = { NULL, 0, "" }; + struct cpio_data cp; + u32 *new_rev, rev, dummy; - if (cont.size == -1) - return; + if (IS_ENABLED(CONFIG_X86_32)) { + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); + new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); + } else { + mc = (struct microcode_amd *)amd_ucode_patch; + new_rev = &ucode_new_rev; + } -reget: - if (!get_builtin_microcode(&cp, family)) { -#ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); -#endif - if (!(cp.data && cp.size)) { - /* - * Mark it so that other APs do not scan again - * for no real reason and slow down boot - * needlessly. - */ - cont.size = -1; - return; - } - } + native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) { - cont.size = -1; + /* Check whether we have saved a new patch already: */ + if (*new_rev && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + *new_rev = mc->hdr.patch_id; return; } } - eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(cont.data + CONTAINER_HDR_SZ); - - eq_id = find_equiv_id(eq, eax); - if (!eq_id) + __load_ucode_amd(cpuid_1_eax, &cp); + if (!(cp.data && cp.size)) return; - if (eq_id == this_equiv_id) { - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) - ucode_new_rev = mc->hdr.patch_id; - } - - } else { - - /* - * AP has a different equivalence ID than BSP, looks like - * mixed-steppings silicon so go through the ucode blob anew. - */ - goto reget; - } + apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false); } -#endif /* CONFIG_X86_32 */ static enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); -int __init save_microcode_in_initrd_amd(unsigned int fam) +int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { + struct cont_desc desc = { 0 }; enum ucode_state ret; - int retval = 0; - u16 eq_id; - - if (!cont.data) { - if (IS_ENABLED(CONFIG_X86_32) && (cont.size != -1)) { - struct cpio_data cp = { NULL, 0, "" }; - -#ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); -#endif + struct cpio_data cp; - if (!(cp.data && cp.size)) { - cont.size = -1; - return -EINVAL; - } + cp = find_microcode_in_initrd(ucode_path, false); + if (!(cp.data && cp.size)) + return -EINVAL; - eq_id = find_proper_container(cp.data, cp.size, &cont); - if (!eq_id) { - cont.size = -1; - return -EINVAL; - } + desc.cpuid_1_eax = cpuid_1_eax; - } else - return -EINVAL; - } + scan_containers(cp.data, cp.size, &desc); + if (!desc.mc) + return -EINVAL; - ret = load_microcode_amd(smp_processor_id(), fam, cont.data, cont.size); + ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax), + desc.data, desc.size); if (ret != UCODE_OK) - retval = -EINVAL; - - /* - * This will be freed any msec now, stash patches for the current - * family and switch to patch cache for cpu hotplug, etc later. - */ - cont.data = NULL; - cont.size = 0; + return -EINVAL; - return retval; + return 0; } void reload_ucode_amd(void) { struct microcode_amd *mc; - u32 rev; - - /* - * early==false because this is a syscore ->resume path and by - * that time paging is long enabled. - */ - if (check_current_patch_level(&rev, false)) - return; + u32 rev, dummy; mc = (struct microcode_amd *)amd_ucode_patch; if (!mc) return; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev < mc->hdr.patch_id) { if (!__apply_microcode_amd(mc)) { ucode_new_rev = mc->hdr.patch_id; @@ -630,60 +494,13 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -/* - * Those patch levels cannot be updated to newer ones and thus should be final. - */ -static u32 final_levels[] = { - 0x01000098, - 0x0100009f, - 0x010000af, - 0, /* T-101 terminator */ -}; - -/* - * Check the current patch level on this CPU. - * - * @rev: Use it to return the patch level. It is set to 0 in the case of - * error. - * - * Returns: - * - true: if update should stop - * - false: otherwise - */ -bool check_current_patch_level(u32 *rev, bool early) -{ - u32 lvl, dummy, i; - bool ret = false; - u32 *levels; - - native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); - - if (IS_ENABLED(CONFIG_X86_32) && early) - levels = (u32 *)__pa_nodebug(&final_levels); - else - levels = final_levels; - - for (i = 0; levels[i]; i++) { - if (lvl == levels[i]) { - lvl = 0; - ret = true; - break; - } - } - - if (rev) - *rev = lvl; - - return ret; -} - static int apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; - u32 rev; + u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -696,8 +513,7 @@ static int apply_microcode_amd(int cpu) mc_amd = p->data; uci->mc = p->data; - if (check_current_patch_level(&rev, false)) - return -1; + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..b4a4cd39b358 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -64,19 +66,50 @@ static DEFINE_MUTEX(microcode_mutex); struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; -/* - * Operations that are run on a target cpu: - */ - struct cpu_info_ctx { struct cpu_signature *cpu_sig; int err; }; +/* + * Those patch levels cannot be updated to newer ones and thus should be final. + */ +static u32 final_levels[] = { + 0x01000098, + 0x0100009f, + 0x010000af, + 0, /* T-101 terminator */ +}; + +/* + * Check the current patch level on this CPU. + * + * Returns: + * - true: if update should stop + * - false: otherwise + */ +static bool amd_check_current_patch_level(void) +{ + u32 lvl, dummy, i; + u32 *levels; + + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); + + if (IS_ENABLED(CONFIG_X86_32)) + levels = (u32 *)__pa_nodebug(&final_levels); + else + levels = final_levels; + + for (i = 0; levels[i]; i++) { + if (lvl == levels[i]) + return true; + } + return false; +} + static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; - u32 a, b, c, d; #ifdef CONFIG_X86_32 const char *cmdline = (const char *)__pa_nodebug(boot_command_line); @@ -92,18 +125,19 @@ static bool __init check_loader_disabled_bsp(void) if (!have_cpuid_p()) return *res; - a = 1; - c = 0; - native_cpuid(&a, &b, &c, &d); - /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not * completely accurate as xen pv guests don't see that CPUID bit set but * that's good enough as they don't land on the BSP path anyway. */ - if (c & BIT(31)) + if (native_cpuid_ecx(1) & BIT(31)) return *res; + if (x86_cpuid_vendor() == X86_VENDOR_AMD) { + if (amd_check_current_patch_level()) + return *res; + } + if (cmdline_find_option_bool(cmdline, option) <= 0) *res = false; @@ -131,23 +165,21 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name) void __init load_ucode_bsp(void) { - int vendor; - unsigned int family; + unsigned int cpuid_1_eax; if (check_loader_disabled_bsp()) return; - vendor = x86_cpuid_vendor(); - family = x86_cpuid_family(); + cpuid_1_eax = native_cpuid_eax(1); - switch (vendor) { + switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (family >= 6) + if (x86_family(cpuid_1_eax) >= 6) load_ucode_intel_bsp(); break; case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(family); + if (x86_family(cpuid_1_eax) >= 0x10) + load_ucode_amd_bsp(cpuid_1_eax); break; default: break; @@ -165,22 +197,21 @@ static bool check_loader_disabled_ap(void) void load_ucode_ap(void) { - int vendor, family; + unsigned int cpuid_1_eax; if (check_loader_disabled_ap()) return; - vendor = x86_cpuid_vendor(); - family = x86_cpuid_family(); + cpuid_1_eax = native_cpuid_eax(1); - switch (vendor) { + switch (x86_cpuid_vendor()) { case X86_VENDOR_INTEL: - if (family >= 6) + if (x86_family(cpuid_1_eax) >= 6) load_ucode_intel_ap(); break; case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_ap(family); + if (x86_family(cpuid_1_eax) >= 0x10) + load_ucode_amd_ap(cpuid_1_eax); break; default: break; @@ -190,21 +221,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + return save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +281,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index b624b54912e1..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -150,7 +150,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) { struct ucode_patch *p; - p = kzalloc(size, GFP_KERNEL); + p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -368,26 +368,6 @@ next: return patch; } -static void cpuid_1(void) -{ - /* - * According to the Intel SDM, Volume 3, 9.11.7: - * - * CPUID returns a value in a model specific register in - * addition to its usual register return values. The - * semantics of CPUID cause it to deposit an update ID value - * in the 64-bit model-specific register at address 08BH - * (IA32_BIOS_SIGN_ID). If no update is present in the - * processor, the value in the MSR remains unmodified. - * - * Use native_cpuid -- this code runs very early and we don't - * want to mess with paravirt. - */ - unsigned int eax = 1, ebx, ecx = 0, edx; - - native_cpuid(&eax, &ebx, &ecx, &edx); -} - static int collect_cpu_info_early(struct ucode_cpu_info *uci) { unsigned int val[2]; @@ -410,15 +390,8 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); csig.pf = 1 << ((val[1] >> 18) & 7); } - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - csig.rev = val[1]; + csig.rev = intel_get_microcode_revision(); uci->cpu_sig = csig; uci->valid = 1; @@ -602,7 +575,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci) static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) { struct microcode_intel *mc; - unsigned int val[2]; + u32 rev; mc = uci->mc; if (!mc) @@ -610,21 +583,16 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - native_wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc->hdr.rev) + rev = intel_get_microcode_revision(); + if (rev != mc->hdr.rev) return -1; #ifdef CONFIG_X86_64 /* Flush global tlb. This is precaution. */ flush_tlb_early(); #endif - uci->cpu_sig.rev = val[1]; + uci->cpu_sig.rev = rev; if (early) print_ucode(uci); @@ -639,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -660,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ @@ -804,8 +765,8 @@ static int apply_microcode_intel(int cpu) struct microcode_intel *mc; struct ucode_cpu_info *uci; struct cpuinfo_x86 *c; - unsigned int val[2]; static int prev_rev; + u32 rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) @@ -822,33 +783,28 @@ static int apply_microcode_intel(int cpu) /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); - wrmsrl(MSR_IA32_UCODE_REV, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - cpuid_1(); - /* get the current revision from MSR 0x8B */ - rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + rev = intel_get_microcode_revision(); - if (val[1] != mc->hdr.rev) { + if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); return -1; } - if (val[1] != prev_rev) { + if (rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", - val[1], + rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, (mc->hdr.date >> 16) & 0xff); - prev_rev = val[1]; + prev_rev = rev; } c = &cpu_data(cpu); - uci->cpu_sig.rev = val[1]; - c->microcode = val[1]; + uci->cpu_sig.rev = rev; + c->microcode = rev; return 0; } @@ -860,7 +816,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL; int new_rev = uci->cpu_sig.rev; unsigned int leftover = size; - unsigned int curr_mc_size = 0; + unsigned int curr_mc_size = 0, new_mc_size = 0; unsigned int csig, cpf; while (leftover) { @@ -901,6 +857,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; + new_mc_size = mc_size; mc = NULL; /* trigger new vmalloc */ } @@ -926,7 +883,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, * permanent memory. So it will be loaded early when a CPU is hot added * or resumes. */ - save_mc_for_early(new_mc, curr_mc_size); + save_mc_for_early(new_mc, new_mc_size); pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 65e20c97e04b..b5375b9497b3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -133,26 +133,6 @@ static uint32_t __init ms_hyperv_platform(void) return 0; } -static u64 read_hv_clock(struct clocksource *arg) -{ - u64 current_tick; - /* - * Read the partition counter to get the current tick count. This count - * is set to 0 when the partition is created and is incremented in - * 100 nanosecond units. - */ - rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); - return current_tick; -} - -static struct clocksource hyperv_cs = { - .name = "hyperv_clocksource", - .rating = 400, /* use this when running on Hyperv*/ - .read = read_hv_clock, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - static unsigned char hv_get_nmi_reason(void) { return 0; @@ -180,6 +160,11 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) static void __init ms_hyperv_init_platform(void) { + int hv_host_info_eax; + int hv_host_info_ebx; + int hv_host_info_ecx; + int hv_host_info_edx; + /* * Extract the features and hints */ @@ -190,6 +175,21 @@ static void __init ms_hyperv_init_platform(void) pr_info("HyperV: features 0x%x, hints 0x%x\n", ms_hyperv.features, ms_hyperv.hints); + /* + * Extract host information. + */ + if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) { + hv_host_info_eax = cpuid_eax(HVCPUID_VERSION); + hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION); + hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION); + hv_host_info_edx = cpuid_edx(HVCPUID_VERSION); + + pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n", + hv_host_info_eax, hv_host_info_ebx >> 16, + hv_host_info_ebx & 0xFFFF, hv_host_info_ecx, + hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF); + } + #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { /* @@ -208,9 +208,6 @@ static void __init ms_hyperv_init_platform(void) "hv_nmi_unknown"); #endif - if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) - clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); - #ifdef CONFIG_X86_IO_APIC no_timer_check = 1; #endif @@ -227,6 +224,13 @@ static void __init ms_hyperv_init_platform(void) */ if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + +#if IS_ENABLED(CONFIG_HYPERV) + /* + * Setup the hook to get control post apic initialization. + */ + x86_platform.apic_post_init = hyperv_init; +#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 34178564be2a..c1ea5b999839 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -1,4 +1,5 @@ #include <linux/kernel.h> +#include <linux/sched.h> #include <linux/mm.h> #include <asm/cpufeature.h> #include <asm/msr.h> @@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) if (xlvl >= 0x80860001) c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } + + clear_sched_clock_stable(); } static void init_transmeta(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 90e8dde3ec26..b2bbad6ebe4d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -580,24 +580,19 @@ static void __init update_e820_saved(void) } #define MAX_GAP_END 0x100000000ull /* - * Search for a gap in the e820 memory space from start_addr to end_addr. + * Search for a gap in the e820 memory space from 0 to MAX_GAP_END. */ -__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr, unsigned long long end_addr) +static int __init e820_search_gap(unsigned long *gapstart, + unsigned long *gapsize) { - unsigned long long last; + unsigned long long last = MAX_GAP_END; int i = e820->nr_map; int found = 0; - last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END; - while (--i >= 0) { unsigned long long start = e820->map[i].addr; unsigned long long end = start + e820->map[i].size; - if (end < start_addr) - continue; - /* * Since "last" is at most 4GB, we know we'll * fit in 32 bits if this condition is true @@ -628,18 +623,19 @@ __init void e820_setup_gap(void) unsigned long gapstart, gapsize; int found; - gapstart = 0x10000000; gapsize = 0x400000; - found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END); + found = e820_search_gap(&gapstart, &gapsize); -#ifdef CONFIG_X86_64 if (!found) { +#ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; printk(KERN_ERR "e820: cannot find a gap in the 32bit address range\n" "e820: PCI devices with unassigned 32bit BARs may break!\n"); - } +#else + gapstart = 0x10000000; #endif + } /* * e820_reserve_resources_late protect stolen RAM already diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..e1114f070c2d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -178,13 +178,8 @@ void fpstate_init(union fpregs_state *state) memset(state, 0, fpu_kernel_xstate_size); - /* - * XRSTORS requires that this bit is set in xcomp_bv, or - * it will #GP. Make sure it is replaced after the memset(). - */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; - + fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 60dece392b3a..19bdd1bf8160 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -48,13 +48,7 @@ void fpu__init_cpu(void) fpu__init_cpu_xstate(); } -/* - * The earliest FPU detection code. - * - * Set the X86_FEATURE_FPU CPU-capability bit based on - * trying to execute an actual sequence of FPU instructions: - */ -static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +static bool fpu__probe_without_cpuid(void) { unsigned long cr0; u16 fsw, fcw; @@ -65,18 +59,25 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw)); + + pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); + return fsw == 0 && (fcw & 0x103f) == 0x003f; +} + +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + if (!boot_cpu_has(X86_FEATURE_CPUID) && + !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + if (fpu__probe_without_cpuid()) + setup_force_cpu_cap(X86_FEATURE_FPU); else - clear_cpu_cap(c, X86_FEATURE_FPU); + setup_clear_cpu_cap(X86_FEATURE_FPU); } #ifndef CONFIG_MATH_EMULATION - if (!boot_cpu_has(X86_FEATURE_FPU)) { + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) { pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); for (;;) asm volatile("hlt"); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1d7770447b3e..c24ac1efb12d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -78,6 +78,7 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_PKU); setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); + setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ); } /* @@ -705,8 +706,14 @@ void __init fpu__init_system_xstate(void) WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; + if (!boot_cpu_has(X86_FEATURE_FPU)) { + pr_info("x86/fpu: No FPU detected\n"); + return; + } + if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + pr_info("x86/fpu: x87 FPU will use %s\n", + boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE"); return; } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index f16c55bfc090..e5fb436a6548 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -49,3 +49,65 @@ asmlinkage __visible void __init i386_start_kernel(void) start_kernel(); } + +/* + * Initialize page tables. This creates a PDE and a set of page + * tables, which are located immediately beyond __brk_base. The variable + * _brk_end is set up to point to the first "safe" location. + * Mappings are created both at virtual address 0 (identity mapping) + * and PAGE_OFFSET for up to _end. + * + * In PAE mode initial_page_table is statically defined to contain + * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3 + * entries). The identity mapping is handled by pointing two PGD entries + * to the first kernel PMD. Note the upper half of each PMD or PTE are + * always zero at this stage. + */ +void __init mk_early_pgtbl_32(void) +{ +#ifdef __pa +#undef __pa +#endif +#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET) + pte_t pte, *ptep; + int i; + unsigned long *ptr; + /* Enough space to fit pagetables for the low memory linear map */ + const unsigned long limit = __pa(_end) + + (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); +#ifdef CONFIG_X86_PAE + pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd); +#define SET_PL2(pl2, val) { (pl2).pmd = (val); } +#else + pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table); +#define SET_PL2(pl2, val) { (pl2).pgd = (val); } +#endif + + ptep = (pte_t *)__pa(__brk_base); + pte.pte = PTE_IDENT_ATTR; + + while ((pte.pte & PTE_PFN_MASK) < limit) { + + SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR); + *pl2p = pl2; +#ifndef CONFIG_X86_PAE + /* Kernel PDE entry */ + *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; +#endif + for (i = 0; i < PTRS_PER_PTE; i++) { + *ptep = pte; + pte.pte += PAGE_SIZE; + ptep++; + } + + pl2p++; + } + + ptr = (unsigned long *)__pa(&max_pfn_mapped); + /* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */ + *ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; + + ptr = (unsigned long *)__pa(&_brk_end); + *ptr = (unsigned long)ptep + PAGE_OFFSET; +} + diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 4e8577d03372..1f85ee8f9439 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -24,6 +24,7 @@ #include <asm/nops.h> #include <asm/bootparam.h> #include <asm/export.h> +#include <asm/pgtable_32.h> /* Physical address */ #define pa(X) ((X) - __PAGE_OFFSET) @@ -41,44 +42,10 @@ #define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability #define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id -/* - * This is how much memory in addition to the memory covered up to - * and including _end we need mapped initially. - * We need: - * (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE) - * (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE) - * - * Modulo rounding, each megabyte assigned here requires a kilobyte of - * memory, which is currently unreclaimed. - * - * This should be a multiple of a page. - * - * KERNEL_IMAGE_SIZE should be greater than pa(_end) - * and small than max_low_pfn, otherwise will waste some page table entries - */ - -#if PTRS_PER_PMD > 1 -#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) -#else -#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) -#endif #define SIZEOF_PTREGS 17*4 /* - * Number of possible pages in the lowmem region. - * - * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a - * gas warning about overflowing shift count when gas has been compiled - * with only a host target support using a 32-bit type for internal - * representation. - */ -LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT) - -/* Enough space to fit pagetables for the low memory linear map */ -MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT - -/* * Worst-case size of the kernel mapping we need to make: * a relocatable kernel can live anywhere in lowmem, so we need to be able * to map all of lowmem. @@ -160,90 +127,15 @@ ENTRY(startup_32) call load_ucode_bsp #endif -/* - * Initialize page tables. This creates a PDE and a set of page - * tables, which are located immediately beyond __brk_base. The variable - * _brk_end is set up to point to the first "safe" location. - * Mappings are created both at virtual address 0 (identity mapping) - * and PAGE_OFFSET for up to _end. - */ -#ifdef CONFIG_X86_PAE - - /* - * In PAE mode initial_page_table is statically defined to contain - * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3 - * entries). The identity mapping is handled by pointing two PGD entries - * to the first kernel PMD. - * - * Note the upper half of each PMD or PTE are always zero at this stage. - */ - -#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ - - xorl %ebx,%ebx /* %ebx is kept at zero */ - - movl $pa(__brk_base), %edi - movl $pa(initial_pg_pmd), %edx - movl $PTE_IDENT_ATTR, %eax -10: - leal PDE_IDENT_ATTR(%edi),%ecx /* Create PMD entry */ - movl %ecx,(%edx) /* Store PMD entry */ - /* Upper half already zero */ - addl $8,%edx - movl $512,%ecx -11: - stosl - xchgl %eax,%ebx - stosl - xchgl %eax,%ebx - addl $0x1000,%eax - loop 11b - - /* - * End condition: we must map up to the end + MAPPING_BEYOND_END. - */ - movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp - cmpl %ebp,%eax - jb 10b -1: - addl $__PAGE_OFFSET, %edi - movl %edi, pa(_brk_end) - shrl $12, %eax - movl %eax, pa(max_pfn_mapped) + /* Create early pagetables. */ + call mk_early_pgtbl_32 /* Do early initialization of the fixmap area */ movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax +#ifdef CONFIG_X86_PAE +#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */ movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8) -#else /* Not PAE */ - -page_pde_offset = (__PAGE_OFFSET >> 20); - - movl $pa(__brk_base), %edi - movl $pa(initial_page_table), %edx - movl $PTE_IDENT_ATTR, %eax -10: - leal PDE_IDENT_ATTR(%edi),%ecx /* Create PDE entry */ - movl %ecx,(%edx) /* Store identity PDE entry */ - movl %ecx,page_pde_offset(%edx) /* Store kernel PDE entry */ - addl $4,%edx - movl $1024, %ecx -11: - stosl - addl $0x1000,%eax - loop 11b - /* - * End condition: we must map up to the end + MAPPING_BEYOND_END. - */ - movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp - cmpl %ebp,%eax - jb 10b - addl $__PAGE_OFFSET, %edi - movl %edi, pa(_brk_end) - shrl $12, %eax - movl %eax, pa(max_pfn_mapped) - - /* Do early initialization of the fixmap area */ - movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax +#else movl %eax,pa(initial_page_table+0xffc) #endif @@ -666,6 +558,7 @@ ENTRY(setup_once_ref) __PAGE_ALIGNED_BSS .align PAGE_SIZE #ifdef CONFIG_X86_PAE +.globl initial_pg_pmd initial_pg_pmd: .fill 1024*KPMDS,4,0 #else diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 85e87b46c318..dc6ba5bda9fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 589b3193f102..b01bc8517450 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <linux/bitmap.h> #include <asm/syscalls.h> +#include <asm/desc.h> /* * this changes the io permissions bitmap in the current task. @@ -45,6 +46,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) memset(bitmap, 0xff, IO_BITMAP_BYTES); t->io_bitmap_ptr = bitmap; set_thread_flag(TIF_IO_BITMAP); + + preempt_disable(); + refresh_TR(); + preempt_enable(); } /* diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index cb9c1ed1d391..f73f475d0573 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -132,10 +132,8 @@ int sched_set_itmt_support(void) sysctl_sched_itmt_enabled = 1; - if (sysctl_sched_itmt_enabled) { - x86_topology_update = true; - rebuild_sched_domains(); - } + x86_topology_update = true; + rebuild_sched_domains(); mutex_unlock(&itmt_update_mutex); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index fc25f698d792..c37bd0f39c70 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line) * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ - pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n", - ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line); + pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line); BUG(); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index eb3509338ae0..520b8dfe1640 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs) * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ - hlist_for_each_entry_safe(ri, tmp, head, hlist) { + hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 36bc66416021..14f65a5f938e 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -589,7 +589,8 @@ out: local_irq_restore(flags); } -__visible bool __kvm_vcpu_is_preempted(int cpu) +#ifdef CONFIG_X86_32 +__visible bool __kvm_vcpu_is_preempted(long cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); @@ -597,6 +598,29 @@ __visible bool __kvm_vcpu_is_preempted(int cpu) } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); +#else + +#include <asm/asm-offsets.h> + +extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); + +/* + * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and + * restoring to/from the stack. + */ +asm( +".pushsection .text;" +".global __raw_callee_save___kvm_vcpu_is_preempted;" +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" +"__raw_callee_save___kvm_vcpu_is_preempted:" +"movq __per_cpu_offset(,%rdi,8), %rax;" +"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" +"setne %al;" +"ret;" +".popsection"); + +#endif + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -620,18 +644,4 @@ void __init kvm_spinlock_init(void) } } -static __init int kvm_spinlock_init_jump(void) -{ - if (!kvm_para_available()) - return 0; - if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - - return 0; -} -early_initcall(kvm_spinlock_init_jump); - #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2a5cafdf8808..bae6ea6cfb94 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> +#include <asm/kvmclock.h> static int kvmclock __ro_after_init = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; @@ -49,6 +50,7 @@ struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) { return hv_clock; } +EXPORT_SYMBOL_GPL(pvclock_pvti_cpu0_va); /* * The wallclock is the time of day when we booted. Since then, some time may @@ -107,12 +109,12 @@ static inline void kvm_sched_clock_init(bool stable) { if (!stable) { pv_time_ops.sched_clock = kvm_clock_read; + clear_sched_clock_stable(); return; } kvm_sched_clock_offset = kvm_clock_read(); pv_time_ops.sched_clock = kvm_sched_clock_read; - set_sched_clock_stable(); printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", kvm_sched_clock_offset); @@ -174,13 +176,14 @@ bool kvm_check_and_clear_guest_paused(void) return ret; } -static struct clocksource kvm_clock = { +struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +EXPORT_SYMBOL_GPL(kvm_clock); int kvm_register_clock(char *txt) { diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 6d4bf812af45..8f2d1c9d43a8 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -20,7 +20,7 @@ bool pv_is_native_spin_unlock(void) __raw_callee_save___native_queued_spin_unlock; } -__visible bool __native_vcpu_is_preempted(int cpu) +__visible bool __native_vcpu_is_preempted(long cpu) { return false; } @@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = { #endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); - -struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; -EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index a1bfba0f7234..4797e87b0fb6 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -425,6 +425,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .pmd_clear = native_pmd_clear, #endif .set_pud = native_set_pud, + .set_pud_at = native_set_pud_at, .pmd_val = PTE_IDENT, .make_pmd = PTE_IDENT, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 5070320780c6..0c150c06fa5a 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, /* were we called with bad_dma_address? */ badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE); - if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) { + if (unlikely(dma_addr < badend)) { WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); return; diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 76f4c039baae..3a216ec869cd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -91,7 +91,8 @@ again: page = NULL; /* CMA can be used only in the context which permits sleeping */ if (gfpflags_allow_blocking(flag)) { - page = dma_alloc_from_contiguous(dev, count, get_order(size)); + page = dma_alloc_from_contiguous(dev, count, get_order(size), + flag); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); page = NULL; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b615a1113f58..7780efa635b9 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -32,6 +32,7 @@ #include <asm/mce.h> #include <asm/vm86.h> #include <asm/switch_to.h> +#include <asm/desc.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -64,6 +65,9 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { }; EXPORT_PER_CPU_SYMBOL(cpu_tss); +DEFINE_PER_CPU(bool, need_tr_refresh); +EXPORT_PER_CPU_SYMBOL_GPL(need_tr_refresh); + /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. @@ -209,6 +213,12 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); + + /* + * Make sure that the TSS limit is correct for the CPU + * to notice the IO bitmap. + */ + refresh_TR(); } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { /* * Clear any possible leftover bits: diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4cfba947d774..69780edf0dde 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1176,6 +1176,20 @@ void __init setup_arch(char **cmdline_p) /* Allocate bigger log buffer */ setup_log_buf(1); + if (efi_enabled(EFI_BOOT)) { + switch (boot_params.secure_boot) { + case efi_secureboot_mode_disabled: + pr_info("Secure boot disabled\n"); + break; + case efi_secureboot_mode_enabled: + pr_info("Secure boot enabled\n"); + break; + default: + pr_info("Secure boot could not be determined\n"); + break; + } + } + reserve_initrd(); acpi_table_upgrade(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 46732dc3b73c..a0d38685f7df 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && - c->cpu_core_id == o->cpu_core_id) - return topology_sane(c, o, "smt"); + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { + if (c->cpu_core_id == o->cpu_core_id) + return topology_sane(c, o, "smt"); + + if ((c->cu_id != 0xff) && + (o->cu_id != 0xff) && + (c->cu_id == o->cu_id)) + return topology_sane(c, o, "smt"); + } } else if (c->phys_proc_id == o->phys_proc_id && c->cpu_core_id == o->cpu_core_id) { @@ -1341,8 +1347,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) pr_info("CPU0: "); print_cpu_info(&cpu_data(0)); - if (is_uv_system()) - uv_system_init(); + uv_system_init(); set_mtrr_aps_delayed_init(); diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c deleted file mode 100644 index a3b875c9e6af..000000000000 --- a/arch/x86/kernel/test_nx.c +++ /dev/null @@ -1,173 +0,0 @@ -/* - * test_nx.c: functional test for NX functionality - * - * (C) Copyright 2008 Intel Corporation - * Author: Arjan van de Ven <arjan@linux.intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#include <linux/module.h> -#include <linux/sort.h> -#include <linux/slab.h> - -#include <linux/uaccess.h> -#include <asm/asm.h> - -extern int rodata_test_data; - -/* - * This file checks 4 things: - * 1) Check if the stack is not executable - * 2) Check if kmalloc memory is not executable - * 3) Check if the .rodata section is not executable - * 4) Check if the .data section of a module is not executable - * - * To do this, the test code tries to execute memory in stack/kmalloc/etc, - * and then checks if the expected trap happens. - * - * Sadly, this implies having a dynamic exception handling table entry. - * ... which can be done (and will make Rusty cry)... but it can only - * be done in a stand-alone module with only 1 entry total. - * (otherwise we'd have to sort and that's just too messy) - */ - - - -/* - * We want to set up an exception handling point on our stack, - * which means a variable value. This function is rather dirty - * and walks the exception table of the module, looking for a magic - * marker and replaces it with a specific function. - */ -static void fudze_exception_table(void *marker, void *new) -{ - struct module *mod = THIS_MODULE; - struct exception_table_entry *extable; - - /* - * Note: This module has only 1 exception table entry, - * so searching and sorting is not needed. If that changes, - * this would be the place to search and re-sort the exception - * table. - */ - if (mod->num_exentries > 1) { - printk(KERN_ERR "test_nx: too many exception table entries!\n"); - printk(KERN_ERR "test_nx: test results are not reliable.\n"); - return; - } - extable = (struct exception_table_entry *)mod->extable; - extable[0].insn = (unsigned long)new; -} - - -/* - * exception tables get their symbols translated so we need - * to use a fake function to put in there, which we can then - * replace at runtime. - */ -void foo_label(void); - -/* - * returns 0 for not-executable, negative for executable - * - * Note: we cannot allow this function to be inlined, because - * that would give us more than 1 exception table entry. - * This in turn would break the assumptions above. - */ -static noinline int test_address(void *address) -{ - unsigned long result; - - /* Set up an exception table entry for our address */ - fudze_exception_table(&foo_label, address); - result = 1; - asm volatile( - "foo_label:\n" - "0: call *%[fake_code]\n" - "1:\n" - ".section .fixup,\"ax\"\n" - "2: mov %[zero], %[rslt]\n" - " ret\n" - ".previous\n" - _ASM_EXTABLE(0b,2b) - : [rslt] "=r" (result) - : [fake_code] "r" (address), [zero] "r" (0UL), "0" (result) - ); - /* change the exception table back for the next round */ - fudze_exception_table(address, &foo_label); - - if (result) - return -ENODEV; - return 0; -} - -static unsigned char test_data = 0xC3; /* 0xC3 is the opcode for "ret" */ - -static int test_NX(void) -{ - int ret = 0; - /* 0xC3 is the opcode for "ret" */ - char stackcode[] = {0xC3, 0x90, 0 }; - char *heap; - - test_data = 0xC3; - - printk(KERN_INFO "Testing NX protection\n"); - - /* Test 1: check if the stack is not executable */ - if (test_address(&stackcode)) { - printk(KERN_ERR "test_nx: stack was executable\n"); - ret = -ENODEV; - } - - - /* Test 2: Check if the heap is executable */ - heap = kmalloc(64, GFP_KERNEL); - if (!heap) - return -ENOMEM; - heap[0] = 0xC3; /* opcode for "ret" */ - - if (test_address(heap)) { - printk(KERN_ERR "test_nx: heap was executable\n"); - ret = -ENODEV; - } - kfree(heap); - - /* - * The following 2 tests currently fail, this needs to get fixed - * Until then, don't run them to avoid too many people getting scared - * by the error message - */ - - /* Test 3: Check if the .rodata section is executable */ - if (rodata_test_data != 0xC3) { - printk(KERN_ERR "test_nx: .rodata marker has invalid value\n"); - ret = -ENODEV; - } else if (test_address(&rodata_test_data)) { - printk(KERN_ERR "test_nx: .rodata section is executable\n"); - ret = -ENODEV; - } - -#if 0 - /* Test 4: Check if the .data section of a module is executable */ - if (test_address(&test_data)) { - printk(KERN_ERR "test_nx: .data section is executable\n"); - ret = -ENODEV; - } - -#endif - return ret; -} - -static void test_exit(void) -{ -} - -module_init(test_NX); -module_exit(test_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Testcase for the NX infrastructure"); -MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bf0c6d049080..1dc86ee60a03 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -563,11 +563,9 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - preempt_disable(); cond_local_irq_enable(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); exit: ist_exit(regs); @@ -742,14 +740,12 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - preempt_disable(); cond_local_irq_enable(regs); if (v8086_mode(regs)) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); goto exit; } @@ -769,7 +765,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); cond_local_irq_disable(regs); - preempt_enable_no_resched(); debug_stack_usage_dec(); exit: diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index be3a49ee0356..2724dc82f992 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void) crystal_khz = 24000; /* 24.0 MHz */ break; case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ATOM_DENVERTON: crystal_khz = 25000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: @@ -1106,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs) return (u64)rdtsc_ordered(); } +static void tsc_cs_mark_unstable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + tsc_unstable = 1; + clear_sched_clock_stable(); + disable_sched_clock_irqtime(); + pr_info("Marking TSC unstable due to clocksource watchdog\n"); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1118,6 +1129,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_MUST_VERIFY, .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, + .mark_unstable = tsc_cs_mark_unstable, }; void mark_tsc_unstable(char *reason) @@ -1355,6 +1367,9 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ + tsc_store_and_check_tsc_adjust(true); + /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same @@ -1385,8 +1400,6 @@ void __init tsc_init(void) if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - else - tsc_store_and_check_tsc_adjust(true); check_system_tsc_reliable(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index d0db011051a5..728f75378475 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu) if (unsynchronized_tsc()) return; - if (tsc_clocksource_reliable) { - if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) - pr_info( - "Skipped synchronization checks as TSC is reliable.\n"); - return; - } - /* * Set the maximum number of test runs to * 1 if the CPU does not provide the TSC_ADJUST MSR @@ -380,14 +373,19 @@ void check_tsc_sync_target(void) int cpus = 2; /* Also aborts if there is no TSC. */ - if (unsynchronized_tsc() || tsc_clocksource_reliable) + if (unsynchronized_tsc()) return; /* * Store, verify and sanitize the TSC adjust register. If * successful skip the test. + * + * The test is also skipped when the TSC is marked reliable. This + * is true for SoCs which have no fallback clocksource. On these + * SoCs the TSC is frequency synchronized, but still the TSC ADJUST + * register might have been wreckaged by the BIOS.. */ - if (tsc_store_and_check_tsc_adjust(false)) { + if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) { atomic_inc(&skip_test); return; } diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 4443e499f279..23d15565d02a 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -6,6 +6,21 @@ #define FRAME_HEADER_SIZE (sizeof(long) * 2) +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + if (task == current) \ + val = READ_ONCE(x); \ + else \ + val = READ_ONCE_NOCHECK(x); \ + val; \ +}) + static void unwind_dump(struct unwind_state *state, unsigned long *sp) { static bool dumped_before = false; @@ -48,7 +63,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state) if (state->regs && user_mode(state->regs)) return 0; - addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, + addr = READ_ONCE_TASK_STACK(state->task, *addr_p); + addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); return __kernel_text_address(addr) ? addr : 0; @@ -162,7 +178,7 @@ bool unwind_next_frame(struct unwind_state *state) if (state->regs) next_bp = (unsigned long *)state->regs->bp; else - next_bp = (unsigned long *)*state->bp; + next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp); /* is the next frame pointer an encoded pointer to pt_regs? */ regs = decode_frame_pointer(next_bp); @@ -207,6 +223,16 @@ bool unwind_next_frame(struct unwind_state *state) return true; bad_address: + /* + * When unwinding a non-current task, the task might actually be + * running on another CPU, in which case it could be modifying its + * stack while we're reading it. This is generally not a problem and + * can be ignored as long as the caller understands that unwinding + * another task will not always succeed. + */ + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index ec5d7545e6dc..0442d98367ae 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) static void mark_screen_rdonly(struct mm_struct *mm) { + struct vm_area_struct *vma; + spinlock_t *ptl; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; - spinlock_t *ptl; int i; down_write(&mm->mmap_sem); @@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pmd = pmd_offset(pud, 0xA0000); if (pmd_trans_huge(*pmd)) { - struct vm_area_struct *vma = find_vma(mm, 0xA0000); + vma = find_vma(mm, 0xA0000); split_huge_pmd(vma, pmd, 0xA0000); } if (pmd_none_or_clear_bad(pmd)) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index e85f6bd7b9d5..1d155cc56629 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -123,8 +123,6 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - kvm_x86_ops->fpu_activate(vcpu); - /* * The existing code assumes virtual address is 48-bit in the canonical * address checks; exit if it is ever changed. @@ -383,7 +381,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(PKU) | 0 /*OSPKE*/; + F(AVX512VBMI) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = @@ -861,12 +859,6 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) if (!best) best = check_cpuid_limit(vcpu, function, index); - /* - * Perfmon not yet supported for L2 guest. - */ - if (is_guest_mode(vcpu) && function == 0xa) - best = NULL; - if (best) { *eax = best->eax; *ebx = best->ebx; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 56628a44668b..45c7306c8780 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -173,6 +173,7 @@ #define NearBranch ((u64)1 << 52) /* Near branches */ #define No16 ((u64)1 << 53) /* No 16 bit operand */ #define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */ +#define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -818,6 +819,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt, return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); } +static int segmented_write_std(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + void *data, + unsigned int size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, true, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception); +} + /* * Prefetch the remaining bytes of the instruction without crossing page * boundary if they are not in fetch_cache yet. @@ -1571,7 +1586,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, &ctxt->exception); } -/* Does not support long mode */ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg, u8 cpl, enum x86_transfer_type transfer, @@ -1608,20 +1622,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, rpl = selector & 3; - /* NULL selector is not valid for TR, CS and SS (except for long mode) */ - if ((seg == VCPU_SREG_CS - || (seg == VCPU_SREG_SS - && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)) - || seg == VCPU_SREG_TR) - && null_selector) - goto exception; - /* TR should be in GDT only */ if (seg == VCPU_SREG_TR && (selector & (1 << 2))) goto exception; - if (null_selector) /* for NULL selector skip all following checks */ + /* NULL selector is not valid for TR, CS and (except for long mode) SS */ + if (null_selector) { + if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR) + goto exception; + + if (seg == VCPU_SREG_SS) { + if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl) + goto exception; + + /* + * ctxt->ops->set_segment expects the CPL to be in + * SS.DPL, so fake an expand-up 32-bit data segment. + */ + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + seg_desc.dpl = cpl; + seg_desc.d = 1; + seg_desc.g = 1; + } + + /* Skip all following checks */ goto load; + } ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) @@ -1737,6 +1765,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg) { u8 cpl = ctxt->ops->cpl(ctxt); + + /* + * None of MOV, POP and LSS can load a NULL selector in CPL=3, but + * they can load it at CPL<3 (Intel's manual says only LSS can, + * but it's wrong). + * + * However, the Intel manual says that putting IST=1/DPL=3 in + * an interrupt gate will result in SS=3 (the AMD manual instead + * says it doesn't), so allow SS=3 in __load_segment_descriptor + * and only forbid it here. + */ + if (seg == VCPU_SREG_SS && selector == 3 && + ctxt->mode == X86EMUL_MODE_PROT64) + return emulate_exception(ctxt, GP_VECTOR, 0, true); + return __load_segment_descriptor(ctxt, selector, seg, cpl, X86_TRANSFER_NONE, NULL); } @@ -3685,8 +3728,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, } /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return segmented_write(ctxt, ctxt->dst.addr.mem, - &desc_ptr, 2 + ctxt->op_bytes); + return segmented_write_std(ctxt, ctxt->dst.addr.mem, + &desc_ptr, 2 + ctxt->op_bytes); } static int em_sgdt(struct x86_emulate_ctxt *ctxt) @@ -3932,7 +3975,7 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) else size = offsetof(struct fxregs_state, xmm_space[0]); - return segmented_write(ctxt, ctxt->memop.addr.mem, &fx_state, size); + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); } static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, @@ -3974,7 +4017,7 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = segmented_read(ctxt, ctxt->memop.addr.mem, &fx_state, 512); + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); if (rc != X86EMUL_CONTINUE) return rc; @@ -4256,7 +4299,7 @@ static const struct opcode group1[] = { }; static const struct opcode group1A[] = { - I(DstMem | SrcNone | Mov | Stack | IncSP, em_pop), N, N, N, N, N, N, N, + I(DstMem | SrcNone | Mov | Stack | IncSP | TwoMemOp, em_pop), N, N, N, N, N, N, N, }; static const struct opcode group2[] = { @@ -4294,7 +4337,7 @@ static const struct opcode group5[] = { I(SrcMemFAddr | ImplicitOps, em_call_far), I(SrcMem | NearBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps, em_jmp_far), - I(SrcMem | Stack, em_push), D(Undefined), + I(SrcMem | Stack | TwoMemOp, em_push), D(Undefined), }; static const struct opcode group6[] = { @@ -4514,8 +4557,8 @@ static const struct opcode opcode_table[256] = { /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), - I2bv(SrcSI | DstDI | Mov | String, em_mov), - F2bv(SrcSI | DstDI | String | NoWrite, em_cmp_r), + I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov), + F2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r), /* 0xA8 - 0xAF */ F2bv(DstAcc | SrcImm | NoWrite, em_test), I2bv(SrcAcc | DstDI | Mov | String, em_mov), @@ -5629,3 +5672,14 @@ void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt) { writeback_registers(ctxt); } + +bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->rep_prefix && (ctxt->d & String)) + return false; + + if (ctxt->d & TwoMemOp) + return false; + + return true; +} diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 1572c35b4f1a..f701d4430727 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -305,13 +305,13 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) return -ENOENT; memset(&irq, 0, sizeof(irq)); - irq.dest_id = kvm_apic_id(vcpu->arch.apic); + irq.shorthand = APIC_DEST_SELF; irq.dest_mode = APIC_DEST_PHYSICAL; irq.delivery_mode = APIC_DM_FIXED; irq.vector = vector; irq.level = 1; - ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL); + ret = kvm_irq_delivery_to_apic(vcpu->kvm, vcpu->arch.apic, &irq, NULL); trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret); return ret; } @@ -964,10 +964,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, /* Calculate cpu time spent by current task in 100ns units */ static u64 current_task_runtime_100ns(void) { - cputime_t utime, stime; + u64 utime, stime; task_cputime_adjusted(current, &utime, &stime); - return div_u64(cputime_to_nsecs(utime + stime), 100); + + return div_u64(utime + stime, 100); } static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 7cc2360f1848..73ea24d4f119 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -598,14 +598,14 @@ static const struct kvm_io_device_ops picdev_eclr_ops = { .write = picdev_eclr_write, }; -struct kvm_pic *kvm_create_pic(struct kvm *kvm) +int kvm_pic_init(struct kvm *kvm) { struct kvm_pic *s; int ret; s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); if (!s) - return NULL; + return -ENOMEM; spin_lock_init(&s->lock); s->kvm = kvm; s->pics[0].elcr_mask = 0xf8; @@ -635,7 +635,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm) mutex_unlock(&kvm->slots_lock); - return s; + kvm->arch.vpic = s; + + return 0; fail_unreg_1: kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &s->dev_slave); @@ -648,13 +650,17 @@ fail_unlock: kfree(s); - return NULL; + return ret; } -void kvm_destroy_pic(struct kvm_pic *vpic) +void kvm_pic_destroy(struct kvm *kvm) { + struct kvm_pic *vpic = kvm->arch.vpic; + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + + kvm->arch.vpic = NULL; kfree(vpic); } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 035731eb3897..40d5b2cf6061 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -73,8 +73,8 @@ struct kvm_pic { unsigned long irq_states[PIC_NUM_PINS]; }; -struct kvm_pic *kvm_create_pic(struct kvm *kvm); -void kvm_destroy_pic(struct kvm_pic *vpic); +int kvm_pic_init(struct kvm *kvm); +void kvm_pic_destroy(struct kvm *kvm); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); @@ -93,18 +93,19 @@ static inline int pic_in_kernel(struct kvm *kvm) static inline int irqchip_split(struct kvm *kvm) { - return kvm->arch.irqchip_split; + return kvm->arch.irqchip_mode == KVM_IRQCHIP_SPLIT; } -static inline int irqchip_in_kernel(struct kvm *kvm) +static inline int irqchip_kernel(struct kvm *kvm) { - struct kvm_pic *vpic = pic_irqchip(kvm); - bool ret; + return kvm->arch.irqchip_mode == KVM_IRQCHIP_KERNEL; +} - ret = (vpic != NULL); - ret |= irqchip_split(kvm); +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + bool ret = kvm->arch.irqchip_mode != KVM_IRQCHIP_NONE; - /* Read vpic before kvm->irq_routing. */ + /* Matches with wmb after initializing kvm->irq_routing. */ smp_rmb(); return ret; } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 6c0191615f23..b96d3893f121 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -41,15 +41,6 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_pic *pic = pic_irqchip(kvm); - - /* - * XXX: rejecting pic routes when pic isn't in use would be better, - * but the default routing table is installed while kvm->arch.vpic is - * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE. - */ - if (!pic) - return -1; - return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); } @@ -58,10 +49,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; - - if (!ioapic) - return -1; - return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level, line_status); } @@ -297,16 +284,20 @@ int kvm_set_routing_entry(struct kvm *kvm, case KVM_IRQ_ROUTING_IRQCHIP: delta = 0; switch (ue->u.irqchip.irqchip) { - case KVM_IRQCHIP_PIC_MASTER: - e->set = kvm_set_pic_irq; - max_pin = PIC_NUM_PINS; - break; case KVM_IRQCHIP_PIC_SLAVE: + delta = 8; + /* fall through */ + case KVM_IRQCHIP_PIC_MASTER: + if (!pic_in_kernel(kvm)) + goto out; + e->set = kvm_set_pic_irq; max_pin = PIC_NUM_PINS; - delta = 8; break; case KVM_IRQCHIP_IOAPIC: + if (!ioapic_in_kernel(kvm)) + goto out; + max_pin = KVM_IOAPIC_NUM_PINS; e->set = kvm_set_ioapic_irq; break; @@ -409,7 +400,7 @@ int kvm_setup_empty_irq_routing(struct kvm *kvm) void kvm_arch_post_irq_routing_update(struct kvm *kvm) { - if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm)) + if (!irqchip_split(kvm)) return; kvm_make_scan_ioapic_request(kvm); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5fe290c1b7d8..bad6a25067bc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -115,6 +115,16 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + +static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) +{ + return apic->vcpu->vcpu_id; +} + static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { switch (map->mode) { @@ -159,13 +169,13 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; int i; - u32 max_id = 255; + u32 max_id = 255; /* enough space for any xAPIC ID */ mutex_lock(&kvm->arch.apic_map_lock); kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_apic_present(vcpu)) - max_id = max(max_id, kvm_apic_id(vcpu->arch.apic)); + max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic)); new = kvm_kvzalloc(sizeof(struct kvm_apic_map) + sizeof(struct kvm_lapic *) * ((u64)max_id + 1)); @@ -179,16 +189,28 @@ static void recalculate_apic_map(struct kvm *kvm) struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_lapic **cluster; u16 mask; - u32 ldr, aid; + u32 ldr; + u8 xapic_id; + u32 x2apic_id; if (!kvm_apic_present(vcpu)) continue; - aid = kvm_apic_id(apic); - ldr = kvm_lapic_get_reg(apic, APIC_LDR); + xapic_id = kvm_xapic_id(apic); + x2apic_id = kvm_x2apic_id(apic); - if (aid <= new->max_apic_id) - new->phys_map[aid] = apic; + /* Hotplug hack: see kvm_apic_match_physical_addr(), ... */ + if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && + x2apic_id <= new->max_apic_id) + new->phys_map[x2apic_id] = apic; + /* + * ... xAPIC ID of VCPUs with APIC ID > 0xff will wrap-around, + * prevent them from masking VCPUs with APIC ID <= 0xff. + */ + if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) + new->phys_map[xapic_id] = apic; + + ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) { new->mode |= KVM_APIC_MODE_X2APIC; @@ -250,6 +272,8 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); + WARN_ON_ONCE(id != apic->vcpu->vcpu_id); + kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); recalculate_apic_map(apic->vcpu->kvm); @@ -317,7 +341,7 @@ static int find_highest_vector(void *bitmap) vec >= 0; vec -= APIC_VECTORS_PER_REG) { reg = bitmap + REG_POS(vec); if (*reg) - return fls(*reg) - 1 + vec; + return __fls(*reg) + vec; } return -1; @@ -337,27 +361,32 @@ static u8 count_vectors(void *bitmap) return count; } -void __kvm_apic_update_irr(u32 *pir, void *regs) +int __kvm_apic_update_irr(u32 *pir, void *regs) { - u32 i, pir_val; + u32 i, vec; + u32 pir_val, irr_val; + int max_irr = -1; - for (i = 0; i <= 7; i++) { + for (i = vec = 0; i <= 7; i++, vec += 32) { pir_val = READ_ONCE(pir[i]); + irr_val = *((u32 *)(regs + APIC_IRR + i * 0x10)); if (pir_val) { - pir_val = xchg(&pir[i], 0); - *((u32 *)(regs + APIC_IRR + i * 0x10)) |= pir_val; + irr_val |= xchg(&pir[i], 0); + *((u32 *)(regs + APIC_IRR + i * 0x10)) = irr_val; } + if (irr_val) + max_irr = __fls(irr_val) + vec; } + + return max_irr; } EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); -void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) { struct kvm_lapic *apic = vcpu->arch.apic; - __kvm_apic_update_irr(pir, apic->regs); - - kvm_make_request(KVM_REQ_EVENT, vcpu); + return __kvm_apic_update_irr(pir, apic->regs); } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); @@ -377,8 +406,6 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) if (!apic->irr_pending) return -1; - if (apic->vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(apic->vcpu); result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); @@ -392,9 +419,10 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) vcpu = apic->vcpu; if (unlikely(vcpu->arch.apicv_active)) { - /* try to update RVI */ + /* need to update RVI */ apic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_x86_ops->hwapic_irr_update(vcpu, + apic_find_highest_irr(apic)); } else { apic->irr_pending = false; apic_clear_vector(vec, apic->regs + APIC_IRR); @@ -484,6 +512,7 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) */ return apic_find_highest_irr(vcpu->arch.apic); } +EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode, @@ -500,16 +529,14 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) { - - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &val, - sizeof(val)); + return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.pv_eoi.data, &val, + sizeof(val)); } static int pv_eoi_get_user(struct kvm_vcpu *vcpu, u8 *val) { - - return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, val, - sizeof(*val)); + return kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.pv_eoi.data, val, + sizeof(*val)); } static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) @@ -546,7 +573,19 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static void apic_update_ppr(struct kvm_lapic *apic) +static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) +{ + int highest_irr; + if (kvm_x86_ops->sync_pir_to_irr && apic->vcpu->arch.apicv_active) + highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + else + highest_irr = apic_find_highest_irr(apic); + if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr) + return -1; + return highest_irr; +} + +static bool __apic_update_ppr(struct kvm_lapic *apic, u32 *new_ppr) { u32 tpr, isrv, ppr, old_ppr; int isr; @@ -564,13 +603,28 @@ static void apic_update_ppr(struct kvm_lapic *apic) apic_debug("vlapic %p, ppr 0x%x, isr 0x%x, isrv 0x%x", apic, ppr, isr, isrv); - if (old_ppr != ppr) { + *new_ppr = ppr; + if (old_ppr != ppr) kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr); - if (ppr < old_ppr) - kvm_make_request(KVM_REQ_EVENT, apic->vcpu); - } + + return ppr < old_ppr; +} + +static void apic_update_ppr(struct kvm_lapic *apic) +{ + u32 ppr; + + if (__apic_update_ppr(apic, &ppr) && + apic_has_interrupt_for_ppr(apic, ppr) != -1) + kvm_make_request(KVM_REQ_EVENT, apic->vcpu); } +void kvm_apic_update_ppr(struct kvm_vcpu *vcpu) +{ + apic_update_ppr(vcpu->arch.apic); +} +EXPORT_SYMBOL_GPL(kvm_apic_update_ppr); + static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) { kvm_lapic_set_reg(apic, APIC_TASKPRI, tpr); @@ -579,10 +633,8 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { - if (apic_x2apic_mode(apic)) - return mda == X2APIC_BROADCAST; - - return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST; + return mda == (apic_x2apic_mode(apic) ? + X2APIC_BROADCAST : APIC_BROADCAST); } static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) @@ -591,9 +643,18 @@ static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) return true; if (apic_x2apic_mode(apic)) - return mda == kvm_apic_id(apic); + return mda == kvm_x2apic_id(apic); + + /* + * Hotplug hack: Make LAPIC in xAPIC mode also accept interrupts as if + * it were in x2APIC mode. Hotplugged VCPUs start in xAPIC mode and + * this allows unique addressing of VCPUs with APIC ID over 0xff. + * The 0xff condition is needed because writeable xAPIC ID. + */ + if (kvm_x2apic_id(apic) > 0xff && mda == kvm_x2apic_id(apic)) + return true; - return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic)); + return mda == kvm_xapic_id(apic); } static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) @@ -610,7 +671,6 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) && (logical_id & mda & 0xffff) != 0; logical_id = GET_APIC_LOGICAL_ID(logical_id); - mda = GET_APIC_DEST_FIELD(mda); switch (kvm_lapic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: @@ -627,9 +687,9 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) /* The KVM local APIC implementation has two quirks: * - * - the xAPIC MDA stores the destination at bits 24-31, while this - * is not true of struct kvm_lapic_irq's dest_id field. This is - * just a quirk in the API and is not problematic. + * - Real hardware delivers interrupts destined to x2APIC ID > 0xff to LAPICs + * in xAPIC mode if the "destination & 0xff" matches its xAPIC ID. + * KVM doesn't do that aliasing. * * - in-kernel IOAPIC messages have to be delivered directly to * x2APIC, because the kernel does not support interrupt remapping. @@ -645,13 +705,12 @@ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, struct kvm_lapic *source, struct kvm_lapic *target) { bool ipi = source != NULL; - bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled && - !ipi && dest_id == APIC_BROADCAST && x2apic_mda) + !ipi && dest_id == APIC_BROADCAST && apic_x2apic_mode(target)) return X2APIC_BROADCAST; - return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); + return dest_id; } bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, @@ -1907,9 +1966,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; - apic_debug("%s: vcpu=%p, id=%d, base_msr=" + apic_debug("%s: vcpu=%p, id=0x%x, base_msr=" "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__, - vcpu, kvm_apic_id(apic), + vcpu, kvm_lapic_get_reg(apic, APIC_ID), vcpu->arch.apic_base, apic->base_address); } @@ -2021,17 +2080,13 @@ nomem: int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - int highest_irr; + u32 ppr; if (!apic_enabled(apic)) return -1; - apic_update_ppr(apic); - highest_irr = apic_find_highest_irr(apic); - if ((highest_irr == -1) || - ((highest_irr & 0xF0) <= kvm_lapic_get_reg(apic, APIC_PROCPRI))) - return -1; - return highest_irr; + __apic_update_ppr(apic, &ppr); + return apic_has_interrupt_for_ppr(apic, ppr); } int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) @@ -2067,6 +2122,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) { int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + u32 ppr; if (vector == -1) return -1; @@ -2078,13 +2134,23 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) * because the process would deliver it through the IDT. */ - apic_set_isr(vector, apic); - apic_update_ppr(apic); apic_clear_irr(vector, apic); - if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { - apic_clear_isr(vector, apic); + /* + * For auto-EOI interrupts, there might be another pending + * interrupt above PPR, so check whether to raise another + * KVM_REQ_EVENT. + */ apic_update_ppr(apic); + } else { + /* + * For normal interrupts, PPR has been raised and there cannot + * be a higher-priority pending interrupt---except if there was + * a concurrent interrupt injection, but that would have + * triggered KVM_REQ_EVENT already. + */ + apic_set_isr(vector, apic); + __apic_update_ppr(apic, &ppr); } return vector; @@ -2145,8 +2211,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; if (vcpu->arch.apicv_active) { - if (kvm_x86_ops->apicv_post_state_restore) - kvm_x86_ops->apicv_post_state_restore(vcpu); + kvm_x86_ops->apicv_post_state_restore(vcpu); kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); kvm_x86_ops->hwapic_isr_update(vcpu, @@ -2220,8 +2285,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32))) + if (kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32))) return; apic_set_tpr(vcpu->arch.apic, data & 0xff); @@ -2273,14 +2338,14 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) max_isr = 0; data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24); - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32)); + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32)); } int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) { if (vapic_addr) { - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apic->vapic_cache, vapic_addr, sizeof(u32))) return -EINVAL; @@ -2374,7 +2439,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data) vcpu->arch.pv_eoi.msr_val = data; if (!pv_eoi_enabled(vcpu)) return 0; - return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data, + return kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.pv_eoi.data, addr, sizeof(u8)); } @@ -2426,3 +2491,9 @@ void kvm_lapic_init(void) jump_label_rate_limit(&apic_hw_disabled, HZ); jump_label_rate_limit(&apic_sw_disabled, HZ); } + +void kvm_lapic_exit(void) +{ + static_key_deferred_flush(&apic_hw_disabled); + static_key_deferred_flush(&apic_sw_disabled); +} diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index e0c80233b3e1..bcbe811f3b97 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -71,8 +71,9 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); -void __kvm_apic_update_irr(u32 *pir, void *regs); -void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); +int __kvm_apic_update_irr(u32 *pir, void *regs); +int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); +void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); @@ -110,6 +111,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); void kvm_lapic_init(void); +void kvm_lapic_exit(void); #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) @@ -202,17 +204,6 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } -static inline u32 kvm_apic_id(struct kvm_lapic *apic) -{ - /* To avoid a race between apic_base and following APIC_ID update when - * switching to x2apic_mode, the x2apic mode returns initial x2apic id. - */ - if (apic_x2apic_mode(apic)) - return apic->vcpu->vcpu_id; - - return kvm_lapic_get_reg(apic, APIC_ID) >> 24; -} - bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7012de4a1fed..2fd7586aad4d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -37,6 +37,8 @@ #include <linux/srcu.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/hash.h> +#include <linux/kern_levels.h> #include <asm/page.h> #include <asm/cmpxchg.h> @@ -129,6 +131,10 @@ module_param(dbg, bool, 0644); #define ACC_USER_MASK PT_USER_MASK #define ACC_ALL (ACC_EXEC_MASK | ACC_WRITE_MASK | ACC_USER_MASK) +/* The mask for the R/X bits in EPT PTEs */ +#define PT64_EPT_READABLE_MASK 0x1ull +#define PT64_EPT_EXECUTABLE_MASK 0x4ull + #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -178,15 +184,40 @@ static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; static u64 __read_mostly shadow_present_mask; +/* + * The mask/value to distinguish a PTE that has been marked not-present for + * access tracking purposes. + * The mask would be either 0 if access tracking is disabled, or + * SPTE_SPECIAL_MASK|VMX_EPT_RWX_MASK if access tracking is enabled. + */ +static u64 __read_mostly shadow_acc_track_mask; +static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; + +/* + * The mask/shift to use for saving the original R/X bits when marking the PTE + * as not-present for access tracking purposes. We do not save the W bit as the + * PTEs being access tracked also need to be dirty tracked, so the W bit will be + * restored only when a write is attempted to the page. + */ +static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK | + PT64_EPT_EXECUTABLE_MASK; +static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT; + static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) { - shadow_mmio_mask = mmio_mask; + shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static inline bool is_access_track_spte(u64 spte) +{ + /* Always false if shadow_acc_track_mask is zero. */ + return (spte & shadow_acc_track_mask) == shadow_acc_track_value; +} + /* * the low bit of the generation number is always presumed to be zero. * This disables mmio caching during memslot updates. The concept is @@ -284,17 +315,35 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) } void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, - u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask) + u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, + u64 acc_track_mask) { + if (acc_track_mask != 0) + acc_track_mask |= SPTE_SPECIAL_MASK; + shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; shadow_dirty_mask = dirty_mask; shadow_nx_mask = nx_mask; shadow_x_mask = x_mask; shadow_present_mask = p_mask; + shadow_acc_track_mask = acc_track_mask; + WARN_ON(shadow_accessed_mask != 0 && shadow_acc_track_mask != 0); } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); +void kvm_mmu_clear_all_pte_masks(void) +{ + shadow_user_mask = 0; + shadow_accessed_mask = 0; + shadow_dirty_mask = 0; + shadow_nx_mask = 0; + shadow_x_mask = 0; + shadow_mmio_mask = 0; + shadow_present_mask = 0; + shadow_acc_track_mask = 0; +} + static int is_cpuid_PSE36(void) { return 1; @@ -307,7 +356,7 @@ static int is_nx(struct kvm_vcpu *vcpu) static int is_shadow_present_pte(u64 pte) { - return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte); + return (pte != 0) && !is_mmio_spte(pte); } static int is_large_pte(u64 pte) @@ -324,6 +373,11 @@ static int is_last_spte(u64 pte, int level) return 0; } +static bool is_executable_pte(u64 spte) +{ + return (spte & (shadow_x_mask | shadow_nx_mask)) == shadow_x_mask; +} + static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -473,7 +527,7 @@ retry: } #endif -static bool spte_is_locklessly_modifiable(u64 spte) +static bool spte_can_locklessly_be_made_writable(u64 spte) { return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) == (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE); @@ -481,36 +535,38 @@ static bool spte_is_locklessly_modifiable(u64 spte) static bool spte_has_volatile_bits(u64 spte) { + if (!is_shadow_present_pte(spte)) + return false; + /* * Always atomically update spte if it can be updated * out of mmu-lock, it can ensure dirty bit is not lost, * also, it can help us to get a stable is_writable_pte() * to ensure tlb flush is not missed. */ - if (spte_is_locklessly_modifiable(spte)) + if (spte_can_locklessly_be_made_writable(spte) || + is_access_track_spte(spte)) return true; - if (!shadow_accessed_mask) - return false; - - if (!is_shadow_present_pte(spte)) - return false; - - if ((spte & shadow_accessed_mask) && - (!is_writable_pte(spte) || (spte & shadow_dirty_mask))) - return false; + if (shadow_accessed_mask) { + if ((spte & shadow_accessed_mask) == 0 || + (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) + return true; + } - return true; + return false; } -static bool spte_is_bit_cleared(u64 old_spte, u64 new_spte, u64 bit_mask) +static bool is_accessed_spte(u64 spte) { - return (old_spte & bit_mask) && !(new_spte & bit_mask); + return shadow_accessed_mask ? spte & shadow_accessed_mask + : !is_access_track_spte(spte); } -static bool spte_is_bit_changed(u64 old_spte, u64 new_spte, u64 bit_mask) +static bool is_dirty_spte(u64 spte) { - return (old_spte & bit_mask) != (new_spte & bit_mask); + return shadow_dirty_mask ? spte & shadow_dirty_mask + : spte & PT_WRITABLE_MASK; } /* Rules for using mmu_spte_set: @@ -525,25 +581,19 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte) __set_spte(sptep, new_spte); } -/* Rules for using mmu_spte_update: - * Update the state bits, it means the mapped pfn is not changed. - * - * Whenever we overwrite a writable spte with a read-only one we - * should flush remote TLBs. Otherwise rmap_write_protect - * will find a read-only spte, even though the writable spte - * might be cached on a CPU's TLB, the return value indicates this - * case. +/* + * Update the SPTE (excluding the PFN), but do not track changes in its + * accessed/dirty status. */ -static bool mmu_spte_update(u64 *sptep, u64 new_spte) +static u64 mmu_spte_update_no_track(u64 *sptep, u64 new_spte) { u64 old_spte = *sptep; - bool ret = false; WARN_ON(!is_shadow_present_pte(new_spte)); if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); - return ret; + return old_spte; } if (!spte_has_volatile_bits(old_spte)) @@ -551,45 +601,62 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) else old_spte = __update_clear_spte_slow(sptep, new_spte); + WARN_ON(spte_to_pfn(old_spte) != spte_to_pfn(new_spte)); + + return old_spte; +} + +/* Rules for using mmu_spte_update: + * Update the state bits, it means the mapped pfn is not changed. + * + * Whenever we overwrite a writable spte with a read-only one we + * should flush remote TLBs. Otherwise rmap_write_protect + * will find a read-only spte, even though the writable spte + * might be cached on a CPU's TLB, the return value indicates this + * case. + * + * Returns true if the TLB needs to be flushed + */ +static bool mmu_spte_update(u64 *sptep, u64 new_spte) +{ + bool flush = false; + u64 old_spte = mmu_spte_update_no_track(sptep, new_spte); + + if (!is_shadow_present_pte(old_spte)) + return false; + /* * For the spte updated out of mmu-lock is safe, since * we always atomically update it, see the comments in * spte_has_volatile_bits(). */ - if (spte_is_locklessly_modifiable(old_spte) && + if (spte_can_locklessly_be_made_writable(old_spte) && !is_writable_pte(new_spte)) - ret = true; - - if (!shadow_accessed_mask) { - /* - * We don't set page dirty when dropping non-writable spte. - * So do it now if the new spte is becoming non-writable. - */ - if (ret) - kvm_set_pfn_dirty(spte_to_pfn(old_spte)); - return ret; - } + flush = true; /* - * Flush TLB when accessed/dirty bits are changed in the page tables, + * Flush TLB when accessed/dirty states are changed in the page tables, * to guarantee consistency between TLB and page tables. */ - if (spte_is_bit_changed(old_spte, new_spte, - shadow_accessed_mask | shadow_dirty_mask)) - ret = true; - if (spte_is_bit_cleared(old_spte, new_spte, shadow_accessed_mask)) + if (is_accessed_spte(old_spte) && !is_accessed_spte(new_spte)) { + flush = true; kvm_set_pfn_accessed(spte_to_pfn(old_spte)); - if (spte_is_bit_cleared(old_spte, new_spte, shadow_dirty_mask)) + } + + if (is_dirty_spte(old_spte) && !is_dirty_spte(new_spte)) { + flush = true; kvm_set_pfn_dirty(spte_to_pfn(old_spte)); + } - return ret; + return flush; } /* * Rules for using mmu_spte_clear_track_bits: * It sets the sptep from present to nonpresent, and track the * state bits, it is used to clear the last level sptep. + * Returns non-zero if the PTE was previously valid. */ static int mmu_spte_clear_track_bits(u64 *sptep) { @@ -613,11 +680,12 @@ static int mmu_spte_clear_track_bits(u64 *sptep) */ WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn))); - if (!shadow_accessed_mask || old_spte & shadow_accessed_mask) + if (is_accessed_spte(old_spte)) kvm_set_pfn_accessed(pfn); - if (old_spte & (shadow_dirty_mask ? shadow_dirty_mask : - PT_WRITABLE_MASK)) + + if (is_dirty_spte(old_spte)) kvm_set_pfn_dirty(pfn); + return 1; } @@ -636,6 +704,78 @@ static u64 mmu_spte_get_lockless(u64 *sptep) return __get_spte_lockless(sptep); } +static u64 mark_spte_for_access_track(u64 spte) +{ + if (shadow_accessed_mask != 0) + return spte & ~shadow_accessed_mask; + + if (shadow_acc_track_mask == 0 || is_access_track_spte(spte)) + return spte; + + /* + * Making an Access Tracking PTE will result in removal of write access + * from the PTE. So, verify that we will be able to restore the write + * access in the fast page fault path later on. + */ + WARN_ONCE((spte & PT_WRITABLE_MASK) && + !spte_can_locklessly_be_made_writable(spte), + "kvm: Writable SPTE is not locklessly dirty-trackable\n"); + + WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask << + shadow_acc_track_saved_bits_shift), + "kvm: Access Tracking saved bit locations are not zero\n"); + + spte |= (spte & shadow_acc_track_saved_bits_mask) << + shadow_acc_track_saved_bits_shift; + spte &= ~shadow_acc_track_mask; + spte |= shadow_acc_track_value; + + return spte; +} + +/* Restore an acc-track PTE back to a regular PTE */ +static u64 restore_acc_track_spte(u64 spte) +{ + u64 new_spte = spte; + u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift) + & shadow_acc_track_saved_bits_mask; + + WARN_ON_ONCE(!is_access_track_spte(spte)); + + new_spte &= ~shadow_acc_track_mask; + new_spte &= ~(shadow_acc_track_saved_bits_mask << + shadow_acc_track_saved_bits_shift); + new_spte |= saved_bits; + + return new_spte; +} + +/* Returns the Accessed status of the PTE and resets it at the same time. */ +static bool mmu_spte_age(u64 *sptep) +{ + u64 spte = mmu_spte_get_lockless(sptep); + + if (!is_accessed_spte(spte)) + return false; + + if (shadow_accessed_mask) { + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + } else { + /* + * Capture the dirty status of the page, so that it doesn't get + * lost when the SPTE is marked for access tracking. + */ + if (is_writable_pte(spte)) + kvm_set_pfn_dirty(spte_to_pfn(spte)); + + spte = mark_spte_for_access_track(spte); + mmu_spte_update_no_track(sptep, spte); + } + + return true; +} + static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { /* @@ -1212,7 +1352,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) u64 spte = *sptep; if (!is_writable_pte(spte) && - !(pt_protect && spte_is_locklessly_modifiable(spte))) + !(pt_protect && spte_can_locklessly_be_made_writable(spte))) return false; rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); @@ -1420,7 +1560,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, restart: for_each_rmap_spte(rmap_head, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); + sptep, *sptep, gfn, level); need_flush = 1; @@ -1433,7 +1573,8 @@ restart: new_spte &= ~PT_WRITABLE_MASK; new_spte &= ~SPTE_HOST_WRITEABLE; - new_spte &= ~shadow_accessed_mask; + + new_spte = mark_spte_for_access_track(new_spte); mmu_spte_clear_track_bits(sptep); mmu_spte_set(sptep, new_spte); @@ -1595,15 +1736,8 @@ static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct rmap_iterator uninitialized_var(iter); int young = 0; - BUG_ON(!shadow_accessed_mask); - - for_each_rmap_spte(rmap_head, &iter, sptep) { - if (*sptep & shadow_accessed_mask) { - young = 1; - clear_bit((ffs(shadow_accessed_mask) - 1), - (unsigned long *)sptep); - } - } + for_each_rmap_spte(rmap_head, &iter, sptep) + young |= mmu_spte_age(sptep); trace_kvm_age_page(gfn, level, slot, young); return young; @@ -1615,24 +1749,20 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, { u64 *sptep; struct rmap_iterator iter; - int young = 0; /* - * If there's no access bit in the secondary pte set by the - * hardware it's up to gup-fast/gup to set the access bit in - * the primary pte or in the page structure. + * If there's no access bit in the secondary pte set by the hardware and + * fast access tracking is also not enabled, it's up to gup-fast/gup to + * set the access bit in the primary pte or in the page structure. */ - if (!shadow_accessed_mask) + if (!shadow_accessed_mask && !shadow_acc_track_mask) goto out; - for_each_rmap_spte(rmap_head, &iter, sptep) { - if (*sptep & shadow_accessed_mask) { - young = 1; - break; - } - } + for_each_rmap_spte(rmap_head, &iter, sptep) + if (is_accessed_spte(*sptep)) + return 1; out: - return young; + return 0; } #define RMAP_RECYCLE_THRESHOLD 1000 @@ -1660,7 +1790,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) * This has some overhead, but not as much as the cost of swapping * out actively used pages or breaking up actively used hugepages. */ - if (!shadow_accessed_mask) + if (!shadow_accessed_mask && !shadow_acc_track_mask) return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); @@ -1713,7 +1843,7 @@ static void kvm_mmu_free_page(struct kvm_mmu_page *sp) static unsigned kvm_page_table_hashfn(gfn_t gfn) { - return gfn & ((1 << KVM_MMU_HASH_SHIFT) - 1); + return hash_64(gfn, KVM_MMU_HASH_SHIFT); } static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu, @@ -1904,17 +2034,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, * since it has been deleted from active_mmu_pages but still can be found * at hast list. * - * for_each_gfn_valid_sp() has skipped that kind of pages. + * for_each_valid_sp() has skipped that kind of pages. */ -#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ +#define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ - if ((_sp)->gfn != (_gfn) || is_obsolete_sp((_kvm), (_sp)) \ - || (_sp)->role.invalid) {} else + if (is_obsolete_sp((_kvm), (_sp)) || (_sp)->role.invalid) { \ + } else #define for_each_gfn_indirect_valid_sp(_kvm, _sp, _gfn) \ - for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ - if ((_sp)->role.direct) {} else + for_each_valid_sp(_kvm, _sp, _gfn) \ + if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else /* @sp->gfn should be write-protected at the call site */ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -2116,6 +2246,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; bool need_sync = false; bool flush = false; + int collisions = 0; LIST_HEAD(invalid_list); role = vcpu->arch.mmu.base_role; @@ -2130,7 +2261,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; role.quadrant = quadrant; } - for_each_gfn_valid_sp(vcpu->kvm, sp, gfn) { + for_each_valid_sp(vcpu->kvm, sp, gfn) { + if (sp->gfn != gfn) { + collisions++; + continue; + } + if (!need_sync && sp->unsync) need_sync = true; @@ -2153,7 +2289,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); - return sp; + goto out; } ++vcpu->kvm->stat.mmu_cache_miss; @@ -2183,6 +2319,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, trace_kvm_mmu_get_page(sp, true); kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); +out: + if (collisions > vcpu->kvm->stat.max_mmu_page_hash_collisions) + vcpu->kvm->stat.max_mmu_page_hash_collisions = collisions; return sp; } @@ -2583,6 +2722,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= shadow_dirty_mask; } + if (speculative) + spte = mark_spte_for_access_track(spte); + set_pte: if (mmu_spte_update(sptep, spte)) kvm_flush_remote_tlbs(vcpu->kvm); @@ -2636,7 +2778,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", is_large_pte(*sptep)? "2MB" : "4kB", - *sptep & PT_PRESENT_MASK ?"RW":"R", gfn, + *sptep & PT_WRITABLE_MASK ? "RW" : "R", gfn, *sptep, sptep); if (!was_rmapped && is_large_pte(*sptep)) ++vcpu->kvm->stat.lpages; @@ -2869,33 +3011,43 @@ static bool page_fault_can_be_fast(u32 error_code) if (unlikely(error_code & PFERR_RSVD_MASK)) return false; + /* See if the page fault is due to an NX violation */ + if (unlikely(((error_code & (PFERR_FETCH_MASK | PFERR_PRESENT_MASK)) + == (PFERR_FETCH_MASK | PFERR_PRESENT_MASK)))) + return false; + /* - * #PF can be fast only if the shadow page table is present and it - * is caused by write-protect, that means we just need change the - * W bit of the spte which can be done out of mmu-lock. + * #PF can be fast if: + * 1. The shadow page table entry is not present, which could mean that + * the fault is potentially caused by access tracking (if enabled). + * 2. The shadow page table entry is present and the fault + * is caused by write-protect, that means we just need change the W + * bit of the spte which can be done out of mmu-lock. + * + * However, if access tracking is disabled we know that a non-present + * page must be a genuine page fault where we have to create a new SPTE. + * So, if access tracking is disabled, we return true only for write + * accesses to a present page. */ - if (!(error_code & PFERR_PRESENT_MASK) || - !(error_code & PFERR_WRITE_MASK)) - return false; - return true; + return shadow_acc_track_mask != 0 || + ((error_code & (PFERR_WRITE_MASK | PFERR_PRESENT_MASK)) + == (PFERR_WRITE_MASK | PFERR_PRESENT_MASK)); } +/* + * Returns true if the SPTE was fixed successfully. Otherwise, + * someone else modified the SPTE from its original value. + */ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *sptep, u64 spte) + u64 *sptep, u64 old_spte, u64 new_spte) { gfn_t gfn; WARN_ON(!sp->role.direct); /* - * The gfn of direct spte is stable since it is calculated - * by sp->gfn. - */ - gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); - - /* * Theoretically we could also set dirty bit (and flush TLB) here in * order to eliminate unnecessary PML logging. See comments in * set_spte. But fast_page_fault is very unlikely to happen with PML @@ -2907,12 +3059,33 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * * Compare with set_spte where instead shadow_dirty_mask is set. */ - if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) + if (cmpxchg64(sptep, old_spte, new_spte) != old_spte) + return false; + + if (is_writable_pte(new_spte) && !is_writable_pte(old_spte)) { + /* + * The gfn of direct spte is stable since it is + * calculated by sp->gfn. + */ + gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); kvm_vcpu_mark_page_dirty(vcpu, gfn); + } return true; } +static bool is_access_allowed(u32 fault_err_code, u64 spte) +{ + if (fault_err_code & PFERR_FETCH_MASK) + return is_executable_pte(spte); + + if (fault_err_code & PFERR_WRITE_MASK) + return is_writable_pte(spte); + + /* Fault was on Read access */ + return spte & PT_PRESENT_MASK; +} + /* * Return value: * - true: let the vcpu to access on the same address again. @@ -2923,8 +3096,9 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; - bool ret = false; + bool fault_handled = false; u64 spte = 0ull; + uint retry_count = 0; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return false; @@ -2933,66 +3107,93 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, return false; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) - if (!is_shadow_present_pte(spte) || iterator.level < level) + + do { + u64 new_spte; + + for_each_shadow_entry_lockless(vcpu, gva, iterator, spte) + if (!is_shadow_present_pte(spte) || + iterator.level < level) + break; + + sp = page_header(__pa(iterator.sptep)); + if (!is_last_spte(spte, sp->role.level)) break; - /* - * If the mapping has been changed, let the vcpu fault on the - * same address again. - */ - if (!is_shadow_present_pte(spte)) { - ret = true; - goto exit; - } + /* + * Check whether the memory access that caused the fault would + * still cause it if it were to be performed right now. If not, + * then this is a spurious fault caused by TLB lazily flushed, + * or some other CPU has already fixed the PTE after the + * current CPU took the fault. + * + * Need not check the access of upper level table entries since + * they are always ACC_ALL. + */ + if (is_access_allowed(error_code, spte)) { + fault_handled = true; + break; + } - sp = page_header(__pa(iterator.sptep)); - if (!is_last_spte(spte, sp->role.level)) - goto exit; + new_spte = spte; - /* - * Check if it is a spurious fault caused by TLB lazily flushed. - * - * Need not check the access of upper level table entries since - * they are always ACC_ALL. - */ - if (is_writable_pte(spte)) { - ret = true; - goto exit; - } + if (is_access_track_spte(spte)) + new_spte = restore_acc_track_spte(new_spte); - /* - * Currently, to simplify the code, only the spte write-protected - * by dirty-log can be fast fixed. - */ - if (!spte_is_locklessly_modifiable(spte)) - goto exit; + /* + * Currently, to simplify the code, write-protection can + * be removed in the fast path only if the SPTE was + * write-protected for dirty-logging or access tracking. + */ + if ((error_code & PFERR_WRITE_MASK) && + spte_can_locklessly_be_made_writable(spte)) + { + new_spte |= PT_WRITABLE_MASK; - /* - * Do not fix write-permission on the large spte since we only dirty - * the first page into the dirty-bitmap in fast_pf_fix_direct_spte() - * that means other pages are missed if its slot is dirty-logged. - * - * Instead, we let the slow page fault path create a normal spte to - * fix the access. - * - * See the comments in kvm_arch_commit_memory_region(). - */ - if (sp->role.level > PT_PAGE_TABLE_LEVEL) - goto exit; + /* + * Do not fix write-permission on the large spte. Since + * we only dirty the first page into the dirty-bitmap in + * fast_pf_fix_direct_spte(), other pages are missed + * if its slot has dirty logging enabled. + * + * Instead, we let the slow page fault path create a + * normal spte to fix the access. + * + * See the comments in kvm_arch_commit_memory_region(). + */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + break; + } + + /* Verify that the fault can be handled in the fast path */ + if (new_spte == spte || + !is_access_allowed(error_code, new_spte)) + break; + + /* + * Currently, fast page fault only works for direct mapping + * since the gfn is not stable for indirect shadow page. See + * Documentation/virtual/kvm/locking.txt to get more detail. + */ + fault_handled = fast_pf_fix_direct_spte(vcpu, sp, + iterator.sptep, spte, + new_spte); + if (fault_handled) + break; + + if (++retry_count > 4) { + printk_once(KERN_WARNING + "kvm: Fast #PF retrying more than 4 times.\n"); + break; + } + + } while (true); - /* - * Currently, fast page fault only works for direct mapping since - * the gfn is not stable for indirect shadow page. - * See Documentation/virtual/kvm/locking.txt to get more detail. - */ - ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte); -exit: trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, - spte, ret); + spte, fault_handled); walk_shadow_page_lockless_end(vcpu); - return ret; + return fault_handled; } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, @@ -5063,6 +5264,8 @@ static void mmu_destroy_caches(void) int kvm_mmu_module_init(void) { + kvm_mmu_clear_all_pte_masks(); + pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, 0, NULL); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 08a4d3ab3455..d1efe2c62b3f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -971,8 +971,8 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) * a particular vCPU. */ #define SVM_VM_DATA_HASH_BITS 8 -DECLARE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); -static spinlock_t svm_vm_data_hash_lock; +static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); +static DEFINE_SPINLOCK(svm_vm_data_hash_lock); /* Note: * This function is called from IOMMU driver to notify @@ -1077,8 +1077,6 @@ static __init int svm_hardware_setup(void) } else { pr_info("AVIC enabled\n"); - hash_init(svm_vm_data_hash); - spin_lock_init(&svm_vm_data_hash_lock); amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); } } @@ -1159,7 +1157,6 @@ static void init_vmcb(struct vcpu_svm *svm) struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; - svm->vcpu.fpu_active = 1; svm->vcpu.arch.hflags = 0; set_cr_intercept(svm, INTERCEPT_CR0_READ); @@ -1901,15 +1898,12 @@ static void update_cr0_intercept(struct vcpu_svm *svm) ulong gcr0 = svm->vcpu.arch.cr0; u64 *hcr0 = &svm->vmcb->save.cr0; - if (!svm->vcpu.fpu_active) - *hcr0 |= SVM_CR0_SELECTIVE_MASK; - else - *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) - | (gcr0 & SVM_CR0_SELECTIVE_MASK); + *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) + | (gcr0 & SVM_CR0_SELECTIVE_MASK); mark_dirty(svm->vmcb, VMCB_CR); - if (gcr0 == *hcr0 && svm->vcpu.fpu_active) { + if (gcr0 == *hcr0) { clr_cr_intercept(svm, INTERCEPT_CR0_READ); clr_cr_intercept(svm, INTERCEPT_CR0_WRITE); } else { @@ -1940,8 +1934,6 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!npt_enabled) cr0 |= X86_CR0_PG | X86_CR0_WP; - if (!vcpu->fpu_active) - cr0 |= X86_CR0_TS; /* * re-enable caching here because the QEMU bios * does not do it - this results in some delay at @@ -2160,22 +2152,6 @@ static int ac_interception(struct vcpu_svm *svm) return 1; } -static void svm_fpu_activate(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - clr_exception_intercept(svm, NM_VECTOR); - - svm->vcpu.fpu_active = 1; - update_cr0_intercept(svm); -} - -static int nm_interception(struct vcpu_svm *svm) -{ - svm_fpu_activate(&svm->vcpu); - return 1; -} - static bool is_erratum_383(void) { int err, i; @@ -2573,9 +2549,6 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) if (!npt_enabled && svm->apf_reason == 0) return NESTED_EXIT_HOST; break; - case SVM_EXIT_EXCP_BASE + NM_VECTOR: - nm_interception(svm); - break; default: break; } @@ -4020,7 +3993,6 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, - [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, [SVM_EXIT_INTR] = intr_interception, @@ -4182,6 +4154,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + vcpu->arch.gpa_available = (exit_code == SVM_EXIT_NPF); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -4357,11 +4331,6 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - return; -} - static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { kvm_lapic_set_irr(vec, vcpu->arch.apic); @@ -5077,14 +5046,6 @@ static bool svm_has_wbinvd_exit(void) return true; } -static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - set_exception_intercept(svm, NM_VECTOR); - update_cr0_intercept(svm); -} - #define PRE_EX(exit) { .exit_code = (exit), \ .stage = X86_ICPT_PRE_EXCEPT, } #define POST_EX(exit) { .exit_code = (exit), \ @@ -5345,9 +5306,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_pkru = svm_get_pkru, - .fpu_activate = svm_fpu_activate, - .fpu_deactivate = svm_fpu_deactivate, - .tlb_flush = svm_flush_tlb, .run = svm_vcpu_run, @@ -5371,7 +5329,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_enable_apicv = svm_get_enable_apicv, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, - .sync_pir_to_irr = svm_sync_pir_to_irr, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, .apicv_post_state_restore = avic_post_state_restore, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a236decb81e4..ef4ba71dbb66 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1856,7 +1856,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); + (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -1865,8 +1865,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = ~0; if (enable_ept) eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */ - if (vcpu->fpu_active) - eb &= ~(1u << NM_VECTOR); /* When we are running a nested L2 guest and L1 specified for it a * certain exception bitmap, we must trap the same exceptions and pass @@ -1992,19 +1990,6 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, m->host[i].value = host_val; } -static void reload_tss(void) -{ - /* - * VT restores TR but not its size. Useless. - */ - struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); - struct desc_struct *descs; - - descs = (void *)gdt->address; - descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ - load_TR_desc(); -} - static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { u64 guest_efer = vmx->vcpu.arch.efer; @@ -2059,41 +2044,36 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) } } +#ifdef CONFIG_X86_32 +/* + * On 32-bit kernels, VM exits still load the FS and GS bases from the + * VMCS rather than the segment table. KVM uses this helper to figure + * out the current bases to poke them into the VMCS before entry. + */ static unsigned long segment_base(u16 selector) { struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *d; - unsigned long table_base; + struct desc_struct *table; unsigned long v; - if (!(selector & ~3)) + if (!(selector & ~SEGMENT_RPL_MASK)) return 0; - table_base = gdt->address; + table = (struct desc_struct *)gdt->address; - if (selector & 4) { /* from ldt */ + if ((selector & SEGMENT_TI_MASK) == SEGMENT_LDT) { u16 ldt_selector = kvm_read_ldt(); - if (!(ldt_selector & ~3)) + if (!(ldt_selector & ~SEGMENT_RPL_MASK)) return 0; - table_base = segment_base(ldt_selector); + table = (struct desc_struct *)segment_base(ldt_selector); } - d = (struct desc_struct *)(table_base + (selector & ~7)); - v = get_desc_base(d); -#ifdef CONFIG_X86_64 - if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; -#endif + v = get_desc_base(&table[selector >> 3]); return v; } - -static inline unsigned long kvm_read_tr_base(void) -{ - u16 tr; - asm("str %0" : "=g"(tr)); - return segment_base(tr); -} +#endif static void vmx_save_host_state(struct kvm_vcpu *vcpu) { @@ -2179,7 +2159,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(es, vmx->host_state.es_sel); } #endif - reload_tss(); + invalidate_tss_limit(); #ifdef CONFIG_X86_64 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); #endif @@ -2294,10 +2274,19 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* * Linux uses per-cpu TSS and GDT, so set these when switching - * processors. + * processors. See 22.2.4. */ - vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */ - vmcs_writel(HOST_GDTR_BASE, gdt->address); /* 22.2.4 */ + vmcs_writel(HOST_TR_BASE, + (unsigned long)this_cpu_ptr(&cpu_tss)); + vmcs_writel(HOST_GDTR_BASE, gdt->address); + + /* + * VM exits change the host TR limit to 0x67 after a VM + * exit. This is okay, since 0x67 covers everything except + * the IO bitmap and have have code to handle the IO bitmap + * being lost after a VM exit. + */ + BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 != 0x67); rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ @@ -2340,25 +2329,6 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu) } } -static void vmx_fpu_activate(struct kvm_vcpu *vcpu) -{ - ulong cr0; - - if (vcpu->fpu_active) - return; - vcpu->fpu_active = 1; - cr0 = vmcs_readl(GUEST_CR0); - cr0 &= ~(X86_CR0_TS | X86_CR0_MP); - cr0 |= kvm_read_cr0_bits(vcpu, X86_CR0_TS | X86_CR0_MP); - vmcs_writel(GUEST_CR0, cr0); - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; - if (is_guest_mode(vcpu)) - vcpu->arch.cr0_guest_owned_bits &= - ~get_vmcs12(vcpu)->cr0_guest_host_mask; - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); -} - static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu); /* @@ -2377,33 +2347,6 @@ static inline unsigned long nested_read_cr4(struct vmcs12 *fields) (fields->cr4_read_shadow & fields->cr4_guest_host_mask); } -static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) -{ - /* Note that there is no vcpu->fpu_active = 0 here. The caller must - * set this *before* calling this function. - */ - vmx_decache_cr0_guest_bits(vcpu); - vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP); - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = 0; - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - if (is_guest_mode(vcpu)) { - /* - * L1's specified read shadow might not contain the TS bit, - * so now that we turned on shadowing of this bit, we need to - * set this bit of the shadow. Like in nested_vmx_run we need - * nested_read_cr0(vmcs12), but vmcs12->guest_cr0 is not yet - * up-to-date here because we just decached cr0.TS (and we'll - * only update vmcs12->guest_cr0 on nested exit). - */ - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); - vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) | - (vcpu->arch.cr0 & X86_CR0_TS); - vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12)); - } else - vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0); -} - static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags, save_rflags; @@ -3962,7 +3905,7 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) } vmcs_write16(sf->selector, var.selector); - vmcs_write32(sf->base, var.base); + vmcs_writel(sf->base, var.base); vmcs_write32(sf->limit, var.limit); vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(&var)); } @@ -4232,9 +4175,6 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (enable_ept) ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu); - if (!vcpu->fpu_active) - hw_cr0 |= X86_CR0_TS | X86_CR0_MP; - vmcs_writel(CR0_READ_SHADOW, cr0); vmcs_writel(GUEST_CR0, hw_cr0); vcpu->arch.cr0 = cr0; @@ -4953,7 +4893,7 @@ static bool vmx_get_enable_apicv(void) return enable_apicv; } -static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) +static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; @@ -4964,19 +4904,15 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmx->nested.pi_pending) { vmx->nested.pi_pending = false; if (!pi_test_and_clear_on(vmx->nested.pi_desc)) - return 0; + return; max_irr = find_last_bit( (unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr == 256) - return 0; + return; vapic_page = kmap(vmx->nested.virtual_apic_page); - if (!vapic_page) { - WARN_ON(1); - return -ENOMEM; - } __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); kunmap(vmx->nested.virtual_apic_page); @@ -4987,7 +4923,6 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) vmcs_write16(GUEST_INTR_STATUS, status); } } - return 0; } static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) @@ -5056,26 +4991,12 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (pi_test_and_set_pir(vector, &vmx->pi_desc)) return; - r = pi_test_and_set_on(&vmx->pi_desc); - kvm_make_request(KVM_REQ_EVENT, vcpu); - if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu)) - kvm_vcpu_kick(vcpu); -} - -static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (!pi_test_on(&vmx->pi_desc)) + /* If a previous notification has sent the IPI, nothing to do. */ + if (pi_test_and_set_on(&vmx->pi_desc)) return; - pi_clear_on(&vmx->pi_desc); - /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. - * But on x86 this is just a compiler barrier anyway. - */ - smp_mb__after_atomic(); - kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + if (!kvm_vcpu_trigger_posted_interrupt(vcpu)) + kvm_vcpu_kick(vcpu); } /* @@ -5236,10 +5157,8 @@ static void ept_set_mmio_spte_mask(void) /* * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). - * Also, magic bits (0x3ull << 62) is set to quickly identify mmio - * spte. */ - kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull); + kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE); } #define VMX_XSS_EXIT_BITMAP 0 @@ -5342,7 +5261,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_init(vmx, vmcs_config.vmentry_ctrl); - vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); + vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; + vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); + set_cr4_guest_host_mask(vmx); if (vmx_xsaves_supported()) @@ -5446,7 +5367,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); - vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); vpid_sync_context(vmx->vpid); @@ -5480,26 +5401,20 @@ static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_INTR_PENDING); } static void enable_nmi_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - if (!cpu_has_virtual_nmis() || vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & GUEST_INTR_STATE_STI) { enable_irq_window(vcpu); return; } - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_NMI_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_NMI_PENDING); } static void vmx_inject_irq(struct kvm_vcpu *vcpu) @@ -5725,11 +5640,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (is_nmi(intr_info)) return 1; /* already handled by vmx_vcpu_run() */ - if (is_no_device(intr_info)) { - vmx_fpu_activate(vcpu); - return 1; - } - if (is_invalid_opcode(intr_info)) { if (is_guest_mode(vcpu)) { kvm_queue_exception(vcpu, UD_VECTOR); @@ -5919,22 +5829,6 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) return kvm_set_cr4(vcpu, val); } -/* called to set cr0 as appropriate for clts instruction exit. */ -static void handle_clts(struct kvm_vcpu *vcpu) -{ - if (is_guest_mode(vcpu)) { - /* - * We get here when L2 did CLTS, and L1 didn't shadow CR0.TS - * but we did (!fpu_active). We need to keep GUEST_CR0.TS on, - * just pretend it's off (also in arch.cr0 for fpu_activate). - */ - vmcs_writel(CR0_READ_SHADOW, - vmcs_readl(CR0_READ_SHADOW) & ~X86_CR0_TS); - vcpu->arch.cr0 &= ~X86_CR0_TS; - } else - vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); -} - static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; @@ -5980,9 +5874,9 @@ static int handle_cr(struct kvm_vcpu *vcpu) } break; case 2: /* clts */ - handle_clts(vcpu); + WARN_ONCE(1, "Guest should always own CR0.TS"); + vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); trace_kvm_cr_write(0, kvm_read_cr0(vcpu)); - vmx_fpu_activate(vcpu); return kvm_skip_emulated_instruction(vcpu); case 1: /*mov from cr*/ switch (cr) { @@ -6152,18 +6046,14 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_apic_update_ppr(vcpu); return 1; } static int handle_interrupt_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - /* clear pending irq */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_INTR_PENDING); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -6374,15 +6264,22 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); trace_kvm_page_fault(gpa, exit_qualification); - /* it is a read fault? */ - error_code = (exit_qualification << 2) & PFERR_USER_MASK; - /* it is a write fault? */ - error_code |= exit_qualification & PFERR_WRITE_MASK; - /* It is a fetch fault? */ - error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK; - /* ept page table is present? */ - error_code |= (exit_qualification & 0x38) != 0; - + /* Is it a read fault? */ + error_code = (exit_qualification & EPT_VIOLATION_ACC_READ) + ? PFERR_USER_MASK : 0; + /* Is it a write fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE) + ? PFERR_WRITE_MASK : 0; + /* Is it a fetch fault? */ + error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR) + ? PFERR_FETCH_MASK : 0; + /* ept page table entry is present? */ + error_code |= (exit_qualification & + (EPT_VIOLATION_READABLE | EPT_VIOLATION_WRITABLE | + EPT_VIOLATION_EXECUTABLE)) + ? PFERR_PRESENT_MASK : 0; + + vcpu->arch.gpa_available = true; vcpu->arch.exit_qualification = exit_qualification; return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -6400,6 +6297,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) } ret = handle_mmio_page_fault(vcpu, gpa, true); + vcpu->arch.gpa_available = true; if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -6421,12 +6319,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) static int handle_nmi_window(struct kvm_vcpu *vcpu) { - u32 cpu_based_vm_exec_control; - - /* clear pending NMI */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_VIRTUAL_NMI_PENDING); ++vcpu->stat.nmi_window_exits; kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -6572,6 +6466,19 @@ static void wakeup_handler(void) spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); } +void vmx_enable_tdp(void) +{ + kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, + enable_ept_ad_bits ? VMX_EPT_ACCESS_BIT : 0ull, + enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, + 0ull, VMX_EPT_EXECUTABLE_MASK, + cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, + enable_ept_ad_bits ? 0ull : VMX_EPT_RWX_MASK); + + ept_set_mmio_spte_mask(); + kvm_enable_tdp(); +} + static __init int hardware_setup(void) { int r = -ENOMEM, i, msr; @@ -6651,8 +6558,10 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_ple()) ple_gap = 0; - if (!cpu_has_vmx_apicv()) + if (!cpu_has_vmx_apicv()) { enable_apicv = 0; + kvm_x86_ops->sync_pir_to_irr = NULL; + } if (cpu_has_vmx_tsc_scaling()) { kvm_has_tsc_control = true; @@ -6697,16 +6606,9 @@ static __init int hardware_setup(void) /* SELF-IPI */ vmx_disable_intercept_msr_x2apic(0x83f, MSR_TYPE_W, true); - if (enable_ept) { - kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK, - (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull, - (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull, - 0ull, VMX_EPT_EXECUTABLE_MASK, - cpu_has_vmx_ept_execute_only() ? - 0ull : VMX_EPT_READABLE_MASK); - ept_set_mmio_spte_mask(); - kvm_enable_tdp(); - } else + if (enable_ept) + vmx_enable_tdp(); + else kvm_disable_tdp(); update_ple_window_actual_max(); @@ -7085,13 +6987,18 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, } page = nested_get_page(vcpu, vmptr); - if (page == NULL || - *(u32 *)kmap(page) != VMCS12_REVISION) { + if (page == NULL) { nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); return kvm_skip_emulated_instruction(vcpu); } kunmap(page); + nested_release_page_clean(page); vmx->nested.vmxon_ptr = vmptr; break; case EXIT_REASON_VMCLEAR: @@ -7129,6 +7036,53 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, return 0; } +static int enter_vmx_operation(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs *shadow_vmcs; + + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); + if (!vmx->nested.cached_vmcs12) + goto out_cached_vmcs12; + + if (enable_shadow_vmcs) { + shadow_vmcs = alloc_vmcs(); + if (!shadow_vmcs) + goto out_shadow_vmcs; + /* mark vmcs as shadow */ + shadow_vmcs->revision_id |= (1u << 31); + /* init shadow vmcs */ + vmcs_clear(shadow_vmcs); + vmx->vmcs01.shadow_vmcs = shadow_vmcs; + } + + INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); + vmx->nested.vmcs02_num = 0; + + hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + + vmx->nested.vmxon = true; + return 0; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; +} + /* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even @@ -7139,9 +7093,9 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, */ static int handle_vmon(struct kvm_vcpu *vcpu) { + int ret; struct kvm_segment cs; struct vcpu_vmx *vmx = to_vmx(vcpu); - struct vmcs *shadow_vmcs; const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; @@ -7168,9 +7122,6 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) - return 1; - if (vmx->nested.vmxon) { nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); return kvm_skip_emulated_instruction(vcpu); @@ -7182,48 +7133,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (cpu_has_vmx_msr_bitmap()) { - vmx->nested.msr_bitmap = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx->nested.msr_bitmap) - goto out_msr_bitmap; - } - - vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); - if (!vmx->nested.cached_vmcs12) - goto out_cached_vmcs12; - - if (enable_shadow_vmcs) { - shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) - goto out_shadow_vmcs; - /* mark vmcs as shadow */ - shadow_vmcs->revision_id |= (1u << 31); - /* init shadow vmcs */ - vmcs_clear(shadow_vmcs); - vmx->vmcs01.shadow_vmcs = shadow_vmcs; - } - - INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); - vmx->nested.vmcs02_num = 0; - - hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); - vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; - - vmx->nested.vmxon = true; + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + return 1; + + ret = enter_vmx_operation(vcpu); + if (ret) + return ret; nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); - -out_shadow_vmcs: - kfree(vmx->nested.cached_vmcs12); - -out_cached_vmcs12: - free_page((unsigned long)vmx->nested.msr_bitmap); - -out_msr_bitmap: - return -ENOMEM; } /* @@ -7672,6 +7590,18 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } +static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) +{ + vmx->nested.current_vmptr = vmptr; + if (enable_shadow_vmcs) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); + vmcs_write64(VMCS_LINK_POINTER, + __pa(vmx->vmcs01.shadow_vmcs)); + vmx->nested.sync_shadow_vmcs = true; + } +} + /* Emulate the VMPTRLD instruction */ static int handle_vmptrld(struct kvm_vcpu *vcpu) { @@ -7702,7 +7632,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) } nested_release_vmcs12(vmx); - vmx->nested.current_vmptr = vmptr; vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; /* @@ -7711,14 +7640,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) */ memcpy(vmx->nested.cached_vmcs12, vmx->nested.current_vmcs12, VMCS12_SIZE); - - if (enable_shadow_vmcs) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_SHADOW_VMCS); - vmcs_write64(VMCS_LINK_POINTER, - __pa(vmx->vmcs01.shadow_vmcs)); - vmx->nested.sync_shadow_vmcs = true; - } + set_current_vmptr(vmx, vmptr); } nested_vmx_succeed(vcpu); @@ -8191,8 +8113,6 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_TASK_SWITCH: return true; case EXIT_REASON_CPUID: - if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return false; return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); @@ -8350,7 +8270,7 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) static void vmx_dump_sel(char *name, uint32_t sel) { pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", - name, vmcs_read32(sel), + name, vmcs_read16(sel), vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); @@ -8514,6 +8434,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 vectoring_info = vmx->idt_vectoring_info; trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + vcpu->arch.gpa_available = false; /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more @@ -8732,6 +8653,27 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } +static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int max_irr; + + WARN_ON(!vcpu->arch.apicv_active); + if (pi_test_on(&vmx->pi_desc)) { + pi_clear_on(&vmx->pi_desc); + /* + * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * But on x86 this is just a compiler barrier anyway. + */ + smp_mb__after_atomic(); + max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + } else { + max_irr = kvm_lapic_find_highest_irr(vcpu); + } + vmx_hwapic_irr_update(vcpu, max_irr); + return max_irr; +} + static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { if (!kvm_vcpu_apicv_active(vcpu)) @@ -8743,6 +8685,14 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } +static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + pi_clear_on(&vmx->pi_desc); + memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); +} + static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9588,17 +9538,16 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, kvm_inject_page_fault(vcpu, fault); } -static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, +static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12); + +static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); + u64 hpa; if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - if (!PAGE_ALIGNED(vmcs12->apic_access_addr) || - vmcs12->apic_access_addr >> maxphyaddr) - return false; - /* * Translate L1 physical address to host physical * address for vmcs02. Keep the page pinned, so this @@ -9609,59 +9558,80 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, nested_release_page(vmx->nested.apic_access_page); vmx->nested.apic_access_page = nested_get_page(vcpu, vmcs12->apic_access_addr); + /* + * If translation failed, no matter: This feature asks + * to exit when accessing the given address, and if it + * can never be accessed, this feature won't do + * anything anyway. + */ + if (vmx->nested.apic_access_page) { + hpa = page_to_phys(vmx->nested.apic_access_page); + vmcs_write64(APIC_ACCESS_ADDR, hpa); + } else { + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + } + } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && + cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + kvm_vcpu_reload_apic_access_page(vcpu); } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { - if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) || - vmcs12->virtual_apic_page_addr >> maxphyaddr) - return false; - if (vmx->nested.virtual_apic_page) /* shouldn't happen */ nested_release_page(vmx->nested.virtual_apic_page); vmx->nested.virtual_apic_page = nested_get_page(vcpu, vmcs12->virtual_apic_page_addr); /* - * Failing the vm entry is _not_ what the processor does - * but it's basically the only possibility we have. - * We could still enter the guest if CR8 load exits are - * enabled, CR8 store exits are enabled, and virtualize APIC - * access is disabled; in this case the processor would never - * use the TPR shadow and we could simply clear the bit from - * the execution control. But such a configuration is useless, - * so let's keep the code simple. + * If translation failed, VM entry will fail because + * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull. + * Failing the vm entry is _not_ what the processor + * does but it's basically the only possibility we + * have. We could still enter the guest if CR8 load + * exits are enabled, CR8 store exits are enabled, and + * virtualize APIC access is disabled; in this case + * the processor would never use the TPR shadow and we + * could simply clear the bit from the execution + * control. But such a configuration is useless, so + * let's keep the code simple. */ - if (!vmx->nested.virtual_apic_page) - return false; + if (vmx->nested.virtual_apic_page) { + hpa = page_to_phys(vmx->nested.virtual_apic_page); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa); + } } if (nested_cpu_has_posted_intr(vmcs12)) { - if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) || - vmcs12->posted_intr_desc_addr >> maxphyaddr) - return false; - if (vmx->nested.pi_desc_page) { /* shouldn't happen */ kunmap(vmx->nested.pi_desc_page); nested_release_page(vmx->nested.pi_desc_page); } vmx->nested.pi_desc_page = nested_get_page(vcpu, vmcs12->posted_intr_desc_addr); - if (!vmx->nested.pi_desc_page) - return false; - vmx->nested.pi_desc = (struct pi_desc *)kmap(vmx->nested.pi_desc_page); if (!vmx->nested.pi_desc) { nested_release_page_clean(vmx->nested.pi_desc_page); - return false; + return; } vmx->nested.pi_desc = (struct pi_desc *)((void *)vmx->nested.pi_desc + (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); + vmcs_write64(POSTED_INTR_DESC_ADDR, + page_to_phys(vmx->nested.pi_desc_page) + + (unsigned long)(vmcs12->posted_intr_desc_addr & + (PAGE_SIZE - 1))); } - - return true; + if (cpu_has_vmx_msr_bitmap() && + nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; + else + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_USE_MSR_BITMAPS); } static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) @@ -9730,11 +9700,6 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, return false; } msr_bitmap_l1 = (unsigned long *)kmap(page); - if (!msr_bitmap_l1) { - nested_release_page_clean(page); - WARN_ON(1); - return false; - } memset(msr_bitmap_l0, 0xff, PAGE_SIZE); @@ -9982,7 +9947,7 @@ static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val) * is assigned to entry_failure_code on failure. */ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, - unsigned long *entry_failure_code) + u32 *entry_failure_code) { if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) { if (!nested_cr3_valid(vcpu, cr3)) { @@ -10022,7 +9987,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - unsigned long *entry_failure_code) + bool from_vmentry, u32 *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; @@ -10065,21 +10030,26 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) { + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - vmcs12->vm_entry_intr_info_field); - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs12->vm_entry_exception_error_code); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs12->vm_entry_instruction_len); - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, - vmcs12->guest_interruptibility_info); + if (from_vmentry) { + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, + vmcs12->vm_entry_intr_info_field); + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, + vmcs12->vm_entry_exception_error_code); + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, + vmcs12->vm_entry_instruction_len); + vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, + vmcs12->guest_interruptibility_info); + } else { + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); + } vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, @@ -10108,12 +10078,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); - vmcs_write64(POSTED_INTR_DESC_ADDR, - page_to_phys(vmx->nested.pi_desc_page) + - (unsigned long)(vmcs12->posted_intr_desc_addr & - (PAGE_SIZE - 1))); - } else + } else { exec_control &= ~PIN_BASED_POSTED_INTR; + } vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); @@ -10158,26 +10125,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; - if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) { - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ - if (!vmx->nested.apic_access_page) - exec_control &= - ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - else - vmcs_write64(APIC_ACCESS_ADDR, - page_to_phys(vmx->nested.apic_access_page)); - } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - exec_control |= - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - kvm_vcpu_reload_apic_access_page(vcpu); - } - if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0); @@ -10192,6 +10139,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0; + + /* + * Write an illegal value to APIC_ACCESS_ADDR. Later, + * nested_get_vmcs12_pages will either fix it up or + * remove the VM execution control. + */ + if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) + vmcs_write64(APIC_ACCESS_ADDR, -1ull); + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } @@ -10228,19 +10184,16 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control &= ~CPU_BASED_TPR_SHADOW; exec_control |= vmcs12->cpu_based_vm_exec_control; + /* + * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if + * nested_get_vmcs12_pages can't fix it up, the illegal value + * will result in a VM entry failure. + */ if (exec_control & CPU_BASED_TPR_SHADOW) { - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - page_to_phys(vmx->nested.virtual_apic_page)); + vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull); vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold); } - if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS && - nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) - ; /* MSR_BITMAP will be set by following vmx_set_efer. */ - else - exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; - /* * Merging of IO bitmap not currently supported. * Rather, exit every time. @@ -10272,16 +10225,18 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) { + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) { vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; - } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); - + } set_cr4_guest_host_mask(vmx); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) + if (from_vmentry && + vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) @@ -10320,8 +10275,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } /* - * This sets GUEST_CR0 to vmcs12->guest_cr0, with possibly a modified - * TS bit (for lazy fpu) and bits which we consider mandatory enabled. + * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those + * bits which we consider mandatory enabled. * The CR0_READ_SHADOW is what L2 should have expected to read given * the specifications by L1; It's not enough to take * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we we @@ -10333,7 +10288,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_set_cr4(vcpu, vmcs12->guest_cr4); vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) + if (from_vmentry && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) vcpu->arch.efer = vmcs12->guest_ia32_efer; else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) vcpu->arch.efer |= (EFER_LMA | EFER_LME); @@ -10367,73 +10323,22 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, return 0; } -/* - * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 - * for running an L2 nested guest. - */ -static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) +static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - int cpu; - struct loaded_vmcs *vmcs02; - bool ia32e; - u32 msr_entry_idx; - unsigned long exit_qualification; - - if (!nested_vmx_check_permission(vcpu)) - return 1; - - if (!nested_vmx_check_vmcs12(vcpu)) - goto out; - - vmcs12 = get_vmcs12(vcpu); - - if (enable_shadow_vmcs) - copy_shadow_to_vmcs12(vmx); - - /* - * The nested entry process starts with enforcing various prerequisites - * on vmcs12 as required by the Intel SDM, and act appropriately when - * they fail: As the SDM explains, some conditions should cause the - * instruction to fail, while others will cause the instruction to seem - * to succeed, but return an EXIT_REASON_INVALID_STATE. - * To speed up the normal (success) code path, we should avoid checking - * for misconfigurations which will anyway be caught by the processor - * when using the merged vmcs02. - */ - if (vmcs12->launch_state == launch) { - nested_vmx_failValid(vcpu, - launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS - : VMXERR_VMRESUME_NONLAUNCHED_VMCS); - goto out; - } if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE && - vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; - if (nested_vmx_check_apicv_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } - - if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control, vmx->nested.nested_vmx_procbased_ctls_low, @@ -10450,28 +10355,30 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) !vmx_control_verify(vmcs12->vm_entry_controls, vmx->nested.nested_vmx_entry_ctls_low, vmx->nested.nested_vmx_entry_ctls_high)) - { - nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); - goto out; - } + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) || !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || - !nested_cr3_valid(vcpu, vmcs12->host_cr3)) { - nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); - goto out; - } + !nested_cr3_valid(vcpu, vmcs12->host_cr3)) + return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + + return 0; +} + +static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 *exit_qual) +{ + bool ia32e; + + *exit_qual = ENTRY_FAIL_DEFAULT; if (!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0) || - !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + !nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)) return 1; - } - if (vmcs12->vmcs_link_pointer != -1ull) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_VMCS_LINK_PTR); + + if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_SHADOW_VMCS) && + vmcs12->vmcs_link_pointer != -1ull) { + *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR; return 1; } @@ -10484,16 +10391,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * to bit 8 (LME) if bit 31 in the CR0 field (corresponding to * CR0.PG) is 1. */ - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) { + if (to_vmx(vcpu)->nested.nested_run_pending && + (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) { ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer) || ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA) || ((vmcs12->guest_cr0 & X86_CR0_PG) && - ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + ia32e != !!(vmcs12->guest_ia32_efer & EFER_LME))) return 1; - } } /* @@ -10507,28 +10412,26 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0; if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) || ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) || - ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) { - nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT); + ia32e != !!(vmcs12->host_ia32_efer & EFER_LME)) return 1; - } } - /* - * We're finally done with prerequisite checking, and can start with - * the nested entry. - */ + return 0; +} + +static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct loaded_vmcs *vmcs02; + int cpu; + u32 msr_entry_idx; + u32 exit_qual; vmcs02 = nested_get_current_vmcs02(vmx); if (!vmcs02) return -ENOMEM; - /* - * After this point, the trap flag no longer triggers a singlestep trap - * on the vm entry instructions. Don't call - * kvm_skip_emulated_instruction. - */ - skip_emulated_instruction(vcpu); enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -10543,14 +10446,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmx_segment_cache_clear(vmx); - if (prepare_vmcs02(vcpu, vmcs12, &exit_qualification)) { + if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) { leave_guest_mode(vcpu); vmx_load_vmcs01(vcpu); nested_vmx_entry_failure(vcpu, vmcs12, - EXIT_REASON_INVALID_STATE, exit_qualification); + EXIT_REASON_INVALID_STATE, exit_qual); return 1; } + nested_get_vmcs12_pages(vcpu, vmcs12); + msr_entry_idx = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count); @@ -10564,17 +10469,90 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_vcpu_halt(vcpu); - - vmx->nested.nested_run_pending = 1; - /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ + return 0; +} + +/* + * nested_vmx_run() handles a nested entry, i.e., a VMLAUNCH or VMRESUME on L1 + * for running an L2 nested guest. + */ +static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) +{ + struct vmcs12 *vmcs12; + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 exit_qual; + int ret; + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (!nested_vmx_check_vmcs12(vcpu)) + goto out; + + vmcs12 = get_vmcs12(vcpu); + + if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + + /* + * The nested entry process starts with enforcing various prerequisites + * on vmcs12 as required by the Intel SDM, and act appropriately when + * they fail: As the SDM explains, some conditions should cause the + * instruction to fail, while others will cause the instruction to seem + * to succeed, but return an EXIT_REASON_INVALID_STATE. + * To speed up the normal (success) code path, we should avoid checking + * for misconfigurations which will anyway be caught by the processor + * when using the merged vmcs02. + */ + if (vmcs12->launch_state == launch) { + nested_vmx_failValid(vcpu, + launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS + : VMXERR_VMRESUME_NONLAUNCHED_VMCS); + goto out; + } + + ret = check_vmentry_prereqs(vcpu, vmcs12); + if (ret) { + nested_vmx_failValid(vcpu, ret); + goto out; + } + + /* + * After this point, the trap flag no longer triggers a singlestep trap + * on the vm entry instructions; don't call kvm_skip_emulated_instruction. + * This is not 100% correct; for performance reasons, we delegate most + * of the checks on host state to the processor. If those fail, + * the singlestep trap is missed. + */ + skip_emulated_instruction(vcpu); + + ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual); + if (ret) { + nested_vmx_entry_failure(vcpu, vmcs12, + EXIT_REASON_INVALID_STATE, exit_qual); + return 1; + } + + /* + * We're finally done with prerequisite checking, and can start with + * the nested entry. + */ + + ret = enter_vmx_non_root_mode(vcpu, true); + if (ret) + return ret; + + if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + return kvm_vcpu_halt(vcpu); + + vmx->nested.nested_run_pending = 1; + return 1; out: @@ -10696,7 +10674,8 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } - return vmx_complete_nested_posted_interrupt(vcpu); + vmx_complete_nested_posted_interrupt(vcpu); + return 0; } static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) @@ -10714,21 +10693,13 @@ static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) } /* - * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits - * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), - * and this function updates it to reflect the changes to the guest state while - * L2 was running (and perhaps made some exits which were handled directly by L0 - * without going back to L1), and to reflect the exit reason. - * Note that we do not have to copy here all VMCS fields, just those that - * could have changed by the L2 guest or the exit - i.e., the guest-state and - * exit-information fields only. Other fields are modified by L1 with VMWRITE, - * which already writes to vmcs12 directly. + * Update the guest state fields of vmcs12 to reflect changes that + * occurred while L2 was running. (The "IA-32e mode guest" bit of the + * VM-entry controls is also updated, since this is really a guest + * state bit.) */ -static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - u32 exit_reason, u32 exit_intr_info, - unsigned long exit_qualification) +static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - /* update guest state fields: */ vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -10834,6 +10805,25 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); if (nested_cpu_has_xsaves(vmcs12)) vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); +} + +/* + * prepare_vmcs12 is part of what we need to do when the nested L2 guest exits + * and we want to prepare to run its L1 parent. L1 keeps a vmcs for L2 (vmcs12), + * and this function updates it to reflect the changes to the guest state while + * L2 was running (and perhaps made some exits which were handled directly by L0 + * without going back to L1), and to reflect the exit reason. + * Note that we do not have to copy here all VMCS fields, just those that + * could have changed by the L2 guest or the exit - i.e., the guest-state and + * exit-information fields only. Other fields are modified by L1 with VMWRITE, + * which already writes to vmcs12 directly. + */ +static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + u32 exit_reason, u32 exit_intr_info, + unsigned long exit_qualification) +{ + /* update guest state fields: */ + sync_vmcs12(vcpu, vmcs12); /* update exit information fields: */ @@ -10884,7 +10874,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct kvm_segment seg; - unsigned long entry_failure_code; + u32 entry_failure_code; if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; @@ -10899,24 +10889,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmx_set_rflags(vcpu, X86_EFLAGS_FIXED); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't - * actually changed, because it depends on the current state of - * fpu_active (which may have changed). - * Note that vmx_set_cr0 refers to efer set above. + * actually changed, because vmx_set_cr0 refers to efer set above. + * + * CR0_GUEST_HOST_MASK is already set in the original vmcs01 + * (KVM doesn't change it); */ + vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; vmx_set_cr0(vcpu, vmcs12->host_cr0); - /* - * If we did fpu_activate()/fpu_deactivate() during L2's run, we need - * to apply the same changes to L1's vmcs. We just set cr0 correctly, - * but we also need to update cr0_guest_host_mask and exception_bitmap. - */ - update_exception_bitmap(vcpu); - vcpu->arch.cr0_guest_owned_bits = (vcpu->fpu_active ? X86_CR0_TS : 0); - vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - /* - * Note that CR4_GUEST_HOST_MASK is already set in the original vmcs01 - * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask(); - */ + /* Same as above - no reason to call set_cr4_guest_host_mask(). */ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); kvm_set_cr4(vcpu, vmcs12->host_cr4); @@ -11545,9 +11526,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_pkru = vmx_get_pkru, - .fpu_activate = vmx_fpu_activate, - .fpu_deactivate = vmx_fpu_deactivate, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, @@ -11572,6 +11550,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, + .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .sync_pir_to_irr = vmx_sync_pir_to_irr, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2f22810a7e0c..b2a4b11274b0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -180,6 +180,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, { "irq_injections", VCPU_STAT(irq_injections) }, { "nmi_injections", VCPU_STAT(nmi_injections) }, + { "req_event", VCPU_STAT(req_event) }, { "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) }, { "mmu_pte_write", VM_STAT(mmu_pte_write) }, { "mmu_pte_updated", VM_STAT(mmu_pte_updated) }, @@ -190,6 +191,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, { "largepages", VM_STAT(lpages) }, + { "max_mmu_page_hash_collisions", + VM_STAT(max_mmu_page_hash_collisions) }, { NULL } }; @@ -1139,6 +1142,7 @@ struct pvclock_gtod_data { u64 boot_ns; u64 nsec_base; + u64 wall_time_sec; }; static struct pvclock_gtod_data pvclock_gtod_data; @@ -1162,6 +1166,8 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->boot_ns = boot_ns; vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->wall_time_sec = tk->xtime_sec; + write_seqcount_end(&vdata->seq); } #endif @@ -1623,6 +1629,28 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now) return mode; } +static int do_realtime(struct timespec *ts, u64 *cycle_now) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + mode = gtod->clock.vclock_mode; + ts->tv_sec = gtod->wall_time_sec; + ns = gtod->nsec_base; + ns += vgettsc(cycle_now); + ns >>= gtod->clock.shift; + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + + ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns); + ts->tv_nsec = ns; + + return mode; +} + /* returns true if host is using tsc clocksource */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) { @@ -1632,6 +1660,17 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; } + +/* returns true if host is using tsc clocksource */ +static bool kvm_get_walltime_and_clockread(struct timespec *ts, + u64 *cycle_now) +{ + /* checked again under seqlock below */ + if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + return false; + + return do_realtime(ts, cycle_now) == VCLOCK_TSC; +} #endif /* @@ -1772,7 +1811,7 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info guest_hv_clock; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, + if (unlikely(kvm_vcpu_read_guest_cached(v, &vcpu->pv_time, &guest_hv_clock, sizeof(guest_hv_clock)))) return; @@ -1793,9 +1832,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); smp_wmb(); @@ -1809,16 +1848,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); smp_wmb(); vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_vcpu_write_guest_cached(v, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); } static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -2051,7 +2090,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 0; } - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apf.data, gpa, sizeof(u32))) return 1; @@ -2070,7 +2109,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + if (unlikely(kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) return; @@ -2081,7 +2120,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu) vcpu->arch.st.steal.version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); smp_wmb(); @@ -2090,14 +2129,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu) vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); smp_wmb(); vcpu->arch.st.steal.version += 1; - kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)); } @@ -2202,7 +2241,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) vcpu->arch.pv_time_enabled = false; @@ -2223,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & KVM_STEAL_RESERVED_MASK) return 1; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime, + if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.st.stime, data & KVM_STEAL_VALID_BITS, sizeof(struct kvm_steal_time))) return 1; @@ -2633,6 +2672,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_DISABLE_QUIRKS: case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: + case KVM_CAP_IMMEDIATE_EXIT: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -2836,7 +2876,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) vcpu->arch.st.steal.preempted = 1; - kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, + kvm_vcpu_write_guest_offset_cached(vcpu, &vcpu->arch.st.stime, &vcpu->arch.st.steal.preempted, offsetof(struct kvm_steal_time, preempted), sizeof(vcpu->arch.st.steal.preempted)); @@ -2870,7 +2910,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (vcpu->arch.apicv_active) + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); @@ -3182,6 +3222,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* @@ -3342,6 +3383,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, switch (cap->cap) { case KVM_CAP_HYPERV_SYNIC: + if (!irqchip_in_kernel(vcpu->kvm)) + return -EINVAL; return kvm_hv_activate_synic(vcpu); default: return -EINVAL; @@ -3894,7 +3937,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, goto split_irqchip_unlock; /* Pairs with irqchip_in_kernel. */ smp_wmb(); - kvm->arch.irqchip_split = true; + kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; r = 0; split_irqchip_unlock: @@ -3957,40 +4000,41 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); break; case KVM_CREATE_IRQCHIP: { - struct kvm_pic *vpic; - mutex_lock(&kvm->lock); + r = -EEXIST; - if (kvm->arch.vpic) + if (irqchip_in_kernel(kvm)) goto create_irqchip_unlock; + r = -EINVAL; if (kvm->created_vcpus) goto create_irqchip_unlock; - r = -ENOMEM; - vpic = kvm_create_pic(kvm); - if (vpic) { - r = kvm_ioapic_init(kvm); - if (r) { - mutex_lock(&kvm->slots_lock); - kvm_destroy_pic(vpic); - mutex_unlock(&kvm->slots_lock); - goto create_irqchip_unlock; - } - } else + + r = kvm_pic_init(kvm); + if (r) + goto create_irqchip_unlock; + + r = kvm_ioapic_init(kvm); + if (r) { + mutex_lock(&kvm->slots_lock); + kvm_pic_destroy(kvm); + mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; + } + r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->irq_lock); kvm_ioapic_destroy(kvm); - kvm_destroy_pic(vpic); + kvm_pic_destroy(kvm); mutex_unlock(&kvm->irq_lock); mutex_unlock(&kvm->slots_lock); goto create_irqchip_unlock; } - /* Write kvm->irq_routing before kvm->arch.vpic. */ + /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); - kvm->arch.vpic = vpic; + kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -4026,7 +4070,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) + if (!irqchip_kernel(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -4050,7 +4094,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) + if (!irqchip_kernel(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); if (r) @@ -4459,6 +4503,21 @@ out: } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva, + gpa_t gpa, bool write) +{ + /* For APIC access vmexit */ + if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + return 1; + + if (vcpu_match_mmio_gpa(vcpu, gpa)) { + trace_vcpu_match_mmio(gva, gpa, write, true); + return 1; + } + + return 0; +} + static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) @@ -4485,16 +4544,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, if (*gpa == UNMAPPED_GVA) return -1; - /* For APIC access vmexit */ - if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - return 1; - - if (vcpu_match_mmio_gpa(vcpu, *gpa)) { - trace_vcpu_match_mmio(gva, *gpa, write, true); - return 1; - } - - return 0; + return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write); } int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -4591,6 +4641,22 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, int handled, ret; bool write = ops->write; struct kvm_mmio_fragment *frag; + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + /* + * If the exit was due to a NPF we may already have a GPA. + * If the GPA is present, use it to avoid the GVA to GPA table walk. + * Note, this cannot be used on string operations since string + * operation using rep will only have the initial GPA from the NPF + * occurred. + */ + if (vcpu->arch.gpa_available && + emulator_can_use_gpa(ctxt) && + vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) && + (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) { + gpa = exception->address; + goto mmio; + } ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write); @@ -5607,6 +5673,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, } restart: + /* Save the faulting GPA (cr2) in the address field */ + ctxt->exception.address = cr2; + r = x86_emulate_insn(ctxt); if (r == EMULATION_INTERCEPTED) @@ -5921,9 +5990,6 @@ static void kvm_set_mmio_spte_mask(void) /* Mask the reserved physical address bits. */ mask = rsvd_bits(maxphyaddr, 51); - /* Bit 62 is always reserved for 32bit host. */ - mask |= 0x3ull << 62; - /* Set the present bit. */ mask |= 1ull; @@ -6022,7 +6088,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, - PT_PRESENT_MASK); + PT_PRESENT_MASK, 0); kvm_timer_init(); perf_register_guest_info_callbacks(&kvm_guest_cbs); @@ -6045,6 +6111,7 @@ out: void kvm_arch_exit(void) { + kvm_lapic_exit(); perf_unregister_guest_info_callbacks(&kvm_guest_cbs); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -6083,6 +6150,35 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +#ifdef CONFIG_X86_64 +static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, + unsigned long clock_type) +{ + struct kvm_clock_pairing clock_pairing; + struct timespec ts; + u64 cycle; + int ret; + + if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) + return -KVM_EOPNOTSUPP; + + if (kvm_get_walltime_and_clockread(&ts, &cycle) == false) + return -KVM_EOPNOTSUPP; + + clock_pairing.sec = ts.tv_sec; + clock_pairing.nsec = ts.tv_nsec; + clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); + clock_pairing.flags = 0; + + ret = 0; + if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, + sizeof(struct kvm_clock_pairing))) + ret = -KVM_EFAULT; + + return ret; +} +#endif + /* * kvm_pv_kick_cpu_op: Kick a vcpu. * @@ -6147,6 +6243,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); ret = 0; break; +#ifdef CONFIG_X86_64 + case KVM_HC_CLOCK_PAIRING: + ret = kvm_pv_clock_pairing(vcpu, a0, a1); + break; +#endif default: ret = -KVM_ENOSYS; break; @@ -6168,7 +6269,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) kvm_x86_ops->patch_hypercall(vcpu, instruction); - return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); + return emulator_write_emulated(ctxt, rip, instruction, 3, + &ctxt->exception); } static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) @@ -6559,7 +6661,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (vcpu->arch.apicv_active) + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -6650,10 +6752,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } - if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) { - vcpu->fpu_active = 0; - kvm_x86_ops->fpu_deactivate(vcpu); - } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ vcpu->arch.apf.halted = true; @@ -6713,21 +6811,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_hv_process_stimers(vcpu); } - /* - * KVM_REQ_EVENT is not set when posted interrupts are set by - * VT-d hardware, so we have to update RVI unconditionally. - */ - if (kvm_lapic_enabled(vcpu)) { - /* - * Update architecture specific hints for APIC - * virtual interrupt delivery. - */ - if (vcpu->arch.apicv_active) - kvm_x86_ops->hwapic_irr_update(vcpu, - kvm_lapic_find_highest_irr(vcpu)); - } - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + ++vcpu->stat.req_event; kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { r = 1; @@ -6768,22 +6853,40 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); - if (vcpu->fpu_active) - kvm_load_guest_fpu(vcpu); + kvm_load_guest_fpu(vcpu); + + /* + * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt + * IPI are then delayed after guest entry, which ensures that they + * result in virtual interrupt delivery. + */ + local_irq_disable(); vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); /* - * We should set ->mode before check ->requests, - * Please see the comment in kvm_make_all_cpus_request. - * This also orders the write to mode from any reads - * to the page tables done while the VCPU is running. - * Please see the comment in kvm_flush_remote_tlbs. + * 1) We should set ->mode before checking ->requests. Please see + * the comment in kvm_make_all_cpus_request. + * + * 2) For APICv, we should set ->mode before checking PIR.ON. This + * pairs with the memory barrier implicit in pi_test_and_set_on + * (see vmx_deliver_posted_interrupt). + * + * 3) This also orders the write to mode from any reads to the page + * tables done while the VCPU is running. Please see the comment + * in kvm_flush_remote_tlbs. */ smp_mb__after_srcu_read_unlock(); - local_irq_disable(); + /* + * This handles the case where a posted interrupt was + * notified with kvm_vcpu_kick. + */ + if (kvm_lapic_enabled(vcpu)) { + if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + } if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests || need_resched() || signal_pending(current)) { @@ -6922,6 +7025,9 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) + kvm_x86_ops->check_nested_events(vcpu, false); + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted); } @@ -7093,7 +7199,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); - r = vcpu_run(vcpu); + if (kvm_run->immediate_exit) + r = -EINTR; + else + r = vcpu_run(vcpu); out: post_kvm_run_save(vcpu); @@ -8288,9 +8397,6 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { - if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) - kvm_x86_ops->check_nested_events(vcpu, false); - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } @@ -8427,9 +8533,8 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) { - - return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, - sizeof(val)); + return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apf.data, &val, + sizeof(val)); } void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 073d1f1a620b..a8e91ae89fb3 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -156,13 +156,13 @@ EXPORT_SYMBOL(__delay); inline void __const_udelay(unsigned long xloops) { + unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy; int d0; xloops *= 4; asm("mull %%edx" :"=d" (xloops), "=&a" (d0) - :"1" (xloops), "0" - (this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4))); + :"1" (xloops), "0" (lpj * (HZ / 4))); __delay(++xloops); } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index ea9c49adaa1f..58b5bee7ea27 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -15,8 +15,10 @@ #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/init.h> +#include <linux/sched.h> #include <linux/seq_file.h> +#include <asm/kasan.h> #include <asm/pgtable.h> /* @@ -50,6 +52,10 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, +#ifdef CONFIG_KASAN + KASAN_SHADOW_START_NR, + KASAN_SHADOW_END_NR, +#endif # ifdef CONFIG_X86_ESPFIX64 ESPFIX_START_NR, # endif @@ -75,6 +81,10 @@ static struct addr_marker address_markers[] = { { 0/* PAGE_OFFSET */, "Low Kernel Mapping" }, { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/* VMEMMAP_START */, "Vmemmap" }, +#ifdef CONFIG_KASAN + { KASAN_SHADOW_START, "KASAN shadow" }, + { KASAN_SHADOW_END, "KASAN shadow end" }, +#endif # ifdef CONFIG_X86_ESPFIX64 { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, # endif @@ -326,18 +336,31 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, #if PTRS_PER_PUD > 1 +/* + * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y + * KASAN fills page tables with the same values. Since there is no + * point in checking page table more than once we just skip repeated + * entries. This saves us dozens of seconds during boot. + */ +static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx) +{ + return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud)); +} + static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P) { int i; pud_t *start; pgprotval_t prot; + pud_t *prev_pud = NULL; start = (pud_t *) pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); - if (!pud_none(*start)) { + if (!pud_none(*start) && + !pud_already_checked(prev_pud, start, st->check_wx)) { if (pud_large(*start) || !pud_present(*start)) { prot = pud_flags(*start); note_page(m, st, __pgprot(prot), 2); @@ -348,6 +371,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, } else note_page(m, st, __pgprot(0), 2); + prev_pud = start; start++; } } @@ -406,6 +430,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, } else note_page(m, &st, __pgprot(0), 1); + cond_resched(); start++; } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 0d4fb3ebbbac..99c7805a9693 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -154,14 +154,12 @@ static inline void get_head_page_multiple(struct page *page, int nr) SetPageReferenced(page); } -static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, +static int __gup_device_huge(unsigned long pfn, unsigned long addr, unsigned long end, struct page **pages, int *nr) { int nr_start = *nr; - unsigned long pfn = pmd_pfn(pmd); struct dev_pagemap *pgmap = NULL; - pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; do { struct page *page = pfn_to_page(pfn); @@ -180,6 +178,24 @@ static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, return 1; } +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + unsigned long fault_pfn; + + fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + return __gup_device_huge(fault_pfn, addr, end, pages, nr); +} + +static int __gup_device_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + unsigned long fault_pfn; + + fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + return __gup_device_huge(fault_pfn, addr, end, pages, nr); +} + static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -251,9 +267,13 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, if (!pte_allows_gup(pud_val(pud), write)) return 0; + + VM_BUG_ON(!pfn_valid(pud_pfn(pud))); + if (pud_devmap(pud)) + return __gup_device_huge_pud(pud, addr, end, pages, nr); + /* hugepages are never "special" */ VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pud_pfn(pud))); refs = 0; head = pud_page(pud); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index af85b686a7b0..97346f987ef2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -679,7 +679,7 @@ static void __meminit free_pagetable(struct page *page, int order) if (PageReserved(page)) { __ClearPageReserved(page); - magic = (unsigned long)page->lru.next; + magic = (unsigned long)page->freelist; if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) { while (nr_pages--) put_page_bootmem(page++); diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 324e5713d386..c98079684bdb 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -51,7 +51,7 @@ static unsigned long mpx_mmap(unsigned long len) down_write(&mm->mmap_sem); addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate); + MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate, NULL); up_write(&mm->mmap_sem); if (populate) mm_populate(addr, populate); @@ -293,7 +293,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) * We were not able to extract an address from the instruction, * probably because there was something invalid in it. */ - if (info->si_addr == (void *)-1) { + if (info->si_addr == (void __user *)-1) { err = -EINVAL; goto err_out; } @@ -796,7 +796,7 @@ static noinline int zap_bt_entries_mapping(struct mm_struct *mm, return -EINVAL; len = min(vma->vm_end, end) - addr; - zap_page_range(vma, addr, len, NULL); + zap_page_range(vma, addr, len); trace_mpx_unmap_zap(addr, addr+len); vma = vma->vm_next; @@ -893,7 +893,7 @@ static int unmap_entire_bt(struct mm_struct *mm, * avoid recursion, do_munmap() will check whether it comes * from one bounds table through VM_MPX flag. */ - return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm)); + return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm), NULL); } static int try_unmap_single_bt(struct mm_struct *mm, diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 5a287e523eab..28d42130243c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -214,7 +214,20 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, int in_flags, struct page **pages) { unsigned int i, level; +#ifdef CONFIG_PREEMPT + /* + * Avoid wbinvd() because it causes latencies on all CPUs, + * regardless of any CPU isolation that may be in effect. + * + * This should be extended for CAT enabled systems independent of + * PREEMPT because wbinvd() does not respect the CAT partitions and + * this is exposed to unpriviledged users through the graphics + * subsystem. + */ + unsigned long do_wbinvd = 0; +#else unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ +#endif BUG_ON(irqs_disabled()); diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 159b52ccd600..d76485b22824 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -47,7 +47,7 @@ static u64 get_subtree_max_end(struct rb_node *node) { u64 ret = 0; if (node) { - struct memtype *data = container_of(node, struct memtype, rb); + struct memtype *data = rb_entry(node, struct memtype, rb); ret = data->subtree_max_end; } return ret; @@ -79,7 +79,7 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root, struct memtype *last_lower = NULL; while (node) { - struct memtype *data = container_of(node, struct memtype, rb); + struct memtype *data = rb_entry(node, struct memtype, rb); if (get_subtree_max_end(node->rb_left) > start) { /* Lowest overlap if any must be on left side */ @@ -121,7 +121,7 @@ static struct memtype *memtype_rb_match(struct rb_root *root, node = rb_next(&match->rb); if (node) - match = container_of(node, struct memtype, rb); + match = rb_entry(node, struct memtype, rb); else match = NULL; } @@ -150,7 +150,7 @@ static int memtype_rb_check_conflict(struct rb_root *root, node = rb_next(&match->rb); while (node) { - match = container_of(node, struct memtype, rb); + match = rb_entry(node, struct memtype, rb); if (match->start >= end) /* Checked all possible matches */ goto success; @@ -181,7 +181,7 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata) struct rb_node *parent = NULL; while (*node) { - struct memtype *data = container_of(*node, struct memtype, rb); + struct memtype *data = rb_entry(*node, struct memtype, rb); parent = *node; if (data->subtree_max_end < newdata->end) @@ -270,7 +270,7 @@ int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos) } if (node) { /* pos == i */ - struct memtype *this = container_of(node, struct memtype, rb); + struct memtype *this = rb_entry(node, struct memtype, rb); *out = *this; return 0; } else { diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3feec5af4e67..6cbdff26bb96 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -445,6 +445,26 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, return changed; } + +int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp, pud_t entry, int dirty) +{ + int changed = !pud_same(*pudp, entry); + + VM_BUG_ON(address & ~HPAGE_PUD_MASK); + + if (changed && dirty) { + *pudp = entry; + /* + * We had a write-protection fault here and changed the pud + * to to more permissive. No need to flush the TLB for that, + * #PF is architecturally guaranteed to do that and in the + * worst-case we'll generate a spurious fault. + */ + } + + return changed; +} #endif int ptep_test_and_clear_young(struct vm_area_struct *vma, @@ -474,6 +494,17 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, return ret; } +int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp) +{ + int ret = 0; + + if (pud_young(*pudp)) + ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, + (unsigned long *)pudp); + + return ret; +} #endif int ptep_clear_flush_young(struct vm_area_struct *vma, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e76d1af60f7a..32322ce9b405 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1067,13 +1067,13 @@ common_load: ilen = prog - temp; if (ilen > BPF_MAX_INSN_SIZE) { - pr_err("bpf_jit_compile fatal insn size error\n"); + pr_err("bpf_jit: fatal insn size error\n"); return -EFAULT; } if (image) { if (unlikely(proglen + ilen > oldproglen)) { - pr_err("bpf_jit_compile fatal error\n"); + pr_err("bpf_jit: fatal error\n"); return -EFAULT; } memcpy(image + proglen, temp, ilen); @@ -1085,10 +1085,6 @@ common_load: return proglen; } -void bpf_jit_compile(struct bpf_prog *prog) -{ -} - struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_binary_header *header = NULL; @@ -1169,9 +1165,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (image) { bpf_flush_icache(header, image + proglen); - set_memory_ro((unsigned long)header, header->pages); + bpf_jit_binary_lock_ro(header); prog->bpf_func = (void *)image; prog->jited = 1; + } else { + prog = orig_prog; } out_addrs: @@ -1182,18 +1180,3 @@ out: tmp : orig_prog); return prog; } - -void bpf_jit_free(struct bpf_prog *fp) -{ - unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; - struct bpf_binary_header *header = (void *)addr; - - if (!fp->jited) - goto free_filter; - - set_memory_rw(addr, header->pages); - bpf_jit_binary_free(header); - -free_filter: - bpf_prog_unlock_free(fp); -} diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 3cd69832d7f4..3961103e9176 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -114,6 +114,16 @@ static const struct dmi_system_id pci_crs_quirks[] __initconst = { DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"), }, }, + /* https://bugzilla.kernel.org/show_bug.cgi?id=42606 */ + { + .callback = set_nouse_crs, + .ident = "Supermicro X8DTH", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"), + DMI_MATCH(DMI_PRODUCT_NAME, "X8DTH-i/6/iF/6F"), + DMI_MATCH(DMI_BIOS_VERSION, "2.0a"), + }, + }, /* https://bugzilla.kernel.org/show_bug.cgi?id=15362 */ { diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 6aad870e8962..04ca8764f0c0 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -19,8 +19,7 @@ #include <linux/efi.h> #include <linux/efi-bgrt.h> -struct acpi_table_bgrt *bgrt_tab; -void *__initdata bgrt_image; +struct acpi_table_bgrt bgrt_tab; size_t __initdata bgrt_image_size; struct bmp_header { @@ -28,66 +27,58 @@ struct bmp_header { u32 size; } __packed; -void __init efi_bgrt_init(void) +void __init efi_bgrt_init(struct acpi_table_header *table) { - acpi_status status; void *image; struct bmp_header bmp_header; + struct acpi_table_bgrt *bgrt = &bgrt_tab; if (acpi_disabled) return; - status = acpi_get_table("BGRT", 0, - (struct acpi_table_header **)&bgrt_tab); - if (ACPI_FAILURE(status)) - return; - - if (bgrt_tab->header.length < sizeof(*bgrt_tab)) { + if (table->length < sizeof(bgrt_tab)) { pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n", - bgrt_tab->header.length, sizeof(*bgrt_tab)); + table->length, sizeof(bgrt_tab)); return; } - if (bgrt_tab->version != 1) { + *bgrt = *(struct acpi_table_bgrt *)table; + if (bgrt->version != 1) { pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n", - bgrt_tab->version); - return; + bgrt->version); + goto out; } - if (bgrt_tab->status & 0xfe) { + if (bgrt->status & 0xfe) { pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", - bgrt_tab->status); - return; + bgrt->status); + goto out; } - if (bgrt_tab->image_type != 0) { + if (bgrt->image_type != 0) { pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", - bgrt_tab->image_type); - return; + bgrt->image_type); + goto out; } - if (!bgrt_tab->image_address) { + if (!bgrt->image_address) { pr_notice("Ignoring BGRT: null image address\n"); - return; + goto out; } - image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB); + image = early_memremap(bgrt->image_address, sizeof(bmp_header)); if (!image) { pr_notice("Ignoring BGRT: failed to map image header memory\n"); - return; + goto out; } memcpy(&bmp_header, image, sizeof(bmp_header)); - memunmap(image); + early_memunmap(image, sizeof(bmp_header)); if (bmp_header.id != 0x4d42) { pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", bmp_header.id); - return; + goto out; } bgrt_image_size = bmp_header.size; + efi_mem_reserve(bgrt->image_address, bgrt_image_size); - bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); - if (!bgrt_image) { - pr_notice("Ignoring BGRT: failed to map image memory\n"); - bgrt_image = NULL; - return; - } - - efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size); + return; +out: + memset(bgrt, 0, sizeof(bgrt_tab)); } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 936a488d6cf6..565dff3c9a12 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -210,6 +210,70 @@ int __init efi_memblock_x86_reserve_range(void) return 0; } +#define OVERFLOW_ADDR_SHIFT (64 - EFI_PAGE_SHIFT) +#define OVERFLOW_ADDR_MASK (U64_MAX << OVERFLOW_ADDR_SHIFT) +#define U64_HIGH_BIT (~(U64_MAX >> 1)) + +static bool __init efi_memmap_entry_valid(const efi_memory_desc_t *md, int i) +{ + u64 end = (md->num_pages << EFI_PAGE_SHIFT) + md->phys_addr - 1; + u64 end_hi = 0; + char buf[64]; + + if (md->num_pages == 0) { + end = 0; + } else if (md->num_pages > EFI_PAGES_MAX || + EFI_PAGES_MAX - md->num_pages < + (md->phys_addr >> EFI_PAGE_SHIFT)) { + end_hi = (md->num_pages & OVERFLOW_ADDR_MASK) + >> OVERFLOW_ADDR_SHIFT; + + if ((md->phys_addr & U64_HIGH_BIT) && !(end & U64_HIGH_BIT)) + end_hi += 1; + } else { + return true; + } + + pr_warn_once(FW_BUG "Invalid EFI memory map entries:\n"); + + if (end_hi) { + pr_warn("mem%02u: %s range=[0x%016llx-0x%llx%016llx] (invalid)\n", + i, efi_md_typeattr_format(buf, sizeof(buf), md), + md->phys_addr, end_hi, end); + } else { + pr_warn("mem%02u: %s range=[0x%016llx-0x%016llx] (invalid)\n", + i, efi_md_typeattr_format(buf, sizeof(buf), md), + md->phys_addr, end); + } + return false; +} + +static void __init efi_clean_memmap(void) +{ + efi_memory_desc_t *out = efi.memmap.map; + const efi_memory_desc_t *in = out; + const efi_memory_desc_t *end = efi.memmap.map_end; + int i, n_removal; + + for (i = n_removal = 0; in < end; i++) { + if (efi_memmap_entry_valid(in, i)) { + if (out != in) + memcpy(out, in, efi.memmap.desc_size); + out = (void *)out + efi.memmap.desc_size; + } else { + n_removal++; + } + in = (void *)in + efi.memmap.desc_size; + } + + if (n_removal > 0) { + u64 size = efi.memmap.nr_map - n_removal; + + pr_warn("Removing %d invalid memory map entries.\n", n_removal); + efi_memmap_install(efi.memmap.phys_map, size); + } +} + void __init efi_print_memmap(void) { efi_memory_desc_t *md; @@ -472,15 +536,12 @@ void __init efi_init(void) } } + efi_clean_memmap(); + if (efi_enabled(EFI_DBG)) efi_print_memmap(); } -void __init efi_late_init(void) -{ - efi_bgrt_init(); -} - void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -894,6 +955,11 @@ static void __init __efi_enter_virtual_mode(void) return; } + if (efi_enabled(EFI_DBG)) { + pr_info("EFI runtime memory map:\n"); + efi_print_memmap(); + } + BUG_ON(!efi.systab); if (efi_setup_page_tables(pa, 1 << pg_shift)) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 319148bd4b05..a4695da42d77 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -269,6 +269,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.use_pgd = true; /* + * Certain firmware versions are way too sentimential and still believe + * they are exclusive and unquestionable owners of the first physical page, + * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY + * (but then write-access it later during SetVirtualAddressMap()). + * + * Create a 1:1 mapping for this page, to avoid triple faults during early + * boot with such firmware. We are free to hand this page to the BIOS, + * as trim_bios_range() will reserve the first page and isolate it away + * from memory allocators anyway. + */ + if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) { + pr_err("Failed to create 1:1 mapping for the first page!\n"); + return 1; + } + + /* * When making calls to the firmware everything needs to be 1:1 * mapped and addressable with 32-bit pointers. Map the kernel * text and allocate a new stack because we can't rely on the @@ -398,10 +414,44 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len) efi_setup = phys_addr + sizeof(struct setup_data); } -void __init efi_runtime_update_mappings(void) +static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf) { unsigned long pfn; pgd_t *pgd = efi_pgd; + int err1, err2; + + /* Update the 1:1 mapping */ + pfn = md->phys_addr >> PAGE_SHIFT; + err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf); + if (err1) { + pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } + + err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf); + if (err2) { + pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n", + md->phys_addr, md->virt_addr); + } + + return err1 || err2; +} + +static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md) +{ + unsigned long pf = 0; + + if (md->attribute & EFI_MEMORY_XP) + pf |= _PAGE_NX; + + if (!(md->attribute & EFI_MEMORY_RO)) + pf |= _PAGE_RW; + + return efi_update_mappings(md, pf); +} + +void __init efi_runtime_update_mappings(void) +{ efi_memory_desc_t *md; if (efi_enabled(EFI_OLD_MEMMAP)) { @@ -410,6 +460,24 @@ void __init efi_runtime_update_mappings(void) return; } + /* + * Use the EFI Memory Attribute Table for mapping permissions if it + * exists, since it is intended to supersede EFI_PROPERTIES_TABLE. + */ + if (efi_enabled(EFI_MEM_ATTR)) { + efi_memattr_apply_permissions(NULL, efi_update_mem_attr); + return; + } + + /* + * EFI_MEMORY_ATTRIBUTES_TABLE is intended to replace + * EFI_PROPERTIES_TABLE. So, use EFI_PROPERTIES_TABLE to update + * permissions only if EFI_MEMORY_ATTRIBUTES_TABLE is not + * published by the firmware. Even if we find a buggy implementation of + * EFI_MEMORY_ATTRIBUTES_TABLE, don't fall back to + * EFI_PROPERTIES_TABLE, because of the same reason. + */ + if (!efi_enabled(EFI_NX_PE_DATA)) return; @@ -430,15 +498,7 @@ void __init efi_runtime_update_mappings(void) (md->type != EFI_RUNTIME_SERVICES_CODE)) pf |= _PAGE_RW; - /* Update the 1:1 mapping */ - pfn = md->phys_addr >> PAGE_SHIFT; - if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf)) - pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", - md->phys_addr, md->virt_addr); - - if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf)) - pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n", - md->phys_addr, md->virt_addr); + efi_update_mappings(md, pf); } } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 10aca63a50d7..30031d5293c4 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -214,7 +214,7 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) new_size = efi.memmap.desc_size * num_entries; - new_phys = memblock_alloc(new_size, 0); + new_phys = efi_memmap_alloc(num_entries); if (!new_phys) { pr_err("Could not allocate boot services memmap\n"); return; @@ -355,7 +355,7 @@ void __init efi_free_boot_services(void) } new_size = efi.memmap.desc_size * num_entries; - new_phys = memblock_alloc(new_size, 0); + new_phys = efi_memmap_alloc(num_entries); if (!new_phys) { pr_err("Failed to allocate new EFI memmap\n"); return; diff --git a/arch/x86/platform/goldfish/goldfish.c b/arch/x86/platform/goldfish/goldfish.c index 1693107a518e..0d17c0aafeb1 100644 --- a/arch/x86/platform/goldfish/goldfish.c +++ b/arch/x86/platform/goldfish/goldfish.c @@ -42,10 +42,22 @@ static struct resource goldfish_pdev_bus_resources[] = { } }; +static bool goldfish_enable __initdata; + +static int __init goldfish_setup(char *str) +{ + goldfish_enable = true; + return 0; +} +__setup("goldfish", goldfish_setup); + static int __init goldfish_init(void) { + if (!goldfish_enable) + return -ENODEV; + platform_device_register_simple("goldfish_pdev_bus", -1, - goldfish_pdev_bus_resources, 2); + goldfish_pdev_bus_resources, 2); return 0; } device_initcall(goldfish_init); diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 61b5ed2b7d40..a7dbec4dce27 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -5,17 +5,15 @@ obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o # WiFi obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o # IPC Devices -obj-y += platform_ipc.o obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o obj-$(subst m,y,$(CONFIG_GPIO_MSIC)) += platform_msic_gpio.o obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_ocd.o obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_battery.o obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o -obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o # SPI Devices -obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_spidev.o +obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o # I2C Devices obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o @@ -28,4 +26,5 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o # MISC Devices obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o +obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c index 52534ec29765..74283875c7e8 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c @@ -32,6 +32,9 @@ static struct gpio_keys_button gpio_button[] = { {SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20}, {KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20}, {KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20}, + {KEY_MUTE, -1, 1, "mute_enable", EV_KEY, 0, 20}, + {KEY_VOLUMEUP, -1, 1, "volume_up", EV_KEY, 0, 20}, + {KEY_VOLUMEDOWN, -1, 1, "volume_down", EV_KEY, 0, 20}, {KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20}, {KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20}, {SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20}, diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c deleted file mode 100644 index a84b73d6c4a0..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c +++ /dev/null @@ -1,68 +0,0 @@ -/* - * platform_ipc.c: IPC platform library file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/sfi.h> -#include <linux/gpio.h> -#include <asm/intel-mid.h> -#include "platform_ipc.h" - -void __init ipc_device_handler(struct sfi_device_table_entry *pentry, - struct devs_id *dev) -{ - struct platform_device *pdev; - void *pdata = NULL; - static struct resource res __initdata = { - .name = "IRQ", - .flags = IORESOURCE_IRQ, - }; - - pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n", - pentry->name, pentry->irq); - - /* - * We need to call platform init of IPC devices to fill misc_pdata - * structure. It will be used in msic_init for initialization. - */ - if (dev != NULL) - pdata = dev->get_platform_data(pentry); - - /* - * On Medfield the platform device creation is handled by the MSIC - * MFD driver so we don't need to do it here. - */ - if (intel_mid_has_msic()) - return; - - pdev = platform_device_alloc(pentry->name, 0); - if (pdev == NULL) { - pr_err("out of memory for SFI platform device '%s'.\n", - pentry->name); - return; - } - res.start = pentry->irq; - platform_device_add_resources(pdev, &res, 1); - - pdev->dev.platform_data = pdata; - intel_scu_device_register(pdev); -} - -static const struct devs_id pmic_audio_dev_id __initconst = { - .name = "pmic_audio", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .device_handler = &ipc_device_handler, -}; - -sfi_device(pmic_audio_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h deleted file mode 100644 index 79bb09d4f718..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * platform_ipc.h: IPC platform library header file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#ifndef _PLATFORM_IPC_H_ -#define _PLATFORM_IPC_H_ - -void __init -ipc_device_handler(struct sfi_device_table_entry *pentry, struct devs_id *dev); - -#endif diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c new file mode 100644 index 000000000000..3135416df037 --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c @@ -0,0 +1,48 @@ +/* + * Intel Merrifield legacy RTC initialization file + * + * (C) Copyright 2017 Intel Corporation + * + * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/init.h> + +#include <asm/hw_irq.h> +#include <asm/intel-mid.h> +#include <asm/io_apic.h> +#include <asm/time.h> +#include <asm/x86_init.h> + +static int __init mrfld_legacy_rtc_alloc_irq(void) +{ + struct irq_alloc_info info; + int ret; + + if (!x86_platform.legacy.rtc) + return -ENODEV; + + ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, 0); + ret = mp_map_gsi_to_irq(RTC_IRQ, IOAPIC_MAP_ALLOC, &info); + if (ret < 0) { + pr_info("Failed to allocate RTC interrupt. Disabling RTC\n"); + x86_platform.legacy.rtc = 0; + return ret; + } + + return 0; +} + +static int __init mrfld_legacy_rtc_init(void) +{ + if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) + return -ENODEV; + + return mrfld_legacy_rtc_alloc_irq(); +} +arch_initcall(mrfld_legacy_rtc_init); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_spidev.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c index 30c601b399ee..27186ad654c9 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_spidev.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_spidev.c @@ -11,6 +11,7 @@ * of the License. */ +#include <linux/err.h> #include <linux/init.h> #include <linux/sfi.h> #include <linux/spi/pxa2xx_spi.h> @@ -34,6 +35,9 @@ static void __init *spidev_platform_data(void *info) { struct spi_board_info *spi_info = info; + if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER) + return ERR_PTR(-ENODEV); + spi_info->mode = SPI_MODE_0; spi_info->controller_data = &spidev_spi_chip; diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c index 3f1f1c77d090..86edd1e941eb 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c @@ -28,9 +28,9 @@ static struct platform_device wdt_dev = { static int tangier_probe(struct platform_device *pdev) { - int gsi; struct irq_alloc_info info; struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; + int gsi, irq; if (!pdata) return -EINVAL; @@ -38,10 +38,10 @@ static int tangier_probe(struct platform_device *pdev) /* IOAPIC builds identity mapping between GSI and IRQ on MID */ gsi = pdata->irq; ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0); - if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) { - dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", - gsi); - return -EINVAL; + irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); + if (irq < 0) { + dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", gsi); + return irq; } return 0; @@ -82,4 +82,4 @@ static int __init register_mid_wdt(void) return 0; } -rootfs_initcall(register_mid_wdt); +arch_initcall(register_mid_wdt); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c index cb3490ecb341..d4dc744dd5a5 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c @@ -20,7 +20,6 @@ #include <asm/intel-mid.h> #include "platform_msic.h" -#include "platform_ipc.h" static void *msic_audio_platform_data(void *info) { @@ -40,8 +39,8 @@ static const struct devs_id msic_audio_dev_id __initconst = { .name = "msic_audio", .type = SFI_DEV_TYPE_IPC, .delay = 1, + .msic = 1, .get_platform_data = &msic_audio_platform_data, - .device_handler = &ipc_device_handler, }; sfi_device(msic_audio_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c index 4f72193939a6..5c3e9919633f 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c @@ -19,7 +19,6 @@ #include <asm/intel-mid.h> #include "platform_msic.h" -#include "platform_ipc.h" static void __init *msic_battery_platform_data(void *info) { @@ -30,8 +29,8 @@ static const struct devs_id msic_battery_dev_id __initconst = { .name = "msic_battery", .type = SFI_DEV_TYPE_IPC, .delay = 1, + .msic = 1, .get_platform_data = &msic_battery_platform_data, - .device_handler = &ipc_device_handler, }; sfi_device(msic_battery_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c index 70de5b531ba0..9fdb88d460d7 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c @@ -20,7 +20,6 @@ #include <asm/intel-mid.h> #include "platform_msic.h" -#include "platform_ipc.h" static void __init *msic_gpio_platform_data(void *info) { @@ -41,8 +40,8 @@ static const struct devs_id msic_gpio_dev_id __initconst = { .name = "msic_gpio", .type = SFI_DEV_TYPE_IPC, .delay = 1, + .msic = 1, .get_platform_data = &msic_gpio_platform_data, - .device_handler = &ipc_device_handler, }; sfi_device(msic_gpio_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c index 3d7c2011b6cf..7ae37cdbf256 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c @@ -20,7 +20,6 @@ #include <asm/intel-mid.h> #include "platform_msic.h" -#include "platform_ipc.h" static void __init *msic_ocd_platform_data(void *info) { @@ -42,8 +41,8 @@ static const struct devs_id msic_ocd_dev_id __initconst = { .name = "msic_ocd", .type = SFI_DEV_TYPE_IPC, .delay = 1, + .msic = 1, .get_platform_data = &msic_ocd_platform_data, - .device_handler = &ipc_device_handler, }; sfi_device(msic_ocd_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c index 038f618fbc52..96809b98cf69 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c @@ -18,7 +18,6 @@ #include <asm/intel-mid.h> #include "platform_msic.h" -#include "platform_ipc.h" static void __init *msic_power_btn_platform_data(void *info) { @@ -29,8 +28,8 @@ static const struct devs_id msic_power_btn_dev_id __initconst = { .name = "msic_power_btn", .type = SFI_DEV_TYPE_IPC, .delay = 1, + .msic = 1, .get_platform_data = &msic_power_btn_platform_data, - .device_handler = &ipc_device_handler, }; sfi_device(msic_power_btn_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c index 114a5755b1e4..3e4167d246cd 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c @@ -19,7 +19,6 @@ #include <asm/intel-mid.h> #include "platform_msic.h" -#include "platform_ipc.h" static void __init *msic_thermal_platform_data(void *info) { @@ -30,8 +29,8 @@ static const struct devs_id msic_thermal_dev_id __initconst = { .name = "msic_thermal", .type = SFI_DEV_TYPE_IPC, .delay = 1, + .msic = 1, .get_platform_data = &msic_thermal_platform_data, - .device_handler = &ipc_device_handler, }; sfi_device(msic_thermal_dev_id); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c deleted file mode 100644 index e30cb62e3300..000000000000 --- a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c +++ /dev/null @@ -1,54 +0,0 @@ -/* - * platform_pmic_gpio.c: PMIC GPIO platform data initialization file - * - * (C) Copyright 2013 Intel Corporation - * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -#include <linux/kernel.h> -#include <linux/interrupt.h> -#include <linux/scatterlist.h> -#include <linux/gpio.h> -#include <linux/init.h> -#include <linux/sfi.h> -#include <linux/intel_pmic_gpio.h> -#include <asm/intel-mid.h> - -#include "platform_ipc.h" - -static void __init *pmic_gpio_platform_data(void *info) -{ - static struct intel_pmic_gpio_platform_data pmic_gpio_pdata; - int gpio_base = get_gpio_by_name("pmic_gpio_base"); - - if (gpio_base < 0) - gpio_base = 64; - pmic_gpio_pdata.gpio_base = gpio_base; - pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET; - pmic_gpio_pdata.gpiointr = 0xffffeff8; - - return &pmic_gpio_pdata; -} - -static const struct devs_id pmic_gpio_spi_dev_id __initconst = { - .name = "pmic_gpio", - .type = SFI_DEV_TYPE_SPI, - .delay = 1, - .get_platform_data = &pmic_gpio_platform_data, -}; - -static const struct devs_id pmic_gpio_ipc_dev_id __initconst = { - .name = "pmic_gpio", - .type = SFI_DEV_TYPE_IPC, - .delay = 1, - .get_platform_data = &pmic_gpio_platform_data, - .device_handler = &ipc_device_handler -}; - -sfi_device(pmic_gpio_spi_dev_id); -sfi_device(pmic_gpio_ipc_dev_id); diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c index e0607c77a1bd..ae7bdeb0e507 100644 --- a/arch/x86/platform/intel-mid/mrfld.c +++ b/arch/x86/platform/intel-mid/mrfld.c @@ -91,6 +91,7 @@ static unsigned long __init tangier_calibrate_tsc(void) static void __init tangier_arch_setup(void) { x86_platform.calibrate_tsc = tangier_calibrate_tsc; + x86_platform.legacy.rtc = 1; } /* tangier arch ops */ diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index 051d264fce2e..19b43e3a9f0f 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -15,7 +15,6 @@ #include <linux/interrupt.h> #include <linux/scatterlist.h> #include <linux/sfi.h> -#include <linux/intel_pmic_gpio.h> #include <linux/spi/spi.h> #include <linux/i2c.h> #include <linux/skbuff.h> @@ -226,7 +225,7 @@ int get_gpio_by_name(const char *name) return -EINVAL; } -void __init intel_scu_device_register(struct platform_device *pdev) +static void __init intel_scu_ipc_device_register(struct platform_device *pdev) { if (ipc_next_dev == MAX_IPCDEVS) pr_err("too many SCU IPC devices"); @@ -335,10 +334,22 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry, pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n", pentry->name, pentry->irq); + + /* + * We need to call platform init of IPC devices to fill misc_pdata + * structure. It will be used in msic_init for initialization. + */ pdata = intel_mid_sfi_get_pdata(dev, pentry); if (IS_ERR(pdata)) return; + /* + * On Medfield the platform device creation is handled by the MSIC + * MFD driver so we don't need to do it here. + */ + if (dev->msic && intel_mid_has_msic()) + return; + pdev = platform_device_alloc(pentry->name, 0); if (pdev == NULL) { pr_err("out of memory for SFI platform device '%s'.\n", @@ -348,7 +359,10 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry, install_irq_resource(pdev, pentry->irq); pdev->dev.platform_data = pdata; - platform_device_add(pdev); + if (dev->delay) + intel_scu_ipc_device_register(pdev); + else + platform_device_add(pdev); } static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry, @@ -503,27 +517,23 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) if (!dev) continue; - if (dev->device_handler) { - dev->device_handler(pentry, dev); - } else { - switch (pentry->type) { - case SFI_DEV_TYPE_IPC: - sfi_handle_ipc_dev(pentry, dev); - break; - case SFI_DEV_TYPE_SPI: - sfi_handle_spi_dev(pentry, dev); - break; - case SFI_DEV_TYPE_I2C: - sfi_handle_i2c_dev(pentry, dev); - break; - case SFI_DEV_TYPE_SD: - sfi_handle_sd_dev(pentry, dev); - break; - case SFI_DEV_TYPE_UART: - case SFI_DEV_TYPE_HSI: - default: - break; - } + switch (pentry->type) { + case SFI_DEV_TYPE_IPC: + sfi_handle_ipc_dev(pentry, dev); + break; + case SFI_DEV_TYPE_SPI: + sfi_handle_spi_dev(pentry, dev); + break; + case SFI_DEV_TYPE_I2C: + sfi_handle_i2c_dev(pentry, dev); + break; + case SFI_DEV_TYPE_SD: + sfi_handle_sd_dev(pentry, dev); + break; + case SFI_DEV_TYPE_UART: + case SFI_DEV_TYPE_HSI: + default: + break; } } return 0; diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 8410e7d0a5b5..9743d0ccfec6 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -45,8 +45,8 @@ * * Handle system-wide NMI events generated by the global 'power nmi' command. * - * Basic operation is to field the NMI interrupt on each cpu and wait - * until all cpus have arrived into the nmi handler. If some cpus do not + * Basic operation is to field the NMI interrupt on each CPU and wait + * until all CPU's have arrived into the nmi handler. If some CPU's do not * make it into the handler, try and force them in with the IPI(NMI) signal. * * We also have to lessen UV Hub MMR accesses as much as possible as this @@ -56,7 +56,7 @@ * To do this we register our primary NMI notifier on the NMI_UNKNOWN * chain. This reduces the number of false NMI calls when the perf * tools are running which generate an enormous number of NMIs per - * second (~4M/s for 1024 cpu threads). Our secondary NMI handler is + * second (~4M/s for 1024 CPU threads). Our secondary NMI handler is * very short as it only checks that if it has been "pinged" with the * IPI(NMI) signal as mentioned above, and does not read the UV Hub's MMR. * @@ -65,8 +65,20 @@ static struct uv_hub_nmi_s **uv_hub_nmi_list; DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi); -EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi); +/* UV hubless values */ +#define NMI_CONTROL_PORT 0x70 +#define NMI_DUMMY_PORT 0x71 +#define PAD_OWN_GPP_D_0 0x2c +#define GPI_NMI_STS_GPP_D_0 0x164 +#define GPI_NMI_ENA_GPP_D_0 0x174 +#define STS_GPP_D_0_MASK 0x1 +#define PAD_CFG_DW0_GPP_D_0 0x4c0 +#define GPIROUTNMI (1ul << 17) +#define PCH_PCR_GPIO_1_BASE 0xfdae0000ul +#define PCH_PCR_GPIO_ADDRESS(offset) (int *)((u64)(pch_base) | (u64)(offset)) + +static u64 *pch_base; static unsigned long nmi_mmr; static unsigned long nmi_mmr_clear; static unsigned long nmi_mmr_pending; @@ -100,7 +112,7 @@ static int param_get_local64(char *buffer, const struct kernel_param *kp) static int param_set_local64(const char *val, const struct kernel_param *kp) { - /* clear on any write */ + /* Clear on any write */ local64_set((local64_t *)kp->arg, 0); return 0; } @@ -144,16 +156,80 @@ module_param_named(wait_count, uv_nmi_wait_count, int, 0644); static int uv_nmi_retry_count = 500; module_param_named(retry_count, uv_nmi_retry_count, int, 0644); -/* - * Valid NMI Actions: - * "dump" - dump process stack for each cpu - * "ips" - dump IP info for each cpu - * "kdump" - do crash dump - * "kdb" - enter KDB (default) - * "kgdb" - enter KGDB - */ -static char uv_nmi_action[8] = "kdb"; -module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644); +static bool uv_pch_intr_enable = true; +static bool uv_pch_intr_now_enabled; +module_param_named(pch_intr_enable, uv_pch_intr_enable, bool, 0644); + +static bool uv_pch_init_enable = true; +module_param_named(pch_init_enable, uv_pch_init_enable, bool, 0644); + +static int uv_nmi_debug; +module_param_named(debug, uv_nmi_debug, int, 0644); + +#define nmi_debug(fmt, ...) \ + do { \ + if (uv_nmi_debug) \ + pr_info(fmt, ##__VA_ARGS__); \ + } while (0) + +/* Valid NMI Actions */ +#define ACTION_LEN 16 +static struct nmi_action { + char *action; + char *desc; +} valid_acts[] = { + { "kdump", "do kernel crash dump" }, + { "dump", "dump process stack for each cpu" }, + { "ips", "dump Inst Ptr info for each cpu" }, + { "kdb", "enter KDB (needs kgdboc= assignment)" }, + { "kgdb", "enter KGDB (needs gdb target remote)" }, + { "health", "check if CPUs respond to NMI" }, +}; +typedef char action_t[ACTION_LEN]; +static action_t uv_nmi_action = { "dump" }; + +static int param_get_action(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%s\n", uv_nmi_action); +} + +static int param_set_action(const char *val, const struct kernel_param *kp) +{ + int i; + int n = ARRAY_SIZE(valid_acts); + char arg[ACTION_LEN], *p; + + /* (remove possible '\n') */ + strncpy(arg, val, ACTION_LEN - 1); + arg[ACTION_LEN - 1] = '\0'; + p = strchr(arg, '\n'); + if (p) + *p = '\0'; + + for (i = 0; i < n; i++) + if (!strcmp(arg, valid_acts[i].action)) + break; + + if (i < n) { + strcpy(uv_nmi_action, arg); + pr_info("UV: New NMI action:%s\n", uv_nmi_action); + return 0; + } + + pr_err("UV: Invalid NMI action:%s, valid actions are:\n", arg); + for (i = 0; i < n; i++) + pr_err("UV: %-8s - %s\n", + valid_acts[i].action, valid_acts[i].desc); + return -EINVAL; +} + +static const struct kernel_param_ops param_ops_action = { + .get = param_get_action, + .set = param_set_action, +}; +#define param_check_action(name, p) __param_check(name, p, action_t) + +module_param_named(action, uv_nmi_action, action, 0644); static inline bool uv_nmi_action_is(const char *action) { @@ -192,8 +268,200 @@ static inline void uv_local_mmr_clear_nmi(void) } /* - * If first cpu in on this hub, set hub_nmi "in_nmi" and "owner" values and - * return true. If first cpu in on the system, set global "in_nmi" flag. + * UV hubless NMI handler functions + */ +static inline void uv_reassert_nmi(void) +{ + /* (from arch/x86/include/asm/mach_traps.h) */ + outb(0x8f, NMI_CONTROL_PORT); + inb(NMI_DUMMY_PORT); /* dummy read */ + outb(0x0f, NMI_CONTROL_PORT); + inb(NMI_DUMMY_PORT); /* dummy read */ +} + +static void uv_init_hubless_pch_io(int offset, int mask, int data) +{ + int *addr = PCH_PCR_GPIO_ADDRESS(offset); + int readd = readl(addr); + + if (mask) { /* OR in new data */ + int writed = (readd & ~mask) | data; + + nmi_debug("UV:PCH: %p = %x & %x | %x (%x)\n", + addr, readd, ~mask, data, writed); + writel(writed, addr); + } else if (readd & data) { /* clear status bit */ + nmi_debug("UV:PCH: %p = %x\n", addr, data); + writel(data, addr); + } + + (void)readl(addr); /* flush write data */ +} + +static void uv_nmi_setup_hubless_intr(void) +{ + uv_pch_intr_now_enabled = uv_pch_intr_enable; + + uv_init_hubless_pch_io( + PAD_CFG_DW0_GPP_D_0, GPIROUTNMI, + uv_pch_intr_now_enabled ? GPIROUTNMI : 0); + + nmi_debug("UV:NMI: GPP_D_0 interrupt %s\n", + uv_pch_intr_now_enabled ? "enabled" : "disabled"); +} + +static struct init_nmi { + unsigned int offset; + unsigned int mask; + unsigned int data; +} init_nmi[] = { + { /* HOSTSW_OWN_GPP_D_0 */ + .offset = 0x84, + .mask = 0x1, + .data = 0x0, /* ACPI Mode */ + }, + +/* Clear status: */ + { /* GPI_INT_STS_GPP_D_0 */ + .offset = 0x104, + .mask = 0x0, + .data = 0x1, /* Clear Status */ + }, + { /* GPI_GPE_STS_GPP_D_0 */ + .offset = 0x124, + .mask = 0x0, + .data = 0x1, /* Clear Status */ + }, + { /* GPI_SMI_STS_GPP_D_0 */ + .offset = 0x144, + .mask = 0x0, + .data = 0x1, /* Clear Status */ + }, + { /* GPI_NMI_STS_GPP_D_0 */ + .offset = 0x164, + .mask = 0x0, + .data = 0x1, /* Clear Status */ + }, + +/* Disable interrupts: */ + { /* GPI_INT_EN_GPP_D_0 */ + .offset = 0x114, + .mask = 0x1, + .data = 0x0, /* Disable interrupt generation */ + }, + { /* GPI_GPE_EN_GPP_D_0 */ + .offset = 0x134, + .mask = 0x1, + .data = 0x0, /* Disable interrupt generation */ + }, + { /* GPI_SMI_EN_GPP_D_0 */ + .offset = 0x154, + .mask = 0x1, + .data = 0x0, /* Disable interrupt generation */ + }, + { /* GPI_NMI_EN_GPP_D_0 */ + .offset = 0x174, + .mask = 0x1, + .data = 0x0, /* Disable interrupt generation */ + }, + +/* Setup GPP_D_0 Pad Config: */ + { /* PAD_CFG_DW0_GPP_D_0 */ + .offset = 0x4c0, + .mask = 0xffffffff, + .data = 0x82020100, +/* + * 31:30 Pad Reset Config (PADRSTCFG): = 2h # PLTRST# (default) + * + * 29 RX Pad State Select (RXPADSTSEL): = 0 # Raw RX pad state directly + * from RX buffer (default) + * + * 28 RX Raw Override to '1' (RXRAW1): = 0 # No Override + * + * 26:25 RX Level/Edge Configuration (RXEVCFG): + * = 0h # Level + * = 1h # Edge + * + * 23 RX Invert (RXINV): = 0 # No Inversion (signal active high) + * + * 20 GPIO Input Route IOxAPIC (GPIROUTIOXAPIC): + * = 0 # Routing does not cause peripheral IRQ... + * # (we want an NMI not an IRQ) + * + * 19 GPIO Input Route SCI (GPIROUTSCI): = 0 # Routing does not cause SCI. + * 18 GPIO Input Route SMI (GPIROUTSMI): = 0 # Routing does not cause SMI. + * 17 GPIO Input Route NMI (GPIROUTNMI): = 1 # Routing can cause NMI. + * + * 11:10 Pad Mode (PMODE1/0): = 0h = GPIO control the Pad. + * 9 GPIO RX Disable (GPIORXDIS): + * = 0 # Enable the input buffer (active low enable) + * + * 8 GPIO TX Disable (GPIOTXDIS): + * = 1 # Disable the output buffer; i.e. Hi-Z + * + * 1 GPIO RX State (GPIORXSTATE): This is the current internal RX pad state.. + * 0 GPIO TX State (GPIOTXSTATE): + * = 0 # (Leave at default) + */ + }, + +/* Pad Config DW1 */ + { /* PAD_CFG_DW1_GPP_D_0 */ + .offset = 0x4c4, + .mask = 0x3c00, + .data = 0, /* Termination = none (default) */ + }, +}; + +static void uv_init_hubless_pch_d0(void) +{ + int i, read; + + read = *PCH_PCR_GPIO_ADDRESS(PAD_OWN_GPP_D_0); + if (read != 0) { + pr_info("UV: Hubless NMI already configured\n"); + return; + } + + nmi_debug("UV: Initializing UV Hubless NMI on PCH\n"); + for (i = 0; i < ARRAY_SIZE(init_nmi); i++) { + uv_init_hubless_pch_io(init_nmi[i].offset, + init_nmi[i].mask, + init_nmi[i].data); + } +} + +static int uv_nmi_test_hubless(struct uv_hub_nmi_s *hub_nmi) +{ + int *pstat = PCH_PCR_GPIO_ADDRESS(GPI_NMI_STS_GPP_D_0); + int status = *pstat; + + hub_nmi->nmi_value = status; + atomic_inc(&hub_nmi->read_mmr_count); + + if (!(status & STS_GPP_D_0_MASK)) /* Not a UV external NMI */ + return 0; + + *pstat = STS_GPP_D_0_MASK; /* Is a UV NMI: clear GPP_D_0 status */ + (void)*pstat; /* Flush write */ + + return 1; +} + +static int uv_test_nmi(struct uv_hub_nmi_s *hub_nmi) +{ + if (hub_nmi->hub_present) + return uv_nmi_test_mmr(hub_nmi); + + if (hub_nmi->pch_owner) /* Only PCH owner can check status */ + return uv_nmi_test_hubless(hub_nmi); + + return -1; +} + +/* + * If first CPU in on this hub, set hub_nmi "in_nmi" and "owner" values and + * return true. If first CPU in on the system, set global "in_nmi" flag. */ static int uv_set_in_nmi(int cpu, struct uv_hub_nmi_s *hub_nmi) { @@ -214,6 +482,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi) { int cpu = smp_processor_id(); int nmi = 0; + int nmi_detected = 0; local64_inc(&uv_nmi_count); this_cpu_inc(uv_cpu_nmi.queries); @@ -224,35 +493,48 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi) break; if (raw_spin_trylock(&hub_nmi->nmi_lock)) { + nmi_detected = uv_test_nmi(hub_nmi); - /* check hub MMR NMI flag */ - if (uv_nmi_test_mmr(hub_nmi)) { + /* Check flag for UV external NMI */ + if (nmi_detected > 0) { uv_set_in_nmi(cpu, hub_nmi); nmi = 1; break; } - /* MMR NMI flag is clear */ + /* A non-PCH node in a hubless system waits for NMI */ + else if (nmi_detected < 0) + goto slave_wait; + + /* MMR/PCH NMI flag is clear */ raw_spin_unlock(&hub_nmi->nmi_lock); } else { - /* wait a moment for the hub nmi locker to set flag */ - cpu_relax(); + + /* Wait a moment for the HUB NMI locker to set flag */ +slave_wait: cpu_relax(); udelay(uv_nmi_slave_delay); - /* re-check hub in_nmi flag */ + /* Re-check hub in_nmi flag */ nmi = atomic_read(&hub_nmi->in_nmi); if (nmi) break; } - /* check if this BMC missed setting the MMR NMI flag */ + /* + * Check if this BMC missed setting the MMR NMI flag (or) + * UV hubless system where only PCH owner can check flag + */ if (!nmi) { nmi = atomic_read(&uv_in_nmi); if (nmi) uv_set_in_nmi(cpu, hub_nmi); } + /* If we're holding the hub lock, release it now */ + if (nmi_detected < 0) + raw_spin_unlock(&hub_nmi->nmi_lock); + } while (0); if (!nmi) @@ -269,12 +551,15 @@ static inline void uv_clear_nmi(int cpu) if (cpu == atomic_read(&hub_nmi->cpu_owner)) { atomic_set(&hub_nmi->cpu_owner, -1); atomic_set(&hub_nmi->in_nmi, 0); - uv_local_mmr_clear_nmi(); + if (hub_nmi->hub_present) + uv_local_mmr_clear_nmi(); + else + uv_reassert_nmi(); raw_spin_unlock(&hub_nmi->nmi_lock); } } -/* Ping non-responding cpus attemping to force them into the NMI handler */ +/* Ping non-responding CPU's attemping to force them into the NMI handler */ static void uv_nmi_nr_cpus_ping(void) { int cpu; @@ -285,7 +570,7 @@ static void uv_nmi_nr_cpus_ping(void) apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI); } -/* Clean up flags for cpus that ignored both NMI and ping */ +/* Clean up flags for CPU's that ignored both NMI and ping */ static void uv_nmi_cleanup_mask(void) { int cpu; @@ -297,11 +582,12 @@ static void uv_nmi_cleanup_mask(void) } } -/* Loop waiting as cpus enter nmi handler */ +/* Loop waiting as CPU's enter NMI handler */ static int uv_nmi_wait_cpus(int first) { int i, j, k, n = num_online_cpus(); int last_k = 0, waiting = 0; + int cpu = smp_processor_id(); if (first) { cpumask_copy(uv_nmi_cpu_mask, cpu_online_mask); @@ -310,6 +596,12 @@ static int uv_nmi_wait_cpus(int first) k = n - cpumask_weight(uv_nmi_cpu_mask); } + /* PCH NMI causes only one CPU to respond */ + if (first && uv_pch_intr_now_enabled) { + cpumask_clear_cpu(cpu, uv_nmi_cpu_mask); + return n - k - 1; + } + udelay(uv_nmi_initial_delay); for (i = 0; i < uv_nmi_retry_count; i++) { int loop_delay = uv_nmi_loop_delay; @@ -325,13 +617,13 @@ static int uv_nmi_wait_cpus(int first) k = n; break; } - if (last_k != k) { /* abort if no new cpus coming in */ + if (last_k != k) { /* abort if no new CPU's coming in */ last_k = k; waiting = 0; } else if (++waiting > uv_nmi_wait_count) break; - /* extend delay if waiting only for cpu 0 */ + /* Extend delay if waiting only for CPU 0: */ if (waiting && (n - k) == 1 && cpumask_test_cpu(0, uv_nmi_cpu_mask)) loop_delay *= 100; @@ -342,29 +634,29 @@ static int uv_nmi_wait_cpus(int first) return n - k; } -/* Wait until all slave cpus have entered UV NMI handler */ +/* Wait until all slave CPU's have entered UV NMI handler */ static void uv_nmi_wait(int master) { - /* indicate this cpu is in */ + /* Indicate this CPU is in: */ this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN); - /* if not the first cpu in (the master), then we are a slave cpu */ + /* If not the first CPU in (the master), then we are a slave CPU */ if (!master) return; do { - /* wait for all other cpus to gather here */ + /* Wait for all other CPU's to gather here */ if (!uv_nmi_wait_cpus(1)) break; - /* if not all made it in, send IPI NMI to them */ - pr_alert("UV: Sending NMI IPI to %d non-responding CPUs: %*pbl\n", + /* If not all made it in, send IPI NMI to them */ + pr_alert("UV: Sending NMI IPI to %d CPUs: %*pbl\n", cpumask_weight(uv_nmi_cpu_mask), cpumask_pr_args(uv_nmi_cpu_mask)); uv_nmi_nr_cpus_ping(); - /* if all cpus are in, then done */ + /* If all CPU's are in, then done */ if (!uv_nmi_wait_cpus(0)) break; @@ -416,7 +708,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs) this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE); } -/* Trigger a slave cpu to dump it's state */ +/* Trigger a slave CPU to dump it's state */ static void uv_nmi_trigger_dump(int cpu) { int retry = uv_nmi_trigger_delay; @@ -437,7 +729,7 @@ static void uv_nmi_trigger_dump(int cpu) uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE; } -/* Wait until all cpus ready to exit */ +/* Wait until all CPU's ready to exit */ static void uv_nmi_sync_exit(int master) { atomic_dec(&uv_nmi_cpus_in_nmi); @@ -451,7 +743,23 @@ static void uv_nmi_sync_exit(int master) } } -/* Walk through cpu list and dump state of each */ +/* Current "health" check is to check which CPU's are responsive */ +static void uv_nmi_action_health(int cpu, struct pt_regs *regs, int master) +{ + if (master) { + int in = atomic_read(&uv_nmi_cpus_in_nmi); + int out = num_online_cpus() - in; + + pr_alert("UV: NMI CPU health check (non-responding:%d)\n", out); + atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT); + } else { + while (!atomic_read(&uv_nmi_slave_continue)) + cpu_relax(); + } + uv_nmi_sync_exit(master); +} + +/* Walk through CPU list and dump state of each */ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master) { if (master) { @@ -538,7 +846,7 @@ static inline int uv_nmi_kdb_reason(void) #else /* !CONFIG_KGDB_KDB */ static inline int uv_nmi_kdb_reason(void) { - /* Insure user is expecting to attach gdb remote */ + /* Ensure user is expecting to attach gdb remote */ if (uv_nmi_action_is("kgdb")) return 0; @@ -563,7 +871,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) if (reason < 0) return; - /* call KGDB NMI handler as MASTER */ + /* Call KGDB NMI handler as MASTER */ ret = kgdb_nmicallin(cpu, X86_TRAP_NMI, regs, reason, &uv_nmi_slave_continue); if (ret) { @@ -571,7 +879,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT); } } else { - /* wait for KGDB signal that it's ready for slaves to enter */ + /* Wait for KGDB signal that it's ready for slaves to enter */ int sig; do { @@ -579,7 +887,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) sig = atomic_read(&uv_nmi_slave_continue); } while (!sig); - /* call KGDB as slave */ + /* Call KGDB as slave */ if (sig == SLAVE_CONTINUE) kgdb_nmicallback(cpu, regs); } @@ -623,18 +931,23 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) strncpy(uv_nmi_action, "dump", strlen(uv_nmi_action)); } - /* Pause as all cpus enter the NMI handler */ + /* Pause as all CPU's enter the NMI handler */ uv_nmi_wait(master); - /* Dump state of each cpu */ - if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) + /* Process actions other than "kdump": */ + if (uv_nmi_action_is("health")) { + uv_nmi_action_health(cpu, regs, master); + } else if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) { uv_nmi_dump_state(cpu, regs, master); - - /* Call KGDB/KDB if enabled */ - else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) + } else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) { uv_call_kgdb_kdb(cpu, regs, master); + } else { + if (master) + pr_alert("UV: unknown NMI action: %s\n", uv_nmi_action); + uv_nmi_sync_exit(master); + } - /* Clear per_cpu "in nmi" flag */ + /* Clear per_cpu "in_nmi" flag */ this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT); /* Clear MMR NMI flag on each hub */ @@ -648,6 +961,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) atomic_set(&uv_nmi_cpu, -1); atomic_set(&uv_in_nmi, 0); atomic_set(&uv_nmi_kexec_failed, 0); + atomic_set(&uv_nmi_slave_continue, SLAVE_CLEAR); } uv_nmi_touch_watchdogs(); @@ -657,7 +971,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) } /* - * NMI handler for pulling in CPUs when perf events are grabbing our NMI + * NMI handler for pulling in CPU's when perf events are grabbing our NMI */ static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs) { @@ -690,35 +1004,62 @@ void uv_nmi_init(void) unsigned int value; /* - * Unmask NMI on all cpus + * Unmask NMI on all CPU's */ value = apic_read(APIC_LVT1) | APIC_DM_NMI; value &= ~APIC_LVT_MASKED; apic_write(APIC_LVT1, value); } -void uv_nmi_setup(void) +/* Setup HUB NMI info */ +void __init uv_nmi_setup_common(bool hubbed) { int size = sizeof(void *) * (1 << NODES_SHIFT); - int cpu, nid; + int cpu; - /* Setup hub nmi info */ - uv_nmi_setup_mmrs(); uv_hub_nmi_list = kzalloc(size, GFP_KERNEL); - pr_info("UV: NMI hub list @ 0x%p (%d)\n", uv_hub_nmi_list, size); + nmi_debug("UV: NMI hub list @ 0x%p (%d)\n", uv_hub_nmi_list, size); BUG_ON(!uv_hub_nmi_list); size = sizeof(struct uv_hub_nmi_s); for_each_present_cpu(cpu) { - nid = cpu_to_node(cpu); + int nid = cpu_to_node(cpu); if (uv_hub_nmi_list[nid] == NULL) { uv_hub_nmi_list[nid] = kzalloc_node(size, GFP_KERNEL, nid); BUG_ON(!uv_hub_nmi_list[nid]); raw_spin_lock_init(&(uv_hub_nmi_list[nid]->nmi_lock)); atomic_set(&uv_hub_nmi_list[nid]->cpu_owner, -1); + uv_hub_nmi_list[nid]->hub_present = hubbed; + uv_hub_nmi_list[nid]->pch_owner = (nid == 0); } uv_hub_nmi_per(cpu) = uv_hub_nmi_list[nid]; } BUG_ON(!alloc_cpumask_var(&uv_nmi_cpu_mask, GFP_KERNEL)); +} + +/* Setup for UV Hub systems */ +void __init uv_nmi_setup(void) +{ + uv_nmi_setup_mmrs(); + uv_nmi_setup_common(true); + uv_register_nmi_notifier(); + pr_info("UV: Hub NMI enabled\n"); +} + +/* Setup for UV Hubless systems */ +void __init uv_nmi_setup_hubless(void) +{ + uv_nmi_setup_common(false); + pch_base = xlate_dev_mem_ptr(PCH_PCR_GPIO_1_BASE); + nmi_debug("UV: PCH base:%p from 0x%lx, GPP_D_0\n", + pch_base, PCH_PCR_GPIO_1_BASE); + if (uv_pch_init_enable) + uv_init_hubless_pch_d0(); + uv_init_hubless_pch_io(GPI_NMI_ENA_GPP_D_0, + STS_GPP_D_0_MASK, STS_GPP_D_0_MASK); + uv_nmi_setup_hubless_intr(); + /* Ensure NMI enabled in Processor Interface Reg: */ + uv_reassert_nmi(); uv_register_nmi_notifier(); + pr_info("UV: Hubless NMI enabled\n"); } diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index d957d5f21a86..0bc60a308730 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,6 +1,6 @@ config MCE_AMD_INJ tristate "Simple MCE injection interface for AMD processors" - depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB + depends on RAS && X86_MCE && DEBUG_FS && AMD_NB default n help This is a simple debugfs interface to inject MCEs and test different diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index c7b15f3e2cf3..76b6dbd627df 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -53,5 +53,5 @@ config XEN_DEBUG_FS config XEN_PVH bool "Support for running as a PVH guest" - depends on X86_64 && XEN && XEN_PVHVM + depends on XEN && XEN_PVHVM && ACPI def_bool n diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index e47e52787d32..cb0164aee156 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o obj-$(CONFIG_XEN_EFI) += efi.o +obj-$(CONFIG_XEN_PVH) += xen-pvh.o diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 44c88ad1841a..bcea81f36fc5 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -145,7 +145,7 @@ static void xen_silent_inquire(int apicid) static int xen_cpu_present_to_apicid(int cpu) { if (cpu_present(cpu)) - return xen_get_apic_id(xen_apic_read(APIC_ID)); + return cpu_data(cpu).apicid; else return BAD_APICID; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 51ef95232725..ec1d5c46e58f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -45,6 +45,7 @@ #include <xen/interface/memory.h> #include <xen/interface/nmi.h> #include <xen/interface/xen-mca.h> +#include <xen/interface/hvm/start_info.h> #include <xen/features.h> #include <xen/page.h> #include <xen/hvm.h> @@ -176,6 +177,20 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); +#ifdef CONFIG_XEN_PVH +/* + * PVH variables. + * + * xen_pvh and pvh_bootparams need to live in data segment since they + * are used after startup_{32|64}, which clear .bss, are invoked. + */ +bool xen_pvh __attribute__((section(".data"))) = 0; +struct boot_params pvh_bootparams __attribute__((section(".data"))); + +struct hvm_start_info pvh_start_info; +unsigned int pvh_start_info_sz = sizeof(pvh_start_info); +#endif + static void clamp_max_cpus(void) { #ifdef CONFIG_SMP @@ -1138,10 +1153,11 @@ void xen_setup_vcpu_info_placement(void) xen_vcpu_setup(cpu); } - /* xen_vcpu_setup managed to place the vcpu_info within the - * percpu area for all cpus, so make use of it. Note that for - * PVH we want to use native IRQ mechanism. */ - if (have_vcpu_info_placement && !xen_pvh_domain()) { + /* + * xen_vcpu_setup managed to place the vcpu_info within the + * percpu area for all cpus, so make use of it. + */ + if (have_vcpu_info_placement) { pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct); pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct); pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct); @@ -1413,49 +1429,9 @@ static void __init xen_boot_params_init_edd(void) * Set up the GDT and segment registers for -fstack-protector. Until * we do this, we have to be careful not to call any stack-protected * function, which is most of the kernel. - * - * Note, that it is __ref because the only caller of this after init - * is PVH which is not going to use xen_load_gdt_boot or other - * __init functions. */ -static void __ref xen_setup_gdt(int cpu) +static void xen_setup_gdt(int cpu) { - if (xen_feature(XENFEAT_auto_translated_physmap)) { -#ifdef CONFIG_X86_64 - unsigned long dummy; - - load_percpu_segment(cpu); /* We need to access per-cpu area */ - switch_to_new_gdt(cpu); /* GDT and GS set */ - - /* We are switching of the Xen provided GDT to our HVM mode - * GDT. The new GDT has __KERNEL_CS with CS.L = 1 - * and we are jumping to reload it. - */ - asm volatile ("pushq %0\n" - "leaq 1f(%%rip),%0\n" - "pushq %0\n" - "lretq\n" - "1:\n" - : "=&r" (dummy) : "0" (__KERNEL_CS)); - - /* - * While not needed, we also set the %es, %ds, and %fs - * to zero. We don't care about %ss as it is NULL. - * Strictly speaking this is not needed as Xen zeros those - * out (and also MSR_FS_BASE, MSR_GS_BASE, MSR_KERNEL_GS_BASE) - * - * Linux zeros them in cpu_init() and in secondary_startup_64 - * (for BSP). - */ - loadsegment(es, 0); - loadsegment(ds, 0); - loadsegment(fs, 0); -#else - /* PVH: TODO Implement. */ - BUG(); -#endif - return; /* PVH does not need any PV GDT ops. */ - } pv_cpu_ops.write_gdt_entry = xen_write_gdt_entry_boot; pv_cpu_ops.load_gdt = xen_load_gdt_boot; @@ -1466,59 +1442,6 @@ static void __ref xen_setup_gdt(int cpu) pv_cpu_ops.load_gdt = xen_load_gdt; } -#ifdef CONFIG_XEN_PVH -/* - * A PV guest starts with default flags that are not set for PVH, set them - * here asap. - */ -static void xen_pvh_set_cr_flags(int cpu) -{ - - /* Some of these are setup in 'secondary_startup_64'. The others: - * X86_CR0_TS, X86_CR0_PE, X86_CR0_ET are set by Xen for HVM guests - * (which PVH shared codepaths), while X86_CR0_PG is for PVH. */ - write_cr0(read_cr0() | X86_CR0_MP | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM); - - if (!cpu) - return; - /* - * For BSP, PSE PGE are set in probe_page_size_mask(), for APs - * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu(). - */ - if (boot_cpu_has(X86_FEATURE_PSE)) - cr4_set_bits_and_update_boot(X86_CR4_PSE); - - if (boot_cpu_has(X86_FEATURE_PGE)) - cr4_set_bits_and_update_boot(X86_CR4_PGE); -} - -/* - * Note, that it is ref - because the only caller of this after init - * is PVH which is not going to use xen_load_gdt_boot or other - * __init functions. - */ -void __ref xen_pvh_secondary_vcpu_init(int cpu) -{ - xen_setup_gdt(cpu); - xen_pvh_set_cr_flags(cpu); -} - -static void __init xen_pvh_early_guest_init(void) -{ - if (!xen_feature(XENFEAT_auto_translated_physmap)) - return; - - BUG_ON(!xen_feature(XENFEAT_hvm_callback_vector)); - - xen_pvh_early_cpu_init(0, false); - xen_pvh_set_cr_flags(0); - -#ifdef CONFIG_X86_32 - BUG(); /* PVH: Implement proper support. */ -#endif -} -#endif /* CONFIG_XEN_PVH */ - static void __init xen_dom0_set_legacy_features(void) { x86_platform.legacy.rtc = 1; @@ -1555,24 +1478,17 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_domain_type = XEN_PV_DOMAIN; xen_setup_features(); -#ifdef CONFIG_XEN_PVH - xen_pvh_early_guest_init(); -#endif + xen_setup_machphys_mapping(); /* Install Xen paravirt ops */ pv_info = xen_info; pv_init_ops = xen_init_ops; - if (!xen_pvh_domain()) { - pv_cpu_ops = xen_cpu_ops; + pv_cpu_ops = xen_cpu_ops; - x86_platform.get_nmi_reason = xen_get_nmi_reason; - } + x86_platform.get_nmi_reason = xen_get_nmi_reason; - if (xen_feature(XENFEAT_auto_translated_physmap)) - x86_init.resources.memory_setup = xen_auto_xlated_memory_setup; - else - x86_init.resources.memory_setup = xen_memory_setup; + x86_init.resources.memory_setup = xen_memory_setup; x86_init.oem.arch_setup = xen_arch_setup; x86_init.oem.banner = xen_banner; @@ -1665,18 +1581,15 @@ asmlinkage __visible void __init xen_start_kernel(void) /* set the limit of our address space */ xen_reserve_top(); - /* PVH: runs at default kernel iopl of 0 */ - if (!xen_pvh_domain()) { - /* - * We used to do this in xen_arch_setup, but that is too late - * on AMD were early_cpu_init (run before ->arch_setup()) calls - * early_amd_init which pokes 0xcf8 port. - */ - set_iopl.iopl = 1; - rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); - if (rc != 0) - xen_raw_printk("physdev_op failed %d\n", rc); - } + /* + * We used to do this in xen_arch_setup, but that is too late + * on AMD were early_cpu_init (run before ->arch_setup()) calls + * early_amd_init which pokes 0xcf8 port. + */ + set_iopl.iopl = 1; + rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl); + if (rc != 0) + xen_raw_printk("physdev_op failed %d\n", rc); #ifdef CONFIG_X86_32 /* set up basic CPUID stuff */ @@ -1758,6 +1671,102 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif } +#ifdef CONFIG_XEN_PVH + +static void xen_pvh_arch_setup(void) +{ +#ifdef CONFIG_ACPI + /* Make sure we don't fall back to (default) ACPI_IRQ_MODEL_PIC. */ + if (nr_ioapics == 0) + acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM; +#endif +} + +static void __init init_pvh_bootparams(void) +{ + struct xen_memory_map memmap; + unsigned int i; + int rc; + + memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); + + memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map); + set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map); + rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); + if (rc) { + xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); + BUG(); + } + + if (memmap.nr_entries < E820MAX - 1) { + pvh_bootparams.e820_map[memmap.nr_entries].addr = + ISA_START_ADDRESS; + pvh_bootparams.e820_map[memmap.nr_entries].size = + ISA_END_ADDRESS - ISA_START_ADDRESS; + pvh_bootparams.e820_map[memmap.nr_entries].type = + E820_RESERVED; + memmap.nr_entries++; + } else + xen_raw_printk("Warning: Can fit ISA range into e820\n"); + + sanitize_e820_map(pvh_bootparams.e820_map, + ARRAY_SIZE(pvh_bootparams.e820_map), + &memmap.nr_entries); + + pvh_bootparams.e820_entries = memmap.nr_entries; + for (i = 0; i < pvh_bootparams.e820_entries; i++) + e820_add_region(pvh_bootparams.e820_map[i].addr, + pvh_bootparams.e820_map[i].size, + pvh_bootparams.e820_map[i].type); + + pvh_bootparams.hdr.cmd_line_ptr = + pvh_start_info.cmdline_paddr; + + /* The first module is always ramdisk. */ + if (pvh_start_info.nr_modules) { + struct hvm_modlist_entry *modaddr = + __va(pvh_start_info.modlist_paddr); + pvh_bootparams.hdr.ramdisk_image = modaddr->paddr; + pvh_bootparams.hdr.ramdisk_size = modaddr->size; + } + + /* + * See Documentation/x86/boot.txt. + * + * Version 2.12 supports Xen entry point but we will use default x86/PC + * environment (i.e. hardware_subarch 0). + */ + pvh_bootparams.hdr.version = 0x212; + pvh_bootparams.hdr.type_of_loader = (9 << 4) | 0; /* Xen loader */ +} + +/* + * This routine (and those that it might call) should not use + * anything that lives in .bss since that segment will be cleared later. + */ +void __init xen_prepare_pvh(void) +{ + u32 msr; + u64 pfn; + + if (pvh_start_info.magic != XEN_HVM_START_MAGIC_VALUE) { + xen_raw_printk("Error: Unexpected magic value (0x%08x)\n", + pvh_start_info.magic); + BUG(); + } + + xen_pvh = 1; + + msr = cpuid_ebx(xen_cpuid_base() + 2); + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + + init_pvh_bootparams(); + + x86_init.oem.arch_setup = xen_pvh_arch_setup; +} +#endif + void __ref xen_hvm_init_shared_info(void) { int cpu; @@ -1797,20 +1806,29 @@ void __ref xen_hvm_init_shared_info(void) static void __init init_hvm_pv_info(void) { int major, minor; - uint32_t eax, ebx, ecx, edx, pages, msr, base; - u64 pfn; + uint32_t eax, ebx, ecx, edx, base; base = xen_cpuid_base(); - cpuid(base + 1, &eax, &ebx, &ecx, &edx); + eax = cpuid_eax(base + 1); major = eax >> 16; minor = eax & 0xffff; printk(KERN_INFO "Xen version %d.%d.\n", major, minor); - cpuid(base + 2, &pages, &msr, &ecx, &edx); + xen_domain_type = XEN_HVM_DOMAIN; - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + /* PVH set up hypercall page in xen_prepare_pvh(). */ + if (xen_pvh_domain()) + pv_info.name = "Xen PVH"; + else { + u64 pfn; + uint32_t msr; + + pv_info.name = "Xen HVM"; + msr = cpuid_ebx(base + 2); + pfn = __pa(hypercall_page); + wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + } xen_setup_features(); @@ -1819,10 +1837,6 @@ static void __init init_hvm_pv_info(void) this_cpu_write(xen_vcpu_id, ebx); else this_cpu_write(xen_vcpu_id, smp_processor_id()); - - pv_info.name = "Xen HVM"; - - xen_domain_type = XEN_HVM_DOMAIN; } #endif @@ -1910,6 +1924,9 @@ static void __init xen_hvm_guest_init(void) x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); + + if (xen_pvh_domain()) + machine_ops.emergency_restart = xen_emergency_restart; #ifdef CONFIG_KEXEC_CORE machine_ops.shutdown = xen_hvm_shutdown; machine_ops.crash_shutdown = xen_hvm_crash_shutdown; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 7d5afdb417cc..f6740b5b1738 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1792,10 +1792,6 @@ static void __init set_page_prot_flags(void *addr, pgprot_t prot, unsigned long pfn = __pa(addr) >> PAGE_SHIFT; pte_t pte = pfn_pte(pfn, prot); - /* For PVH no need to set R/O or R/W to pin them or unpin them. */ - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags)) BUG(); } @@ -1902,8 +1898,7 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, * level2_ident_pgt, and level2_kernel_pgt. This means that only the * kernel has a physical mapping to start with - but that's enough to * get __va working. We need to fill in the rest of the physical - * mapping once some sort of allocator has been set up. NOTE: for - * PVH, the page tables are native. + * mapping once some sort of allocator has been set up. */ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { @@ -2812,16 +2807,6 @@ static int do_remap_gfn(struct vm_area_struct *vma, BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO))); - if (xen_feature(XENFEAT_auto_translated_physmap)) { -#ifdef CONFIG_XEN_PVH - /* We need to update the local page tables and the xen HAP */ - return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr, - prot, domid, pages); -#else - return -EINVAL; -#endif - } - rmd.mfn = gfn; rmd.prot = prot; /* We use the err_ptr to indicate if there we are doing a contiguous @@ -2915,10 +2900,6 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, if (!pages || !xen_feature(XENFEAT_auto_translated_physmap)) return 0; -#ifdef CONFIG_XEN_PVH - return xen_xlate_unmap_gfn_range(vma, numpgs, pages); -#else return -EINVAL; -#endif } EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 90d1b83cf35f..33a783c77d96 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -73,8 +73,8 @@ bool xen_has_pv_devices(void) if (!xen_domain()) return false; - /* PV domains always have them. */ - if (xen_pv_domain()) + /* PV and PVH domains always have them. */ + if (xen_pv_domain() || xen_pvh_domain()) return true; /* And user has xen_platform_pci=0 set in guest config as diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index f3f7b41116f7..a8c306cf8868 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -915,39 +915,6 @@ char * __init xen_memory_setup(void) } /* - * Machine specific memory setup for auto-translated guests. - */ -char * __init xen_auto_xlated_memory_setup(void) -{ - struct xen_memory_map memmap; - int i; - int rc; - - memmap.nr_entries = ARRAY_SIZE(xen_e820_map); - set_xen_guest_handle(memmap.buffer, xen_e820_map); - - rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); - if (rc < 0) - panic("No memory map (%d)\n", rc); - - xen_e820_map_entries = memmap.nr_entries; - - sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), - &xen_e820_map_entries); - - for (i = 0; i < xen_e820_map_entries; i++) - e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size, - xen_e820_map[i].type); - - /* Remove p2m info, it is not needed. */ - xen_start_info->mfn_list = 0; - xen_start_info->first_p2m_pfn = 0; - xen_start_info->nr_p2m_frames = 0; - - return "Xen"; -} - -/* * Set the bit indicating "nosegneg" library variants should be used. * We only need to bother in pure 32-bit mode; compat 32-bit processes * can have un-truncated segments, so wrapping around is allowed. @@ -1032,8 +999,8 @@ void __init xen_pvmmu_arch_setup(void) void __init xen_arch_setup(void) { xen_panic_handler_init(); - if (!xen_feature(XENFEAT_auto_translated_physmap)) - xen_pvmmu_arch_setup(); + + xen_pvmmu_arch_setup(); #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 311acad7dad2..0dee6f59ea82 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -99,18 +99,8 @@ static void cpu_bringup(void) local_irq_enable(); } -/* - * Note: cpu parameter is only relevant for PVH. The reason for passing it - * is we can't do smp_processor_id until the percpu segments are loaded, for - * which we need the cpu number! So we pass it in rdi as first parameter. - */ -asmlinkage __visible void cpu_bringup_and_idle(int cpu) +asmlinkage __visible void cpu_bringup_and_idle(void) { -#ifdef CONFIG_XEN_PVH - if (xen_feature(XENFEAT_auto_translated_physmap) && - xen_feature(XENFEAT_supervisor_mode_kernel)) - xen_pvh_secondary_vcpu_init(cpu); -#endif cpu_bringup(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } @@ -404,61 +394,47 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) gdt = get_cpu_gdt_table(cpu); #ifdef CONFIG_X86_32 - /* Note: PVH is not yet supported on x86_32. */ ctxt->user_regs.fs = __KERNEL_PERCPU; ctxt->user_regs.gs = __KERNEL_STACK_CANARY; #endif memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; - ctxt->flags = VGCF_IN_KERNEL; - ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ - ctxt->user_regs.ds = __USER_DS; - ctxt->user_regs.es = __USER_DS; - ctxt->user_regs.ss = __KERNEL_DS; + ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; + ctxt->flags = VGCF_IN_KERNEL; + ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ + ctxt->user_regs.ds = __USER_DS; + ctxt->user_regs.es = __USER_DS; + ctxt->user_regs.ss = __KERNEL_DS; - xen_copy_trap_info(ctxt->trap_ctxt); + xen_copy_trap_info(ctxt->trap_ctxt); - ctxt->ldt_ents = 0; + ctxt->ldt_ents = 0; - BUG_ON((unsigned long)gdt & ~PAGE_MASK); + BUG_ON((unsigned long)gdt & ~PAGE_MASK); - gdt_mfn = arbitrary_virt_to_mfn(gdt); - make_lowmem_page_readonly(gdt); - make_lowmem_page_readonly(mfn_to_virt(gdt_mfn)); + gdt_mfn = arbitrary_virt_to_mfn(gdt); + make_lowmem_page_readonly(gdt); + make_lowmem_page_readonly(mfn_to_virt(gdt_mfn)); - ctxt->gdt_frames[0] = gdt_mfn; - ctxt->gdt_ents = GDT_ENTRIES; + ctxt->gdt_frames[0] = gdt_mfn; + ctxt->gdt_ents = GDT_ENTRIES; - ctxt->kernel_ss = __KERNEL_DS; - ctxt->kernel_sp = idle->thread.sp0; + ctxt->kernel_ss = __KERNEL_DS; + ctxt->kernel_sp = idle->thread.sp0; #ifdef CONFIG_X86_32 - ctxt->event_callback_cs = __KERNEL_CS; - ctxt->failsafe_callback_cs = __KERNEL_CS; + ctxt->event_callback_cs = __KERNEL_CS; + ctxt->failsafe_callback_cs = __KERNEL_CS; #else - ctxt->gs_base_kernel = per_cpu_offset(cpu); -#endif - ctxt->event_callback_eip = - (unsigned long)xen_hypervisor_callback; - ctxt->failsafe_callback_eip = - (unsigned long)xen_failsafe_callback; - ctxt->user_regs.cs = __KERNEL_CS; - per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir); - } -#ifdef CONFIG_XEN_PVH - else { - /* - * The vcpu comes on kernel page tables which have the NX pte - * bit set. This means before DS/SS is touched, NX in - * EFER must be set. Hence the following assembly glue code. - */ - ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init; - ctxt->user_regs.rdi = cpu; - ctxt->user_regs.rsi = true; /* entry == true */ - } + ctxt->gs_base_kernel = per_cpu_offset(cpu); #endif + ctxt->event_callback_eip = + (unsigned long)xen_hypervisor_callback; + ctxt->failsafe_callback_eip = + (unsigned long)xen_failsafe_callback; + ctxt->user_regs.cs = __KERNEL_CS; + per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir); + ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs); ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir)); if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt)) diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index c5c16dc4f694..9beef333584a 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -21,12 +21,4 @@ static inline int xen_smp_intr_init(unsigned int cpu) static inline void xen_smp_intr_free(unsigned int cpu) {} #endif /* CONFIG_SMP */ -#ifdef CONFIG_XEN_PVH -extern void xen_pvh_early_cpu_init(int cpu, bool entry); -#else -static inline void xen_pvh_early_cpu_init(int cpu, bool entry) -{ -} -#endif - #endif diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index e8a9ea7d7a21..25a7c4302ce7 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -141,25 +141,6 @@ void __init xen_init_spinlocks(void) pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen); } -/* - * While the jump_label init code needs to happend _after_ the jump labels are - * enabled and before SMP is started. Hence we use pre-SMP initcall level - * init. We cannot do it in xen_init_spinlocks as that is done before - * jump labels are activated. - */ -static __init int xen_init_spinlocks_jump(void) -{ - if (!xen_pvspin) - return 0; - - if (!xen_domain()) - return 0; - - static_key_slow_inc(¶virt_ticketlocks_enabled); - return 0; -} -early_initcall(xen_init_spinlocks_jump); - static __init int xen_parse_nopvspin(char *arg) { xen_pvspin = false; diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7f8d8abf4c1a..37794e42b67d 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -16,25 +16,6 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> -#ifdef CONFIG_XEN_PVH -#define PVH_FEATURES_STR "|writable_descriptor_tables|auto_translated_physmap|supervisor_mode_kernel" -/* Note the lack of 'hvm_callback_vector'. Older hypervisor will - * balk at this being part of XEN_ELFNOTE_FEATURES, so we put it in - * XEN_ELFNOTE_SUPPORTED_FEATURES which older hypervisors will ignore. - */ -#define PVH_FEATURES ((1 << XENFEAT_writable_page_tables) | \ - (1 << XENFEAT_auto_translated_physmap) | \ - (1 << XENFEAT_supervisor_mode_kernel) | \ - (1 << XENFEAT_hvm_callback_vector)) -/* The XENFEAT_writable_page_tables is not stricly necessary as we set that - * up regardless whether this CONFIG option is enabled or not, but it - * clarifies what the right flags need to be. - */ -#else -#define PVH_FEATURES_STR "" -#define PVH_FEATURES (0) -#endif - __INIT ENTRY(startup_xen) cld @@ -54,41 +35,6 @@ ENTRY(startup_xen) __FINIT -#ifdef CONFIG_XEN_PVH -/* - * xen_pvh_early_cpu_init() - early PVH VCPU initialization - * @cpu: this cpu number (%rdi) - * @entry: true if this is a secondary vcpu coming up on this entry - * point, false if this is the boot CPU being initialized for - * the first time (%rsi) - * - * Note: This is called as a function on the boot CPU, and is the entry point - * on the secondary CPU. - */ -ENTRY(xen_pvh_early_cpu_init) - mov %rsi, %r11 - - /* Gather features to see if NX implemented. */ - mov $0x80000001, %eax - cpuid - mov %edx, %esi - - mov $MSR_EFER, %ecx - rdmsr - bts $_EFER_SCE, %eax - - bt $20, %esi - jnc 1f /* No NX, skip setting it */ - bts $_EFER_NX, %eax -1: wrmsr -#ifdef CONFIG_SMP - cmp $0, %r11b - jne cpu_bringup_and_idle -#endif - ret - -#endif /* CONFIG_XEN_PVH */ - .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) @@ -114,10 +60,10 @@ ENTRY(hypercall_page) #endif ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) - ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, .ascii "!writable_page_tables|pae_pgdir_above_4gb"; .asciz PVH_FEATURES_STR) - ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long (PVH_FEATURES) | - (1 << XENFEAT_writable_page_tables) | - (1 << XENFEAT_dom0)) + ELFNOTE(Xen, XEN_ELFNOTE_FEATURES, + .ascii "!writable_page_tables|pae_pgdir_above_4gb") + ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, + .long (1 << XENFEAT_writable_page_tables) | (1 << XENFEAT_dom0)) ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE, .asciz "yes") ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID, diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index ac0a2b0f9e62..f6a41c41ebc7 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -146,5 +146,4 @@ __visible void xen_adjust_exception_frame(void); extern int xen_panic_handler_init(void); -void xen_pvh_secondary_vcpu_init(int cpu); #endif /* XEN_OPS_H */ diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S new file mode 100644 index 000000000000..5e246716d58f --- /dev/null +++ b/arch/x86/xen/xen-pvh.S @@ -0,0 +1,161 @@ +/* + * Copyright C 2016, Oracle and/or its affiliates. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program. If not, see <http://www.gnu.org/licenses/>. + */ + + .code32 + .text +#define _pa(x) ((x) - __START_KERNEL_map) + +#include <linux/elfnote.h> +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/asm.h> +#include <asm/boot.h> +#include <asm/processor-flags.h> +#include <asm/msr.h> +#include <xen/interface/elfnote.h> + + __HEAD + +/* + * Entry point for PVH guests. + * + * Xen ABI specifies the following register state when we come here: + * + * - `ebx`: contains the physical memory address where the loader has placed + * the boot start info structure. + * - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared. + * - `cr4`: all bits are cleared. + * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’ + * and a limit of ‘0xFFFFFFFF’. The selector value is unspecified. + * - `ds`, `es`: must be a 32-bit read/write data segment with a base of + * ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all + * unspecified. + * - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit + * of '0x67'. + * - `eflags`: bit 17 (VM) must be cleared. Bit 9 (IF) must be cleared. + * Bit 8 (TF) must be cleared. Other bits are all unspecified. + * + * All other processor registers and flag bits are unspecified. The OS is in + * charge of setting up it's own stack, GDT and IDT. + */ + +ENTRY(pvh_start_xen) + cld + + lgdt (_pa(gdt)) + + mov $(__BOOT_DS),%eax + mov %eax,%ds + mov %eax,%es + mov %eax,%ss + + /* Stash hvm_start_info. */ + mov $_pa(pvh_start_info), %edi + mov %ebx, %esi + mov _pa(pvh_start_info_sz), %ecx + shr $2,%ecx + rep + movsl + + mov $_pa(early_stack_end), %esp + + /* Enable PAE mode. */ + mov %cr4, %eax + orl $X86_CR4_PAE, %eax + mov %eax, %cr4 + +#ifdef CONFIG_X86_64 + /* Enable Long mode. */ + mov $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + /* Enable pre-constructed page tables. */ + mov $_pa(init_level4_pgt), %eax + mov %eax, %cr3 + mov $(X86_CR0_PG | X86_CR0_PE), %eax + mov %eax, %cr0 + + /* Jump to 64-bit mode. */ + ljmp $__KERNEL_CS, $_pa(1f) + + /* 64-bit entry point. */ + .code64 +1: + call xen_prepare_pvh + + /* startup_64 expects boot_params in %rsi. */ + mov $_pa(pvh_bootparams), %rsi + mov $_pa(startup_64), %rax + jmp *%rax + +#else /* CONFIG_X86_64 */ + + call mk_early_pgtbl_32 + + mov $_pa(initial_page_table), %eax + mov %eax, %cr3 + + mov %cr0, %eax + or $(X86_CR0_PG | X86_CR0_PE), %eax + mov %eax, %cr0 + + ljmp $__BOOT_CS, $1f +1: + call xen_prepare_pvh + mov $_pa(pvh_bootparams), %esi + + /* startup_32 doesn't expect paging and PAE to be on. */ + ljmp $__BOOT_CS, $_pa(2f) +2: + mov %cr0, %eax + and $~X86_CR0_PG, %eax + mov %eax, %cr0 + mov %cr4, %eax + and $~X86_CR4_PAE, %eax + mov %eax, %cr4 + + ljmp $__BOOT_CS, $_pa(startup_32) +#endif +END(pvh_start_xen) + + .section ".init.data","aw" + .balign 8 +gdt: + .word gdt_end - gdt_start + .long _pa(gdt_start) + .word 0 +gdt_start: + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x0000000000000000 /* reserved */ +#ifdef CONFIG_X86_64 + .quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* __KERNEL_CS */ +#else + .quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* __KERNEL_CS */ +#endif + .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* __KERNEL_DS */ +gdt_end: + + .balign 4 +early_stack: + .fill 256, 1, 0 +early_stack_end: + + ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, + _ASM_PTR (pvh_start_xen - __START_KERNEL_map)) |