diff options
Diffstat (limited to 'arch/x86')
135 files changed, 2538 insertions, 3045 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 97956b56074d..42bc6fb0d2be 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -96,7 +96,7 @@ config X86 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANTS_THP_SWAP if X86_64 - select BUILDTIME_EXTABLE_SORT + select BUILDTIME_TABLE_SORT select CLKEVT_I8253 select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CLOCKSOURCE_WATCHDOG @@ -124,6 +124,7 @@ config X86 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY + select GENERIC_VDSO_TIME_NS select GUP_GET_PTE_LOW_HIGH if X86_PAE select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI @@ -456,6 +457,7 @@ config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS + select PROC_CPU_RESCTRL if PROC_FS help Enable x86 CPU resource control support. @@ -1512,7 +1514,7 @@ config X86_CPA_STATISTICS bool "Enable statistic for Change Page Attribute" depends on DEBUG_FS ---help--- - Expose statistics about the Change Page Attribute mechanims, which + Expose statistics about the Change Page Attribute mechanism, which helps to determine the effectiveness of preserving large and huge page mappings when mapping protections are changed. @@ -1993,6 +1995,7 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI && !X86_USE_3DNOW + depends on $(cc-option,-mabi=ms) || X86_32 select RELOCATABLE ---help--- This kernel feature allows a bzImage to be loaded directly diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 95410d6ee2ff..748b6d28a91d 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -88,7 +88,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index aa976adb7094..56aa5fa0a66b 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -89,7 +89,7 @@ vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone -vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \ +vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o \ $(objtree)/drivers/firmware/efi/libstub/lib.a vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o @@ -103,7 +103,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o quiet_cmd_check_data_rel = DATAREL $@ define cmd_check_data_rel for obj in $(filter %.o,$^); do \ - ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \ + $(READELF) -S $$obj | grep -qF .rel.local && { \ echo "error: $$obj has data relocations!" >&2; \ exit 1; \ } || true; \ diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 72b08fde6de6..287393d725f0 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -6,6 +6,8 @@ * * ----------------------------------------------------------------------- */ +#pragma GCC visibility push(hidden) + #include <linux/efi.h> #include <linux/pci.h> @@ -19,32 +21,18 @@ #include "eboot.h" static efi_system_table_t *sys_table; +extern const bool efi_is64; -static struct efi_config *efi_early; - -__pure const struct efi_config *__efi_early(void) +__pure efi_system_table_t *efi_system_table(void) { - return efi_early; + return sys_table; } -#define BOOT_SERVICES(bits) \ -static void setup_boot_services##bits(struct efi_config *c) \ -{ \ - efi_system_table_##bits##_t *table; \ - \ - 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 *table, efi_char16_t *str) +__attribute_const__ bool efi_is_64bit(void) { - efi_call_proto(efi_simple_text_output_protocol, output_string, - efi_early->text_output, str); + if (IS_ENABLED(CONFIG_EFI_MIXED)) + return efi_is64; + return IS_ENABLED(CONFIG_X86_64); } static efi_status_t @@ -63,17 +51,17 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) * large romsize. The UEFI spec limits the size of option ROMs to 16 * MiB so we reject any ROMs over 16 MiB in size to catch this. */ - romimage = (void *)(unsigned long)efi_table_attr(efi_pci_io_protocol, - romimage, pci); - romsize = efi_table_attr(efi_pci_io_protocol, romsize, pci); + romimage = efi_table_attr(pci, romimage); + romsize = efi_table_attr(pci, romsize); if (!romimage || !romsize || romsize > SZ_16M) return EFI_INVALID_PARAMETER; size = romsize + sizeof(*rom); - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)&rom); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'rom'\n"); + efi_printk("Failed to allocate memory for 'rom'\n"); return status; } @@ -85,27 +73,24 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) rom->pcilen = pci->romsize; *__rom = rom; - status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, - EfiPciIoWidthUint16, PCI_VENDOR_ID, 1, - &rom->vendor); + status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, + PCI_VENDOR_ID, 1, &rom->vendor); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to read rom->vendor\n"); + efi_printk("Failed to read rom->vendor\n"); goto free_struct; } - status = efi_call_proto(efi_pci_io_protocol, pci.read, pci, - EfiPciIoWidthUint16, PCI_DEVICE_ID, 1, - &rom->devid); + status = efi_call_proto(pci, pci.read, EfiPciIoWidthUint16, + PCI_DEVICE_ID, 1, &rom->devid); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to read rom->devid\n"); + efi_printk("Failed to read rom->devid\n"); goto free_struct; } - status = efi_call_proto(efi_pci_io_protocol, get_location, pci, - &rom->segment, &rom->bus, &rom->device, - &rom->function); + status = efi_call_proto(pci, get_location, &rom->segment, &rom->bus, + &rom->device, &rom->function); if (status != EFI_SUCCESS) goto free_struct; @@ -114,7 +99,7 @@ preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) return status; free_struct: - efi_call_early(free_pool, rom); + efi_bs_call(free_pool, rom); return status; } @@ -133,27 +118,24 @@ static void setup_efi_pci(struct boot_params *params) void **pci_handle = NULL; efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID; unsigned long size = 0; - unsigned long nr_pci; struct setup_data *data; + efi_handle_t h; int i; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - &pci_proto, NULL, &size, pci_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &size, pci_handle); if (status == EFI_BUFFER_TOO_SMALL) { - status = efi_call_early(allocate_pool, - EFI_LOADER_DATA, - size, (void **)&pci_handle); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)&pci_handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n"); + efi_printk("Failed to allocate memory for 'pci_handle'\n"); return; } - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, &pci_proto, - NULL, &size, pci_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &pci_proto, NULL, &size, pci_handle); } if (status != EFI_SUCCESS) @@ -164,15 +146,12 @@ static void setup_efi_pci(struct boot_params *params) while (data && data->next) data = (struct setup_data *)(unsigned long)data->next; - nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); - for (i = 0; i < nr_pci; i++) { + for_each_efi_handle(h, pci_handle, size, i) { efi_pci_io_protocol_t *pci = NULL; struct pci_setup_rom *rom; - status = efi_call_early(handle_protocol, - efi_is_64bit() ? ((u64 *)pci_handle)[i] - : ((u32 *)pci_handle)[i], - &pci_proto, (void **)&pci); + status = efi_bs_call(handle_protocol, h, &pci_proto, + (void **)&pci); if (status != EFI_SUCCESS || !pci) continue; @@ -189,7 +168,7 @@ static void setup_efi_pci(struct boot_params *params) } free_handle: - efi_call_early(free_pool, pci_handle); + efi_bs_call(free_pool, pci_handle); } static void retrieve_apple_device_properties(struct boot_params *boot_params) @@ -198,34 +177,34 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params) struct setup_data *data, *new; efi_status_t status; u32 size = 0; - void *p; + apple_properties_protocol_t *p; - status = efi_call_early(locate_protocol, &guid, NULL, &p); + status = efi_bs_call(locate_protocol, &guid, NULL, (void **)&p); if (status != EFI_SUCCESS) return; - if (efi_table_attr(apple_properties_protocol, version, p) != 0x10000) { - efi_printk(sys_table, "Unsupported properties proto version\n"); + if (efi_table_attr(p, version) != 0x10000) { + efi_printk("Unsupported properties proto version\n"); return; } - efi_call_proto(apple_properties_protocol, get_all, p, NULL, &size); + efi_call_proto(p, get_all, NULL, &size); if (!size) return; do { - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size + sizeof(struct setup_data), &new); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + size + sizeof(struct setup_data), + (void **)&new); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'properties'\n"); + efi_printk("Failed to allocate memory for 'properties'\n"); return; } - status = efi_call_proto(apple_properties_protocol, get_all, p, - new->data, &size); + status = efi_call_proto(p, get_all, new->data, &size); if (status == EFI_BUFFER_TOO_SMALL) - efi_call_early(free_pool, new); + efi_bs_call(free_pool, new); } while (status == EFI_BUFFER_TOO_SMALL); new->type = SETUP_APPLE_PROPERTIES; @@ -247,7 +226,7 @@ static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params) { efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor, sys_table); + efi_table_attr(efi_system_table(), fw_vendor); if (!memcmp(fw_vendor, apple, sizeof(apple))) { if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) @@ -265,17 +244,16 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) u32 width, height; void **uga_handle = NULL; efi_uga_draw_protocol_t *uga = NULL, *first_uga; - unsigned long nr_ugas; + efi_handle_t handle; int i; - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&uga_handle); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)&uga_handle); if (status != EFI_SUCCESS) return status; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - uga_proto, NULL, &size, uga_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + uga_proto, NULL, &size, uga_handle); if (status != EFI_SUCCESS) goto free_handle; @@ -283,24 +261,20 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) width = 0; first_uga = NULL; - nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32)); - for (i = 0; i < nr_ugas; i++) { + for_each_efi_handle(handle, uga_handle, size, i) { efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID; u32 w, h, depth, refresh; void *pciio; - unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i] - : ((u32 *)uga_handle)[i]; - status = efi_call_early(handle_protocol, handle, - uga_proto, (void **)&uga); + status = efi_bs_call(handle_protocol, handle, uga_proto, + (void **)&uga); if (status != EFI_SUCCESS) continue; pciio = NULL; - efi_call_early(handle_protocol, handle, &pciio_proto, &pciio); + efi_bs_call(handle_protocol, handle, &pciio_proto, &pciio); - status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga, - &w, &h, &depth, &refresh); + status = efi_call_proto(uga, get_mode, &w, &h, &depth, &refresh); if (status == EFI_SUCCESS && (!first_uga || pciio)) { width = w; height = h; @@ -336,7 +310,7 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size) si->rsvd_pos = 24; free_handle: - efi_call_early(free_pool, uga_handle); + efi_bs_call(free_pool, uga_handle); return status; } @@ -355,37 +329,38 @@ void setup_graphics(struct boot_params *boot_params) memset(si, 0, sizeof(*si)); size = 0; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - &graphics_proto, NULL, &size, gop_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &graphics_proto, NULL, &size, gop_handle); if (status == EFI_BUFFER_TOO_SMALL) - status = efi_setup_gop(NULL, si, &graphics_proto, size); + status = efi_setup_gop(si, &graphics_proto, size); if (status != EFI_SUCCESS) { size = 0; - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - &uga_proto, NULL, &size, uga_handle); + status = efi_bs_call(locate_handle, EFI_LOCATE_BY_PROTOCOL, + &uga_proto, NULL, &size, uga_handle); if (status == EFI_BUFFER_TOO_SMALL) setup_uga(si, &uga_proto, size); } } +void startup_32(struct boot_params *boot_params); + +void __noreturn efi_stub_entry(efi_handle_t handle, + efi_system_table_t *sys_table_arg, + struct boot_params *boot_params); + /* * Because the x86 boot code expects to be passed a boot_params we * need to create one ourselves (usually the bootloader would create * one for us). - * - * The caller is responsible for filling out ->code32_start in the - * returned boot_params. */ -struct boot_params *make_boot_params(struct efi_config *c) +efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, + efi_system_table_t *sys_table_arg) { struct boot_params *boot_params; struct apm_bios_info *bi; struct setup_header *hdr; efi_loaded_image_t *image; - void *handle; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; @@ -393,31 +368,22 @@ struct boot_params *make_boot_params(struct efi_config *c) unsigned long ramdisk_addr; unsigned long ramdisk_size; - efi_early = c; - sys_table = (efi_system_table_t *)(unsigned long)efi_early->table; - handle = (void *)(unsigned long)efi_early->image_handle; + sys_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) - return NULL; - - if (efi_is_64bit()) - setup_boot_services64(efi_early); - else - setup_boot_services32(efi_early); + return EFI_INVALID_PARAMETER; - status = efi_call_early(handle_protocol, handle, - &proto, (void *)&image); + status = efi_bs_call(handle_protocol, handle, &proto, (void *)&image); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); - return NULL; + efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); + return status; } - status = efi_low_alloc(sys_table, 0x4000, 1, - (unsigned long *)&boot_params); + status = efi_low_alloc(0x4000, 1, (unsigned long *)&boot_params); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate lowmem for boot params\n"); - return NULL; + efi_printk("Failed to allocate lowmem for boot params\n"); + return status; } memset(boot_params, 0x0, 0x4000); @@ -439,7 +405,7 @@ struct boot_params *make_boot_params(struct efi_config *c) hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); + cmdline_ptr = efi_convert_cmdline(image, &options_size); if (!cmdline_ptr) goto fail; @@ -457,15 +423,15 @@ struct boot_params *make_boot_params(struct efi_config *c) if (status != EFI_SUCCESS) goto fail2; - status = handle_cmdline_files(sys_table, image, + status = handle_cmdline_files(image, (char *)(unsigned long)hdr->cmd_line_ptr, "initrd=", hdr->initrd_addr_max, &ramdisk_addr, &ramdisk_size); if (status != EFI_SUCCESS && hdr->xloadflags & XLF_CAN_BE_LOADED_ABOVE_4G) { - efi_printk(sys_table, "Trying to load files to higher address\n"); - status = handle_cmdline_files(sys_table, image, + efi_printk("Trying to load files to higher address\n"); + status = handle_cmdline_files(image, (char *)(unsigned long)hdr->cmd_line_ptr, "initrd=", -1UL, &ramdisk_addr, &ramdisk_size); @@ -478,14 +444,17 @@ struct boot_params *make_boot_params(struct efi_config *c) boot_params->ext_ramdisk_image = (u64)ramdisk_addr >> 32; boot_params->ext_ramdisk_size = (u64)ramdisk_size >> 32; - return boot_params; + hdr->code32_start = (u32)(unsigned long)startup_32; + + efi_stub_entry(handle, sys_table, boot_params); + /* not reached */ fail2: - efi_free(sys_table, options_size, hdr->cmd_line_ptr); + efi_free(options_size, hdr->cmd_line_ptr); fail: - efi_free(sys_table, 0x4000, (unsigned long)boot_params); + efi_free(0x4000, (unsigned long)boot_params); - return NULL; + return status; } static void add_e820ext(struct boot_params *params, @@ -620,13 +589,13 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, sizeof(struct e820_entry) * nr_desc; if (*e820ext) { - efi_call_early(free_pool, *e820ext); + efi_bs_call(free_pool, *e820ext); *e820ext = NULL; *e820ext_size = 0; } - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)e820ext); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, size, + (void **)e820ext); if (status == EFI_SUCCESS) *e820ext_size = size; @@ -650,7 +619,7 @@ static efi_status_t allocate_e820(struct boot_params *params, boot_map.key_ptr = NULL; boot_map.buff_size = &buff_size; - status = efi_get_memory_map(sys_table, &boot_map); + status = efi_get_memory_map(&boot_map); if (status != EFI_SUCCESS) return status; @@ -672,8 +641,7 @@ struct exit_boot_struct { struct efi_info *efi; }; -static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, - struct efi_boot_memmap *map, +static efi_status_t exit_boot_func(struct efi_boot_memmap *map, void *priv) { const char *signature; @@ -683,14 +651,14 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, : EFI32_LOADER_SIGNATURE; memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32)); - p->efi->efi_systab = (unsigned long)sys_table_arg; + p->efi->efi_systab = (unsigned long)efi_system_table(); p->efi->efi_memdesc_size = *map->desc_size; p->efi->efi_memdesc_version = *map->desc_ver; p->efi->efi_memmap = (unsigned long)*map->map; p->efi->efi_memmap_size = *map->map_size; #ifdef CONFIG_X86_64 - p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32; + p->efi->efi_systab_hi = (unsigned long)efi_system_table() >> 32; p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32; #endif @@ -722,8 +690,7 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) return status; /* Might as well exit boot services now */ - status = efi_exit_boot_services(sys_table, handle, &map, &priv, - exit_boot_func); + status = efi_exit_boot_services(handle, &map, &priv, exit_boot_func); if (status != EFI_SUCCESS) return status; @@ -741,33 +708,22 @@ static efi_status_t exit_boot(struct boot_params *boot_params, void *handle) * On success we return a pointer to a boot_params structure, and NULL * on failure. */ -struct boot_params * -efi_main(struct efi_config *c, struct boot_params *boot_params) +struct boot_params *efi_main(efi_handle_t handle, + efi_system_table_t *sys_table_arg, + struct boot_params *boot_params) { struct desc_ptr *gdt = NULL; struct setup_header *hdr = &boot_params->hdr; efi_status_t status; struct desc_struct *desc; - void *handle; - efi_system_table_t *_table; unsigned long cmdline_paddr; - efi_early = c; - - _table = (efi_system_table_t *)(unsigned long)efi_early->table; - handle = (void *)(unsigned long)efi_early->image_handle; - - sys_table = _table; + sys_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) goto fail; - if (efi_is_64bit()) - setup_boot_services64(efi_early); - else - setup_boot_services32(efi_early); - /* * make_boot_params() may have been called before efi_main(), in which * case this is the second time we parse the cmdline. This is ok, @@ -782,14 +738,14 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) * otherwise we ask the BIOS. */ if (boot_params->secure_boot == efi_secureboot_mode_unset) - boot_params->secure_boot = efi_get_secureboot(sys_table); + boot_params->secure_boot = efi_get_secureboot(); /* Ask the firmware to clear memory on unclean shutdown */ - efi_enable_reset_attack_mitigation(sys_table); + efi_enable_reset_attack_mitigation(); - efi_random_get_seed(sys_table); + efi_random_get_seed(); - efi_retrieve_tpm2_eventlog(sys_table); + efi_retrieve_tpm2_eventlog(); setup_graphics(boot_params); @@ -797,18 +753,17 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) setup_quirks(boot_params); - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - sizeof(*gdt), (void **)&gdt); + status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, sizeof(*gdt), + (void **)&gdt); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n"); + efi_printk("Failed to allocate memory for 'gdt' structure\n"); goto fail; } gdt->size = 0x800; - status = efi_low_alloc(sys_table, gdt->size, 8, - (unsigned long *)&gdt->address); + status = efi_low_alloc(gdt->size, 8, (unsigned long *)&gdt->address); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n"); + efi_printk("Failed to allocate memory for 'gdt'\n"); goto fail; } @@ -818,13 +773,13 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) */ if (hdr->pref_address != hdr->code32_start) { unsigned long bzimage_addr = hdr->code32_start; - status = efi_relocate_kernel(sys_table, &bzimage_addr, + status = efi_relocate_kernel(&bzimage_addr, hdr->init_size, hdr->init_size, hdr->pref_address, hdr->kernel_alignment, LOAD_PHYSICAL_ADDR); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "efi_relocate_kernel() failed!\n"); + efi_printk("efi_relocate_kernel() failed!\n"); goto fail; } @@ -834,7 +789,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) status = exit_boot(boot_params, handle); if (status != EFI_SUCCESS) { - efi_printk(sys_table, "exit_boot() failed!\n"); + efi_printk("exit_boot() failed!\n"); goto fail; } @@ -927,7 +882,8 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) return boot_params; fail: - efi_printk(sys_table, "efi_main() failed!\n"); + efi_printk("efi_main() failed!\n"); - return NULL; + for (;;) + asm("hlt"); } diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 8297387c4676..99f35343d443 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -12,22 +12,20 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -typedef struct { - u32 get_mode; - u32 set_mode; - u32 blt; -} efi_uga_draw_protocol_32_t; +typedef union efi_uga_draw_protocol efi_uga_draw_protocol_t; -typedef struct { - u64 get_mode; - u64 set_mode; - u64 blt; -} efi_uga_draw_protocol_64_t; - -typedef struct { - void *get_mode; - void *set_mode; - void *blt; -} efi_uga_draw_protocol_t; +union efi_uga_draw_protocol { + struct { + efi_status_t (__efiapi *get_mode)(efi_uga_draw_protocol_t *, + u32*, u32*, u32*, u32*); + void *set_mode; + void *blt; + }; + struct { + u32 get_mode; + u32 set_mode; + u32 blt; + } mixed_mode; +}; #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S deleted file mode 100644 index ed6c351d34ed..000000000000 --- a/arch/x86/boot/compressed/efi_stub_32.S +++ /dev/null @@ -1,87 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * EFI call stub for IA32. - * - * This stub allows us to make EFI calls in physical mode with interrupts - * turned off. Note that this implementation is different from the one in - * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical - * mode at this point. - */ - -#include <linux/linkage.h> -#include <asm/page_types.h> - -/* - * efi_call_phys(void *, ...) is a function with variable parameters. - * All the callers of this function assure that all the parameters are 4-bytes. - */ - -/* - * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save. - * So we'd better save all of them at the beginning of this function and restore - * at the end no matter how many we use, because we can not assure EFI runtime - * service functions will comply with gcc calling convention, too. - */ - -.text -SYM_FUNC_START(efi_call_phys) - /* - * 0. The function can only be called in Linux kernel. So CS has been - * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found - * the values of these registers are the same. And, the corresponding - * GDT entries are identical. So I will do nothing about segment reg - * and GDT, but change GDT base register in prelog and epilog. - */ - - /* - * 1. Because we haven't been relocated by this point we need to - * use relative addressing. - */ - call 1f -1: popl %edx - subl $1b, %edx - - /* - * 2. Now on the top of stack is the return - * address in the caller of efi_call_phys(), then parameter 1, - * parameter 2, ..., param n. To make things easy, we save the return - * address of efi_call_phys in a global variable. - */ - popl %ecx - movl %ecx, saved_return_addr(%edx) - /* get the function pointer into ECX*/ - popl %ecx - movl %ecx, efi_rt_function_ptr(%edx) - - /* - * 3. Call the physical function. - */ - call *%ecx - - /* - * 4. Balance the stack. And because EAX contain the return value, - * we'd better not clobber it. We need to calculate our address - * again because %ecx and %edx are not preserved across EFI function - * calls. - */ - call 1f -1: popl %edx - subl $1b, %edx - - movl efi_rt_function_ptr(%edx), %ecx - pushl %ecx - - /* - * 10. Push the saved return address onto the stack and return. - */ - movl saved_return_addr(%edx), %ecx - pushl %ecx - ret -SYM_FUNC_END(efi_call_phys) -.previous - -.data -saved_return_addr: - .long 0 -efi_rt_function_ptr: - .long 0 diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S deleted file mode 100644 index 99494dff2113..000000000000 --- a/arch/x86/boot/compressed/efi_stub_64.S +++ /dev/null @@ -1,5 +0,0 @@ -#include <asm/segment.h> -#include <asm/msr.h> -#include <asm/processor-flags.h> - -#include "../../platform/efi/efi_stub_64.S" diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index 593913692d16..8fb7f6799c52 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -10,7 +10,7 @@ * needs to be able to service interrupts. * * On the plus side, we don't have to worry about mangling 64-bit - * addresses into 32-bits because we're executing with an identify + * addresses into 32-bits because we're executing with an identity * mapped pagetable and haven't transitioned to 64-bit virtual addresses * yet. */ @@ -23,16 +23,13 @@ .code64 .text -SYM_FUNC_START(efi64_thunk) +SYM_FUNC_START(__efi64_thunk) push %rbp push %rbx - subq $8, %rsp - leaq efi_exit32(%rip), %rax - movl %eax, 4(%rsp) - leaq efi_gdt64(%rip), %rax - movl %eax, (%rsp) - movl %eax, 2(%rax) /* Fixup the gdt base address */ + leaq 1f(%rip), %rbp + leaq efi_gdt64(%rip), %rbx + movl %ebx, 2(%rbx) /* Fixup the gdt base address */ movl %ds, %eax push %rax @@ -48,15 +45,10 @@ SYM_FUNC_START(efi64_thunk) movl %esi, 0x0(%rsp) movl %edx, 0x4(%rsp) movl %ecx, 0x8(%rsp) - movq %r8, %rsi - movl %esi, 0xc(%rsp) - movq %r9, %rsi - movl %esi, 0x10(%rsp) + movl %r8d, 0xc(%rsp) + movl %r9d, 0x10(%rsp) - sgdt save_gdt(%rip) - - leaq 1f(%rip), %rbx - movq %rbx, func_rt_ptr(%rip) + sgdt 0x14(%rsp) /* * Switch to gdt with 32-bit segments. This is the firmware GDT @@ -71,9 +63,9 @@ SYM_FUNC_START(efi64_thunk) pushq %rax lretq -1: addq $32, %rsp - - lgdt save_gdt(%rip) +1: lgdt 0x14(%rsp) + addq $32, %rsp + movq %rdi, %rax pop %rbx movl %ebx, %ss @@ -85,26 +77,13 @@ SYM_FUNC_START(efi64_thunk) /* * Convert 32-bit status code into 64-bit. */ - test %rax, %rax - jz 1f - movl %eax, %ecx - andl $0x0fffffff, %ecx - andl $0xf0000000, %eax - shl $32, %rax - or %rcx, %rax -1: - addq $8, %rsp + roll $1, %eax + rorq $1, %rax + pop %rbx pop %rbp ret -SYM_FUNC_END(efi64_thunk) - -SYM_FUNC_START_LOCAL(efi_exit32) - movq func_rt_ptr(%rip), %rax - push %rax - mov %rdi, %rax - ret -SYM_FUNC_END(efi_exit32) +SYM_FUNC_END(__efi64_thunk) .code32 /* @@ -144,9 +123,7 @@ SYM_FUNC_START_LOCAL(efi_enter32) */ cli - movl 56(%esp), %eax - movl %eax, 2(%eax) - lgdtl (%eax) + lgdtl (%ebx) movl %cr4, %eax btsl $(X86_CR4_PAE_BIT), %eax @@ -163,9 +140,8 @@ SYM_FUNC_START_LOCAL(efi_enter32) xorl %eax, %eax lldt %ax - movl 60(%esp), %eax pushl $__KERNEL_CS - pushl %eax + pushl %ebp /* Enable paging */ movl %cr0, %eax @@ -181,13 +157,6 @@ SYM_DATA_START(efi32_boot_gdt) .quad 0 SYM_DATA_END(efi32_boot_gdt) -SYM_DATA_START_LOCAL(save_gdt) - .word 0 - .quad 0 -SYM_DATA_END(save_gdt) - -SYM_DATA_LOCAL(func_rt_ptr, .quad 0) - SYM_DATA_START(efi_gdt64) .word efi_gdt64_end - efi_gdt64 .long 0 /* Filled out by user */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f2dfd6d083ef..73f17d0544dd 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -145,67 +145,16 @@ SYM_FUNC_START(startup_32) SYM_FUNC_END(startup_32) #ifdef CONFIG_EFI_STUB -/* - * We don't need the return address, so set up the stack so efi_main() can find - * its arguments. - */ -SYM_FUNC_START(efi_pe_entry) - add $0x4, %esp - - call 1f -1: popl %esi - subl $1b, %esi - - popl %ecx - movl %ecx, efi32_config(%esi) /* Handle */ - popl %ecx - movl %ecx, efi32_config+8(%esi) /* EFI System table pointer */ - - /* Relocate efi_config->call() */ - leal efi32_config(%esi), %eax - add %esi, 40(%eax) - pushl %eax - - call make_boot_params - cmpl $0, %eax - je fail - movl %esi, BP_code32_start(%eax) - popl %ecx - pushl %eax - pushl %ecx - jmp 2f /* Skip efi_config initialization */ -SYM_FUNC_END(efi_pe_entry) - SYM_FUNC_START(efi32_stub_entry) +SYM_FUNC_START_ALIAS(efi_stub_entry) add $0x4, %esp - popl %ecx - popl %edx - - call 1f -1: popl %esi - subl $1b, %esi - - movl %ecx, efi32_config(%esi) /* Handle */ - movl %edx, efi32_config+8(%esi) /* EFI System table pointer */ - - /* Relocate efi_config->call() */ - leal efi32_config(%esi), %eax - add %esi, 40(%eax) - pushl %eax -2: call efi_main - cmpl $0, %eax movl %eax, %esi - jne 2f -fail: - /* EFI init failed, so hang. */ - hlt - jmp fail -2: movl BP_code32_start(%esi), %eax leal startup_32(%eax), %eax jmp *%eax SYM_FUNC_END(efi32_stub_entry) +SYM_FUNC_END_ALIAS(efi_stub_entry) #endif .text @@ -240,11 +189,9 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) /* push arguments for extract_kernel: */ pushl $z_output_len /* decompressed length, end of relocs */ - movl BP_init_size(%esi), %eax - subl $_end, %eax - movl %ebx, %ebp - subl %eax, %ebp - pushl %ebp /* output address */ + leal _end(%ebx), %eax + subl BP_init_size(%esi), %eax + pushl %eax /* output address */ pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax @@ -262,15 +209,6 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) jmp *%eax SYM_FUNC_END(.Lrelocated) -#ifdef CONFIG_EFI_STUB - .data -efi32_config: - .fill 5,8,0 - .long efi_call_phys - .long 0 - .byte 0 -#endif - /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 58a512e33d8d..1f1f6c8139b3 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -208,10 +208,12 @@ SYM_FUNC_START(startup_32) pushl $__KERNEL_CS leal startup_64(%ebp), %eax #ifdef CONFIG_EFI_MIXED - movl efi32_config(%ebp), %ebx - cmp $0, %ebx + movl efi32_boot_args(%ebp), %edi + cmp $0, %edi jz 1f - leal handover_entry(%ebp), %eax + leal efi64_stub_entry(%ebp), %eax + movl %esi, %edx + movl efi32_boot_args+4(%ebp), %esi 1: #endif pushl %eax @@ -232,17 +234,19 @@ SYM_FUNC_START(efi32_stub_entry) popl %edx popl %esi - leal (BP_scratch+4)(%esi), %esp call 1f 1: pop %ebp subl $1b, %ebp - movl %ecx, efi32_config(%ebp) - movl %edx, efi32_config+8(%ebp) + movl %ecx, efi32_boot_args(%ebp) + movl %edx, efi32_boot_args+4(%ebp) sgdtl efi32_boot_gdt(%ebp) + movb $0, efi_is64(%ebp) - leal efi32_config(%ebp), %eax - movl %eax, efi_config(%ebp) + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 jmp startup_32 SYM_FUNC_END(efi32_stub_entry) @@ -445,70 +449,17 @@ trampoline_return: SYM_CODE_END(startup_64) #ifdef CONFIG_EFI_STUB - -/* The entry point for the PE/COFF executable is efi_pe_entry. */ -SYM_FUNC_START(efi_pe_entry) - movq %rcx, efi64_config(%rip) /* Handle */ - movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ - - leaq efi64_config(%rip), %rax - movq %rax, efi_config(%rip) - - call 1f -1: popq %rbp - subq $1b, %rbp - - /* - * Relocate efi_config->call(). - */ - addq %rbp, efi64_config+40(%rip) - - movq %rax, %rdi - call make_boot_params - cmpq $0,%rax - je fail - mov %rax, %rsi - leaq startup_32(%rip), %rax - movl %eax, BP_code32_start(%rsi) - jmp 2f /* Skip the relocation */ - -handover_entry: - call 1f -1: popq %rbp - subq $1b, %rbp - - /* - * Relocate efi_config->call(). - */ - movq efi_config(%rip), %rax - addq %rbp, 40(%rax) -2: - movq efi_config(%rip), %rdi + .org 0x390 +SYM_FUNC_START(efi64_stub_entry) +SYM_FUNC_START_ALIAS(efi_stub_entry) + and $~0xf, %rsp /* realign the stack */ call efi_main movq %rax,%rsi - cmpq $0,%rax - jne 2f -fail: - /* EFI init failed, so hang. */ - hlt - jmp fail -2: movl BP_code32_start(%esi), %eax leaq startup_64(%rax), %rax jmp *%rax -SYM_FUNC_END(efi_pe_entry) - - .org 0x390 -SYM_FUNC_START(efi64_stub_entry) - movq %rdi, efi64_config(%rip) /* Handle */ - movq %rsi, efi64_config+8(%rip) /* EFI System table pointer */ - - leaq efi64_config(%rip), %rax - movq %rax, efi_config(%rip) - - movq %rdx, %rsi - jmp handover_entry SYM_FUNC_END(efi64_stub_entry) +SYM_FUNC_END_ALIAS(efi_stub_entry) #endif .text @@ -677,24 +628,11 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x0000000000000000 /* TS continued */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) -#ifdef CONFIG_EFI_STUB -SYM_DATA_LOCAL(efi_config, .quad 0) - #ifdef CONFIG_EFI_MIXED -SYM_DATA_START(efi32_config) - .fill 5,8,0 - .quad efi64_thunk - .byte 0 -SYM_DATA_END(efi32_config) +SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0) +SYM_DATA(efi_is64, .byte 1) #endif -SYM_DATA_START(efi64_config) - .fill 5,8,0 - .quad efi_call - .byte 1 -SYM_DATA_END(efi64_config) -#endif /* CONFIG_EFI_STUB */ - /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 0149e41d42c2..3da1c37c6dd5 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -51,7 +51,10 @@ SECTIONS . = ALIGN(16); _end = .; - /DISCARD/ : { *(.note*) } + /DISCARD/ : { + *(.eh_frame) + *(.note*) + } /* * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 76942cbd95a1..f2bb91e87877 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1728,7 +1728,7 @@ SYM_CODE_END(nmi) SYM_CODE_START(ignore_sysret) UNWIND_HINT_EMPTY mov $-ENOSYS, %eax - sysret + sysretl SYM_CODE_END(ignore_sysret) #endif diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index 93c6dc7812d0..ea7e0155c604 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -16,18 +16,23 @@ SECTIONS * segment. */ - vvar_start = . - 3 * PAGE_SIZE; - vvar_page = vvar_start; + vvar_start = . - 4 * PAGE_SIZE; + vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ #define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; -#define __VVAR_KERNEL_LDS #include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS #undef EMIT_VVAR pvclock_page = vvar_start + PAGE_SIZE; hvclock_page = vvar_start + 2 * PAGE_SIZE; + timens_page = vvar_start + 3 * PAGE_SIZE; + +#undef _ASM_X86_VVAR_H + /* Place all vvars in timens too at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) timens_ ## name = timens_page + offset; +#include <asm/vvar.h> +#undef EMIT_VVAR . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 3a4d8d4d39f8..3842873b3ae3 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -75,12 +75,14 @@ enum { sym_vvar_page, sym_pvclock_page, sym_hvclock_page, + sym_timens_page, }; const int special_pages[] = { sym_vvar_page, sym_pvclock_page, sym_hvclock_page, + sym_timens_page, }; struct vdso_sym { @@ -93,6 +95,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_page] = {"vvar_page", true}, [sym_pvclock_page] = {"pvclock_page", true}, [sym_hvclock_page] = {"hvclock_page", true}, + [sym_timens_page] = {"timens_page", true}, {"VDSO32_NOTE_MASK", true}, {"__kernel_vsyscall", true}, {"__kernel_sigreturn", true}, diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index f5937742b290..c1b8496b5606 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -14,16 +14,30 @@ #include <linux/elf.h> #include <linux/cpu.h> #include <linux/ptrace.h> +#include <linux/time_namespace.h> + #include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> #include <asm/vvar.h> +#include <asm/tlb.h> #include <asm/page.h> #include <asm/desc.h> #include <asm/cpufeature.h> #include <clocksource/hyperv_timer.h> +#undef _ASM_X86_VVAR_H +#define EMIT_VVAR(name, offset) \ + const size_t name ## _offset = offset; +#include <asm/vvar.h> + +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page + _vdso_data_offset); +} +#undef EMIT_VVAR + #if defined(CONFIG_X86_64) unsigned int __read_mostly vdso64_enabled = 1; #endif @@ -37,6 +51,7 @@ void __init init_vdso_image(const struct vdso_image *image) image->alt_len)); } +static const struct vm_special_mapping vvar_mapping; struct linux_binprm; static vm_fault_t vdso_fault(const struct vm_special_mapping *sm, @@ -84,10 +99,74 @@ static int vdso_mremap(const struct vm_special_mapping *sm, return 0; } +static int vvar_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + const struct vdso_image *image = new_vma->vm_mm->context.vdso_image; + unsigned long new_size = new_vma->vm_end - new_vma->vm_start; + + if (new_size != -image->sym_vvar_start) + return -EINVAL; + + return 0; +} + +#ifdef CONFIG_TIME_NS +static struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + if (likely(vma->vm_mm == current->mm)) + return current->nsproxy->time_ns->vvar_page; + + /* + * VM_PFNMAP | VM_IO protect .fault() handler from being called + * through interfaces like /proc/$pid/mem or + * process_vm_{readv,writev}() as long as there's no .access() + * in special_mapping_vmops(). + * For more details check_vma_flags() and __access_remote_vm() + */ + + WARN(1, "vvar_page accessed remotely"); + + return NULL; +} + +/* + * The vvar page layout depends on whether a task belongs to the root or + * non-root time namespace. Whenever a task changes its namespace, the VVAR + * page tables are cleared and then they will re-faulted with a + * corresponding layout. + * See also the comment near timens_setup_vdso_data() for details. + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + if (down_write_killable(&mm->mmap_sem)) + return -EINTR; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long size = vma->vm_end - vma->vm_start; + + if (vma_is_special_mapping(vma, &vvar_mapping)) + zap_page_range(vma, vma->vm_start, size); + } + + up_write(&mm->mmap_sem); + return 0; +} +#else +static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) +{ + return NULL; +} +#endif + static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) { const struct vdso_image *image = vma->vm_mm->context.vdso_image; + unsigned long pfn; long sym_offset; if (!image) @@ -107,8 +186,36 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, return VM_FAULT_SIGBUS; if (sym_offset == image->sym_vvar_page) { - return vmf_insert_pfn(vma, vmf->address, - __pa_symbol(&__vvar_page) >> PAGE_SHIFT); + struct page *timens_page = find_timens_vvar_page(vma); + + pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT; + + /* + * If a task belongs to a time namespace then a namespace + * specific VVAR is mapped with the sym_vvar_page offset and + * the real VVAR page is mapped with the sym_timens_page + * offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (timens_page) { + unsigned long addr; + vm_fault_t err; + + /* + * Optimization: inside time namespace pre-fault + * VVAR page too. As on timens page there are only + * offsets for clocks on VVAR, it'll be faulted + * shortly by VDSO code. + */ + addr = vmf->address + (image->sym_timens_page - sym_offset); + err = vmf_insert_pfn(vma, addr, pfn); + if (unlikely(err & VM_FAULT_ERROR)) + return err; + + pfn = page_to_pfn(timens_page); + } + + return vmf_insert_pfn(vma, vmf->address, pfn); } else if (sym_offset == image->sym_pvclock_page) { struct pvclock_vsyscall_time_info *pvti = pvclock_get_pvti_cpu0_va(); @@ -123,6 +230,14 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK)) return vmf_insert_pfn(vma, vmf->address, virt_to_phys(tsc_pg) >> PAGE_SHIFT); + } else if (sym_offset == image->sym_timens_page) { + struct page *timens_page = find_timens_vvar_page(vma); + + if (!timens_page) + return VM_FAULT_SIGBUS; + + pfn = __pa_symbol(&__vvar_page) >> PAGE_SHIFT; + return vmf_insert_pfn(vma, vmf->address, pfn); } return VM_FAULT_SIGBUS; @@ -136,6 +251,7 @@ static const struct vm_special_mapping vdso_mapping = { static const struct vm_special_mapping vvar_mapping = { .name = "[vvar]", .fault = vvar_fault, + .mremap = vvar_mremap, }; /* diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index a7752cd78b89..1f22b6bbda68 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -14,6 +14,10 @@ static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp); static unsigned long perf_nmi_window; +/* AMD Event 0xFFF: Merge. Used with Large Increment per Cycle events */ +#define AMD_MERGE_EVENT ((0xFULL << 32) | 0xFFULL) +#define AMD_MERGE_EVENT_ENABLE (AMD_MERGE_EVENT | ARCH_PERFMON_EVENTSEL_ENABLE) + static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -301,6 +305,25 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } +/* + * AMD64 events are detected based on their event codes. + */ +static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) +{ + return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); +} + +static inline bool amd_is_pair_event_code(struct hw_perf_event *hwc) +{ + if (!(x86_pmu.flags & PMU_FL_PAIR)) + return false; + + switch (amd_get_event_code(hwc)) { + case 0x003: return true; /* Retired SSE/AVX FLOPs */ + default: return false; + } +} + static int amd_core_hw_config(struct perf_event *event) { if (event->attr.exclude_host && event->attr.exclude_guest) @@ -316,15 +339,10 @@ static int amd_core_hw_config(struct perf_event *event) else if (event->attr.exclude_guest) event->hw.config |= AMD64_EVENTSEL_HOSTONLY; - return 0; -} + if ((x86_pmu.flags & PMU_FL_PAIR) && amd_is_pair_event_code(&event->hw)) + event->hw.flags |= PERF_X86_EVENT_PAIR; -/* - * AMD64 events are detected based on their event codes. - */ -static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) -{ - return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); + return 0; } static inline int amd_is_nb_event(struct hw_perf_event *hwc) @@ -855,6 +873,29 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, } } +static struct event_constraint pair_constraint; + +static struct event_constraint * +amd_get_event_constraints_f17h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (amd_is_pair_event_code(hwc)) + return &pair_constraint; + + return &unconstrained; +} + +static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (is_counter_pair(hwc)) + --cpuc->n_pair; +} + static ssize_t amd_event_sysfs_show(char *page, u64 config) { u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) | @@ -898,33 +939,15 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { + u64 even_ctr_mask = 0ULL; + int i; + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; - /* Avoid calulating the value each time in the NMI handler */ + /* Avoid calculating the value each time in the NMI handler */ perf_nmi_window = msecs_to_jiffies(100); - switch (boot_cpu_data.x86) { - case 0x15: - pr_cont("Fam15h "); - x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; - break; - case 0x17: - pr_cont("Fam17h "); - /* - * In family 17h, there are no event constraints in the PMC hardware. - * We fallback to using default amd_get_event_constraints. - */ - break; - case 0x18: - pr_cont("Fam18h "); - /* Using default amd_get_event_constraints. */ - break; - default: - pr_err("core perfctr but no constraints; unknown hardware!\n"); - return -ENODEV; - } - /* * If core performance counter extensions exists, we must use * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also @@ -939,6 +962,32 @@ static int __init amd_core_pmu_init(void) */ x86_pmu.amd_nb_constraints = 0; + if (boot_cpu_data.x86 == 0x15) { + pr_cont("Fam15h "); + x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; + } + if (boot_cpu_data.x86 >= 0x17) { + pr_cont("Fam17h+ "); + /* + * Family 17h and compatibles have constraints for Large + * Increment per Cycle events: they may only be assigned an + * even numbered counter that has a consecutive adjacent odd + * numbered counter following it. + */ + for (i = 0; i < x86_pmu.num_counters - 1; i += 2) + even_ctr_mask |= 1 << i; + + pair_constraint = (struct event_constraint) + __EVENT_CONSTRAINT(0, even_ctr_mask, 0, + x86_pmu.num_counters / 2, 0, + PERF_X86_EVENT_PAIR); + + x86_pmu.get_event_constraints = amd_get_event_constraints_f17h; + x86_pmu.put_event_constraints = amd_put_event_constraints_f17h; + x86_pmu.perf_ctr_pair_en = AMD_MERGE_EVENT_ENABLE; + x86_pmu.flags |= PMU_FL_PAIR; + } + pr_cont("core perfctr, "); return 0; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 9a89d98c55bd..3bb738f5a472 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -376,7 +376,7 @@ int x86_add_exclusive(unsigned int what) * LBR and BTS are still mutually exclusive. */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) - return 0; + goto out; if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); @@ -388,6 +388,7 @@ int x86_add_exclusive(unsigned int what) mutex_unlock(&pmc_reserve_mutex); } +out: atomic_inc(&active_events); return 0; @@ -398,11 +399,15 @@ fail_unlock: void x86_del_exclusive(unsigned int what) { + atomic_dec(&active_events); + + /* + * See the comment in x86_add_exclusive(). + */ if (x86_pmu.lbr_pt_coexist && what == x86_lbr_exclusive_pt) return; atomic_dec(&x86_pmu.lbr_exclusive[what]); - atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -613,6 +618,7 @@ void x86_pmu_disable_all(void) int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { + struct hw_perf_event *hwc = &cpuc->events[idx]->hw; u64 val; if (!test_bit(idx, cpuc->active_mask)) @@ -622,6 +628,8 @@ void x86_pmu_disable_all(void) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; wrmsrl(x86_pmu_config_addr(idx), val); + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(idx + 1), 0); } } @@ -694,7 +702,7 @@ struct sched_state { int counter; /* counter index */ int unassigned; /* number of events to be assigned left */ int nr_gp; /* number of GP counters used */ - unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + u64 used; }; /* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */ @@ -751,8 +759,12 @@ static bool perf_sched_restore_state(struct perf_sched *sched) sched->saved_states--; sched->state = sched->saved[sched->saved_states]; - /* continue with next counter: */ - clear_bit(sched->state.counter++, sched->state.used); + /* this assignment didn't work out */ + /* XXX broken vs EVENT_PAIR */ + sched->state.used &= ~BIT_ULL(sched->state.counter); + + /* try the next one */ + sched->state.counter++; return true; } @@ -777,20 +789,32 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) { - if (!__test_and_set_bit(idx, sched->state.used)) - goto done; + u64 mask = BIT_ULL(idx); + + if (sched->state.used & mask) + continue; + + sched->state.used |= mask; + goto done; } } /* Grab the first unused counter starting with idx */ idx = sched->state.counter; for_each_set_bit_from(idx, c->idxmsk, INTEL_PMC_IDX_FIXED) { - if (!__test_and_set_bit(idx, sched->state.used)) { - if (sched->state.nr_gp++ >= sched->max_gp) - return false; + u64 mask = BIT_ULL(idx); - goto done; - } + if (c->flags & PERF_X86_EVENT_PAIR) + mask |= mask << 1; + + if (sched->state.used & mask) + continue; + + if (sched->state.nr_gp++ >= sched->max_gp) + return false; + + sched->state.used |= mask; + goto done; } return false; @@ -867,12 +891,10 @@ EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { struct event_constraint *c; - unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; int n0, i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; - - bitmap_zero(used_mask, X86_PMC_IDX_MAX); + u64 used_mask = 0; /* * Compute the number of events already present; see x86_pmu_add(), @@ -915,6 +937,8 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) * fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { + u64 mask; + hwc = &cpuc->event_list[i]->hw; c = cpuc->event_constraint[i]; @@ -926,11 +950,16 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (!test_bit(hwc->idx, c->idxmsk)) break; + mask = BIT_ULL(hwc->idx); + if (is_counter_pair(hwc)) + mask |= mask << 1; + /* not already used */ - if (test_bit(hwc->idx, used_mask)) + if (used_mask & mask) break; - __set_bit(hwc->idx, used_mask); + used_mask |= mask; + if (assign) assign[i] = hwc->idx; } @@ -953,6 +982,15 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) READ_ONCE(cpuc->excl_cntrs->exclusive_present)) gpmax /= 2; + /* + * Reduce the amount of available counters to allow fitting + * the extra Merge events needed by large increment events. + */ + if (x86_pmu.flags & PMU_FL_PAIR) { + gpmax = x86_pmu.num_counters - cpuc->n_pair; + WARN_ON(gpmax <= 0); + } + unsched = perf_assign_events(cpuc->event_constraint, n, wmin, wmax, gpmax, assign); } @@ -1033,6 +1071,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, return -EINVAL; cpuc->event_list[n] = leader; n++; + if (is_counter_pair(&leader->hw)) + cpuc->n_pair++; } if (!dogrp) return n; @@ -1047,6 +1087,8 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, cpuc->event_list[n] = event; n++; + if (is_counter_pair(&event->hw)) + cpuc->n_pair++; } return n; } @@ -1233,6 +1275,13 @@ int x86_perf_event_set_period(struct perf_event *event) wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* + * Clear the Merge event counter's upper 16 bits since + * we currently declare a 48-bit counter width + */ + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_event_addr(idx + 1), 0); + + /* * Due to erratum on certan cpu we need * a second write to be sure the register * is updated properly @@ -1642,9 +1691,12 @@ static struct attribute_group x86_pmu_format_group __ro_after_init = { ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { - struct perf_pmu_events_attr *pmu_attr = \ + struct perf_pmu_events_attr *pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - u64 config = x86_pmu.event_map(pmu_attr->id); + u64 config = 0; + + if (pmu_attr->id < x86_pmu.max_events) + config = x86_pmu.event_map(pmu_attr->id); /* string trumps id */ if (pmu_attr->event_str) @@ -1713,6 +1765,9 @@ is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct perf_pmu_events_attr *pmu_attr; + if (idx >= x86_pmu.max_events) + return 0; + pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); /* str trumps id */ return pmu_attr->event_str || x86_pmu.event_map(idx) ? attr->mode : 0; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 38de4a7f6752..6a3b599ee0fe 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -63,9 +63,17 @@ struct bts_buffer { static struct pmu bts_pmu; +static int buf_nr_pages(struct page *page) +{ + if (!PagePrivate(page)) + return 1; + + return 1 << page_private(page); +} + static size_t buf_size(struct page *page) { - return 1 << (PAGE_SHIFT + page_private(page)); + return buf_nr_pages(page) * PAGE_SIZE; } static void * @@ -83,9 +91,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, /* count all the high order buffers */ for (pg = 0, nbuf = 0; pg < nr_pages;) { page = virt_to_page(pages[pg]); - if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) - return NULL; - pg += 1 << page_private(page); + pg += buf_nr_pages(page); nbuf++; } @@ -109,7 +115,7 @@ bts_buffer_setup_aux(struct perf_event *event, void **pages, unsigned int __nr_pages; page = virt_to_page(pages[pg]); - __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + __nr_pages = buf_nr_pages(page); buf->buf[nbuf].page = page; buf->buf[nbuf].offset = offset; buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index ce83950036c5..4b94ae4ae369 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -7,6 +7,7 @@ #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/insn.h> +#include <asm/io.h> #include "../perf_event.h" diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 5053a403e4ae..09913121e726 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -741,6 +741,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, model_hsw), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L, model_skl), X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L, model_skl), + X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE, model_skl), {}, }; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index dbaa1b088a30..c37cb12d0ef6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -15,6 +15,7 @@ #define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC 0x1910 #define PCI_DEVICE_ID_INTEL_SKL_SD_IMC 0x190f #define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC 0x191f +#define PCI_DEVICE_ID_INTEL_SKL_E3_IMC 0x1918 #define PCI_DEVICE_ID_INTEL_KBL_Y_IMC 0x590c #define PCI_DEVICE_ID_INTEL_KBL_U_IMC 0x5904 #define PCI_DEVICE_ID_INTEL_KBL_UQ_IMC 0x5914 @@ -658,6 +659,10 @@ static const struct pci_device_id skl_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_E3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBL_Y_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, @@ -826,6 +831,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core H Quad Core */ IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Dual Core */ IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver), /* 6th Gen Core S Quad Core */ + IMC_DEV(SKL_E3_IMC, &skl_uncore_pci_driver), /* Xeon E3 V5 Gen Core processor */ IMC_DEV(KBL_Y_IMC, &skl_uncore_pci_driver), /* 7th Gen Core Y */ IMC_DEV(KBL_U_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U */ IMC_DEV(KBL_UQ_IMC, &skl_uncore_pci_driver), /* 7th Gen Core U Quad Core */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index b10a5ec79e48..ad20220af303 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -369,11 +369,6 @@ #define SNR_M2M_PCI_PMON_BOX_CTL 0x438 #define SNR_M2M_PCI_PMON_UMASK_EXT 0xff -/* SNR PCIE3 */ -#define SNR_PCIE3_PCI_PMON_CTL0 0x508 -#define SNR_PCIE3_PCI_PMON_CTR0 0x4e8 -#define SNR_PCIE3_PCI_PMON_BOX_CTL 0x4e4 - /* SNR IMC */ #define SNR_IMC_MMIO_PMON_FIXED_CTL 0x54 #define SNR_IMC_MMIO_PMON_FIXED_CTR 0x38 @@ -4328,27 +4323,12 @@ static struct intel_uncore_type snr_uncore_m2m = { .format_group = &snr_m2m_uncore_format_group, }; -static struct intel_uncore_type snr_uncore_pcie3 = { - .name = "pcie3", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNR_PCIE3_PCI_PMON_CTR0, - .event_ctl = SNR_PCIE3_PCI_PMON_CTL0, - .event_mask = SNBEP_PMON_RAW_EVENT_MASK, - .box_ctl = SNR_PCIE3_PCI_PMON_BOX_CTL, - .ops = &ivbep_uncore_pci_ops, - .format_group = &ivbep_uncore_format_group, -}; - enum { SNR_PCI_UNCORE_M2M, - SNR_PCI_UNCORE_PCIE3, }; static struct intel_uncore_type *snr_pci_uncores[] = { [SNR_PCI_UNCORE_M2M] = &snr_uncore_m2m, - [SNR_PCI_UNCORE_PCIE3] = &snr_uncore_pcie3, NULL, }; @@ -4357,10 +4337,6 @@ static const struct pci_device_id snr_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x344a), .driver_data = UNCORE_PCI_DEV_FULL_DATA(12, 0, SNR_PCI_UNCORE_M2M, 0), }, - { /* PCIe3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x334a), - .driver_data = UNCORE_PCI_DEV_FULL_DATA(4, 0, SNR_PCI_UNCORE_PCIE3, 0), - }, { /* end: all zeroes */ } }; @@ -4536,6 +4512,7 @@ static struct uncore_event_desc snr_uncore_imc_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(write, "event=0xff,umask=0x21"), INTEL_UNCORE_EVENT_DESC(write.scale, "3.814697266e-6"), INTEL_UNCORE_EVENT_DESC(write.unit, "MiB"), + { /* end: all zeroes */ }, }; static struct intel_uncore_ops snr_uncore_imc_freerunning_ops = { diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 930611db8f9a..f1cd1ca1a77b 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -77,6 +77,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ #define PERF_X86_EVENT_PEBS_VIA_PT 0x0800 /* use PT buffer for PEBS */ +#define PERF_X86_EVENT_PAIR 0x1000 /* Large Increment per Cycle */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -272,6 +273,7 @@ struct cpu_hw_events { struct amd_nb *amd_nb; /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ u64 perf_ctr_virt_mask; + int n_pair; /* Large increment events */ void *kfree_on_online[X86_PERF_KFREE_MAX]; }; @@ -694,6 +696,7 @@ struct x86_pmu { * AMD bits */ unsigned int amd_nb_constraints : 1; + u64 perf_ctr_pair_en; /* * Extra registers for events @@ -743,6 +746,7 @@ do { \ #define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define PMU_FL_PEBS_ALL 0x10 /* all events are valid PEBS events */ #define PMU_FL_TFA 0x20 /* deal with TSX force abort */ +#define PMU_FL_PAIR 0x40 /* merge counters for large incr. events */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -838,6 +842,11 @@ int x86_pmu_hw_config(struct perf_event *event); void x86_pmu_disable_all(void); +static inline bool is_counter_pair(struct hw_perf_event *hwc) +{ + return hwc->flags & PERF_X86_EVENT_PAIR; +} + static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { @@ -845,6 +854,14 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, if (hwc->extra_reg.reg) wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); + + /* + * Add enabled Merge event on next counter + * if large increment event being enabled on this counter + */ + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en); + wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask); } @@ -861,6 +878,9 @@ static inline void x86_pmu_disable_event(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; wrmsrl(hwc->config_base, hwc->config); + + if (is_counter_pair(hwc)) + wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0); } void x86_pmu_enable_event(struct perf_event *event); diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 30416d7f19d4..a3aefe9b9401 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -114,8 +114,6 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, err |= fpu__restore_sig(buf, 1); - force_iret(); - return err; } diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index bc9693c9107e..ca0976456a6b 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -13,7 +13,6 @@ #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mpspec.h> -#include <asm/realmode.h> #include <asm/x86_init.h> #ifdef CONFIG_ACPI_APEI @@ -62,7 +61,7 @@ static inline void acpi_disable_pci(void) extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ -#define acpi_wakeup_address ((unsigned long)(real_mode_header->wakeup_start)) +unsigned long acpi_get_wakeup_address(void); /* * Check if the CPU can handle C2 and deeper diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 804734058c77..02c0078d3787 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -6,6 +6,7 @@ #include <linux/percpu-defs.h> #include <asm/processor.h> #include <asm/intel_ds.h> +#include <asm/pgtable_areas.h> #ifdef CONFIG_X86_64 @@ -134,15 +135,6 @@ DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); extern void setup_cpu_entry_areas(void); extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); -/* Single page reserved for the readonly IDT mapping: */ -#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE -#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) - -#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) - -#define CPU_ENTRY_AREA_MAP_SIZE \ - (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE) - extern struct cpu_entry_area *get_cpu_entry_area(int cpu); static inline struct entry_stack *cpu_entry_stack(int cpu) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index e9b62498fe75..98c60fa31ced 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -357,6 +357,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index d028e9acdf1c..86169a24b0d8 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -8,6 +8,7 @@ #include <asm/tlb.h> #include <asm/nospec-branch.h> #include <asm/mmu_context.h> +#include <linux/build_bug.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -19,13 +20,16 @@ * This is the main reason why we're doing stable VA mappings for RT * services. * - * This flag is used in conjunction with a chicken bit called - * "efi=old_map" which can be used as a fallback to the old runtime - * services mapping method in case there's some b0rkage with a - * particular EFI implementation (haha, it is hard to hold up the - * sarcasm here...). + * SGI UV1 machines are known to be incompatible with this scheme, so we + * provide an opt-out for these machines via a DMI quirk that sets the + * attribute below. */ -#define EFI_OLD_MEMMAP EFI_ARCH_1 +#define EFI_UV1_MEMMAP EFI_ARCH_1 + +static inline bool efi_have_uv1_memmap(void) +{ + return IS_ENABLED(CONFIG_X86_UV) && efi_enabled(EFI_UV1_MEMMAP); +} #define EFI32_LOADER_SIGNATURE "EL32" #define EFI64_LOADER_SIGNATURE "EL64" @@ -34,10 +38,46 @@ #define ARCH_EFI_IRQ_FLAGS_MASK X86_EFLAGS_IF -#ifdef CONFIG_X86_32 +/* + * The EFI services are called through variadic functions in many cases. These + * functions are implemented in assembler and support only a fixed number of + * arguments. The macros below allows us to check at build time that we don't + * try to call them with too many arguments. + * + * __efi_nargs() will return the number of arguments if it is 7 or less, and + * cause a BUILD_BUG otherwise. The limitations of the C preprocessor make it + * impossible to calculate the exact number of arguments beyond some + * pre-defined limit. The maximum number of arguments currently supported by + * any of the thunks is 7, so this is good enough for now and can be extended + * in the obvious way if we ever need more. + */ -extern asmlinkage unsigned long efi_call_phys(void *, ...); +#define __efi_nargs(...) __efi_nargs_(__VA_ARGS__) +#define __efi_nargs_(...) __efi_nargs__(0, ##__VA_ARGS__, \ + __efi_arg_sentinel(7), __efi_arg_sentinel(6), \ + __efi_arg_sentinel(5), __efi_arg_sentinel(4), \ + __efi_arg_sentinel(3), __efi_arg_sentinel(2), \ + __efi_arg_sentinel(1), __efi_arg_sentinel(0)) +#define __efi_nargs__(_0, _1, _2, _3, _4, _5, _6, _7, n, ...) \ + __take_second_arg(n, \ + ({ BUILD_BUG_ON_MSG(1, "__efi_nargs limit exceeded"); 8; })) +#define __efi_arg_sentinel(n) , n +/* + * __efi_nargs_check(f, n, ...) will cause a BUILD_BUG if the ellipsis + * represents more than n arguments. + */ + +#define __efi_nargs_check(f, n, ...) \ + __efi_nargs_check_(f, __efi_nargs(__VA_ARGS__), n) +#define __efi_nargs_check_(f, p, n) __efi_nargs_check__(f, p, n) +#define __efi_nargs_check__(f, p, n) ({ \ + BUILD_BUG_ON_MSG( \ + (p) > (n), \ + #f " called with too many arguments (" #p ">" #n ")"); \ +}) + +#ifdef CONFIG_X86_32 #define arch_efi_call_virt_setup() \ ({ \ kernel_fpu_begin(); \ @@ -51,13 +91,7 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); }) -/* - * Wrap all the virtual calls in a way that forces the parameters on the stack. - */ -#define arch_efi_call_virt(p, f, args...) \ -({ \ - ((efi_##f##_t __attribute__((regparm(0)))*) p->f)(args); \ -}) +#define arch_efi_call_virt(p, f, args...) p->f(args) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) @@ -65,9 +99,12 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); #define EFI_LOADER_SIGNATURE "EL64" -extern asmlinkage u64 efi_call(void *fp, ...); +extern asmlinkage u64 __efi_call(void *fp, ...); -#define efi_call_phys(f, args...) efi_call((f), args) +#define efi_call(...) ({ \ + __efi_nargs_check(efi_call, 7, __VA_ARGS__); \ + __efi_call(__VA_ARGS__); \ +}) /* * struct efi_scratch - Scratch space used while switching to/from efi_mm @@ -85,7 +122,7 @@ struct efi_scratch { kernel_fpu_begin(); \ firmware_restrict_branch_speculation_start(); \ \ - if (!efi_enabled(EFI_OLD_MEMMAP)) \ + if (!efi_have_uv1_memmap()) \ efi_switch_mm(&efi_mm); \ }) @@ -94,7 +131,7 @@ struct efi_scratch { #define arch_efi_call_virt_teardown() \ ({ \ - if (!efi_enabled(EFI_OLD_MEMMAP)) \ + if (!efi_have_uv1_memmap()) \ efi_switch_mm(efi_scratch.prev_mm); \ \ firmware_restrict_branch_speculation_end(); \ @@ -121,8 +158,6 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, extern struct efi_scratch efi_scratch; extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); -extern pgd_t * __init efi_call_phys_prolog(void); -extern void __init efi_call_phys_epilog(pgd_t *save_pgd); extern void __init efi_print_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); @@ -140,6 +175,8 @@ extern void efi_delete_dummy_variable(void); extern void efi_switch_mm(struct mm_struct *mm); extern void efi_recover_from_page_fault(unsigned long phys_addr); extern void efi_free_boot_services(void); +extern pgd_t * __init efi_uv1_memmap_phys_prolog(void); +extern void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd); struct efi_setup_data { u64 fw_vendor; @@ -152,93 +189,144 @@ struct efi_setup_data { extern u64 efi_setup; #ifdef CONFIG_EFI +extern efi_status_t __efi64_thunk(u32, ...); -static inline bool efi_is_native(void) +#define efi64_thunk(...) ({ \ + __efi_nargs_check(efi64_thunk, 6, __VA_ARGS__); \ + __efi64_thunk(__VA_ARGS__); \ +}) + +static inline bool efi_is_mixed(void) { - return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT); + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return false; + return IS_ENABLED(CONFIG_X86_64) && !efi_enabled(EFI_64BIT); } static inline bool efi_runtime_supported(void) { - if (efi_is_native()) - return true; - - if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP)) + if (IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT)) return true; - return false; + return IS_ENABLED(CONFIG_EFI_MIXED); } extern void parse_efi_setup(u64 phys_addr, u32 data_len); extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); -#ifdef CONFIG_EFI_MIXED extern void efi_thunk_runtime_setup(void); -extern efi_status_t efi_thunk_set_virtual_address_map( - void *phys_set_virtual_address_map, - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map); -#else -static inline void efi_thunk_runtime_setup(void) {} -static inline efi_status_t efi_thunk_set_virtual_address_map( - void *phys_set_virtual_address_map, - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map) -{ - return EFI_SUCCESS; -} -#endif /* CONFIG_EFI_MIXED */ - +efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map); /* arch specific definitions used by the stub code */ -struct efi_config { - u64 image_handle; - u64 table; - u64 runtime_services; - u64 boot_services; - u64 text_output; - efi_status_t (*call)(unsigned long, ...); - bool is64; -} __packed; - -__pure const struct efi_config *__efi_early(void); +__attribute_const__ bool efi_is_64bit(void); -static inline bool efi_is_64bit(void) +static inline bool efi_is_native(void) { if (!IS_ENABLED(CONFIG_X86_64)) - return false; - + return true; if (!IS_ENABLED(CONFIG_EFI_MIXED)) return true; + return efi_is_64bit(); +} + +#define efi_mixed_mode_cast(attr) \ + __builtin_choose_expr( \ + __builtin_types_compatible_p(u32, __typeof__(attr)), \ + (unsigned long)(attr), (attr)) - return __efi_early()->is64; +#define efi_table_attr(inst, attr) \ + (efi_is_native() \ + ? inst->attr \ + : (__typeof__(inst->attr)) \ + efi_mixed_mode_cast(inst->mixed_mode.attr)) + +/* + * The following macros allow translating arguments if necessary from native to + * mixed mode. The use case for this is to initialize the upper 32 bits of + * output parameters, and where the 32-bit method requires a 64-bit argument, + * which must be split up into two arguments to be thunked properly. + * + * As examples, the AllocatePool boot service returns the address of the + * allocation, but it will not set the high 32 bits of the address. To ensure + * that the full 64-bit address is initialized, we zero-init the address before + * calling the thunk. + * + * The FreePages boot service takes a 64-bit physical address even in 32-bit + * mode. For the thunk to work correctly, a native 64-bit call of + * free_pages(addr, size) + * must be translated to + * efi64_thunk(free_pages, addr & U32_MAX, addr >> 32, size) + * so that the two 32-bit halves of addr get pushed onto the stack separately. + */ + +static inline void *efi64_zero_upper(void *p) +{ + ((u32 *)p)[1] = 0; + return p; } -#define efi_table_attr(table, attr, instance) \ - (efi_is_64bit() ? \ - ((table##_64_t *)(unsigned long)instance)->attr : \ - ((table##_32_t *)(unsigned long)instance)->attr) +#define __efi64_argmap_free_pages(addr, size) \ + ((addr), 0, (size)) + +#define __efi64_argmap_get_memory_map(mm_size, mm, key, size, ver) \ + ((mm_size), (mm), efi64_zero_upper(key), efi64_zero_upper(size), (ver)) + +#define __efi64_argmap_allocate_pool(type, size, buffer) \ + ((type), (size), efi64_zero_upper(buffer)) -#define efi_call_proto(protocol, f, instance, ...) \ - __efi_early()->call(efi_table_attr(protocol, f, instance), \ - instance, ##__VA_ARGS__) +#define __efi64_argmap_handle_protocol(handle, protocol, interface) \ + ((handle), (protocol), efi64_zero_upper(interface)) -#define efi_call_early(f, ...) \ - __efi_early()->call(efi_table_attr(efi_boot_services, f, \ - __efi_early()->boot_services), __VA_ARGS__) +#define __efi64_argmap_locate_protocol(protocol, reg, interface) \ + ((protocol), (reg), efi64_zero_upper(interface)) -#define __efi_call_early(f, ...) \ - __efi_early()->call((unsigned long)f, __VA_ARGS__); +/* PCI I/O */ +#define __efi64_argmap_get_location(protocol, seg, bus, dev, func) \ + ((protocol), efi64_zero_upper(seg), efi64_zero_upper(bus), \ + efi64_zero_upper(dev), efi64_zero_upper(func)) + +/* + * The macros below handle the plumbing for the argument mapping. To add a + * mapping for a specific EFI method, simply define a macro + * __efi64_argmap_<method name>, following the examples above. + */ -#define efi_call_runtime(f, ...) \ - __efi_early()->call(efi_table_attr(efi_runtime_services, f, \ - __efi_early()->runtime_services), __VA_ARGS__) +#define __efi64_thunk_map(inst, func, ...) \ + efi64_thunk(inst->mixed_mode.func, \ + __efi64_argmap(__efi64_argmap_ ## func(__VA_ARGS__), \ + (__VA_ARGS__))) + +#define __efi64_argmap(mapped, args) \ + __PASTE(__efi64_argmap__, __efi_nargs(__efi_eat mapped))(mapped, args) +#define __efi64_argmap__0(mapped, args) __efi_eval mapped +#define __efi64_argmap__1(mapped, args) __efi_eval args + +#define __efi_eat(...) +#define __efi_eval(...) __VA_ARGS__ + +/* The three macros below handle dispatching via the thunk if needed */ + +#define efi_call_proto(inst, func, ...) \ + (efi_is_native() \ + ? inst->func(inst, ##__VA_ARGS__) \ + : __efi64_thunk_map(inst, func, inst, ##__VA_ARGS__)) + +#define efi_bs_call(func, ...) \ + (efi_is_native() \ + ? efi_system_table()->boottime->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_table_attr(efi_system_table(), \ + boottime), func, __VA_ARGS__)) + +#define efi_rt_call(func, ...) \ + (efi_is_native() \ + ? efi_system_table()->runtime->func(__VA_ARGS__) \ + : __efi64_thunk_map(efi_table_attr(efi_system_table(), \ + runtime), func, __VA_ARGS__)) extern bool efi_reboot_required(void); extern bool efi_is_table_address(unsigned long phys_addr); diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index c2a7458f912c..85be2f506272 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -47,8 +47,6 @@ struct dyn_arch_ftrace { /* No extra data needed for x86 */ }; -int ftrace_int3_handler(struct pt_regs *regs); - #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif /* CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index c606c0b70738..4981c293f926 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -111,6 +111,7 @@ #define INTEL_FAM6_ATOM_TREMONT_D 0x86 /* Jacobsville */ #define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ +#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h index 9e7adcdbe031..e6da1ce26256 100644 --- a/arch/x86/include/asm/intel_pmc_ipc.h +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -31,30 +31,13 @@ #if IS_ENABLED(CONFIG_INTEL_PMC_IPC) -int intel_pmc_ipc_simple_command(int cmd, int sub); -int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, - u32 *out, u32 outlen, u32 dptr, u32 sptr); int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen); int intel_pmc_s0ix_counter_read(u64 *data); -int intel_pmc_gcr_read(u32 offset, u32 *data); int intel_pmc_gcr_read64(u32 offset, u64 *data); -int intel_pmc_gcr_write(u32 offset, u32 data); -int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val); #else -static inline int intel_pmc_ipc_simple_command(int cmd, int sub) -{ - return -EINVAL; -} - -static inline int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, - u32 *out, u32 outlen, u32 dptr, u32 sptr) -{ - return -EINVAL; -} - static inline int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen) { @@ -66,26 +49,11 @@ static inline int intel_pmc_s0ix_counter_read(u64 *data) return -EINVAL; } -static inline int intel_pmc_gcr_read(u32 offset, u32 *data) -{ - return -EINVAL; -} - static inline int intel_pmc_gcr_read64(u32 offset, u64 *data) { return -EINVAL; } -static inline int intel_pmc_gcr_write(u32 offset, u32 data) -{ - return -EINVAL; -} - -static inline int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val) -{ - return -EINVAL; -} - #endif /*CONFIG_INTEL_PMC_IPC*/ #endif diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 4a8c6e817398..2a1442ba6e78 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -22,24 +22,12 @@ /* Read single register */ int intel_scu_ipc_ioread8(u16 addr, u8 *data); -/* Read two sequential registers */ -int intel_scu_ipc_ioread16(u16 addr, u16 *data); - -/* Read four sequential registers */ -int intel_scu_ipc_ioread32(u16 addr, u32 *data); - /* Read a vector */ int intel_scu_ipc_readv(u16 *addr, u8 *data, int len); /* Write single register */ int intel_scu_ipc_iowrite8(u16 addr, u8 data); -/* Write two sequential registers */ -int intel_scu_ipc_iowrite16(u16 addr, u16 data); - -/* Write four sequential registers */ -int intel_scu_ipc_iowrite32(u16 addr, u32 data); - /* Write a vector */ int intel_scu_ipc_writev(u16 *addr, u8 *data, int len); @@ -50,14 +38,6 @@ int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask); int intel_scu_ipc_simple_command(int cmd, int sub); int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, u32 *out, int outlen); -int intel_scu_ipc_raw_command(int cmd, int sub, u8 *in, int inlen, - u32 *out, int outlen, u32 dptr, u32 sptr); - -/* I2C control api */ -int intel_scu_ipc_i2c_cntrl(u32 addr, u32 *data); - -/* Update FW version */ -int intel_scu_ipc_fw_update(u8 *buffer, u32 length); extern struct blocking_notifier_head intel_scu_notifier; diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h index 214394860632..2f77e31a1283 100644 --- a/arch/x86/include/asm/intel_telemetry.h +++ b/arch/x86/include/asm/intel_telemetry.h @@ -40,13 +40,10 @@ struct telemetry_evtmap { struct telemetry_unit_config { struct telemetry_evtmap *telem_evts; void __iomem *regmap; - u32 ssram_base_addr; u8 ssram_evts_used; u8 curr_period; u8 max_period; u8 min_period; - u32 ssram_size; - }; struct telemetry_plt_config { diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 9997521fc5cd..e1aa17a468a8 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -399,4 +399,40 @@ extern bool arch_memremap_can_ram_remap(resource_size_t offset, extern bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size); +/** + * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units + * @__dst: destination, in MMIO space (must be 512-bit aligned) + * @src: source + * @count: number of 512 bits quantities to submit + * + * Submit data from kernel space to MMIO space, in units of 512 bits at a + * time. Order of access is not guaranteed, nor is a memory barrier + * performed afterwards. + * + * Warning: Do not use this helper unless your driver has checked that the CPU + * instruction is supported on the platform. + */ +static inline void iosubmit_cmds512(void __iomem *__dst, const void *src, + size_t count) +{ + /* + * Note that this isn't an "on-stack copy", just definition of "dst" + * as a pointer to 64-bytes of stuff that is going to be overwritten. + * In the MOVDIR64B case that may be needed as you can use the + * MOVDIR64B instruction to copy arbitrary memory around. This trick + * lets the compiler know how much gets clobbered. + */ + volatile struct { char _[64]; } *dst = __dst; + const u8 *from = src; + const u8 *end = from + count * 64; + + while (from < end) { + /* MOVDIR64B [rdx], rax */ + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" + : "=m" (dst) + : "d" (from), "a" (dst)); + from += 64; + } +} + #endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 5dc909d9ad81..95b1f053bd96 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -11,12 +11,11 @@ #include <asm-generic/kprobes.h> -#define BREAKPOINT_INSTRUCTION 0xcc - #ifdef CONFIG_KPROBES #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> +#include <asm/text-patching.h> #include <asm/insn.h> #define __ARCH_WANT_KPROBES_INSN_SLOT @@ -25,10 +24,7 @@ struct pt_regs; struct kprobe; typedef u8 kprobe_opcode_t; -#define RELATIVEJUMP_OPCODE 0xe9 -#define RELATIVEJUMP_SIZE 5 -#define RELATIVECALL_OPCODE 0xe8 -#define RELATIVE_ADDR_SIZE 4 + #define MAX_STACK_SIZE 64 #define CUR_STACK_SIZE(ADDR) \ (current_top_of_stack() - (unsigned long)(ADDR)) @@ -43,11 +39,11 @@ extern __visible kprobe_opcode_t optprobe_template_entry[]; extern __visible kprobe_opcode_t optprobe_template_val[]; extern __visible kprobe_opcode_t optprobe_template_call[]; extern __visible kprobe_opcode_t optprobe_template_end[]; -#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) +#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)optprobe_template_end - \ (unsigned long)optprobe_template_entry) + \ - MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE) + MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE) extern const int kretprobe_blacklist_size; @@ -73,7 +69,7 @@ struct arch_specific_insn { struct arch_optimized_insn { /* copy of the original instructions */ - kprobe_opcode_t copied_insn[RELATIVE_ADDR_SIZE]; + kprobe_opcode_t copied_insn[DISP32_SIZE]; /* detour code buffer */ kprobe_opcode_t *insn; /* the size of instructions copied to detour code buffer */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index dc2d4b206ab7..4359b955e0b7 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -144,7 +144,7 @@ struct mce_log_buffer { enum mce_notifier_prios { MCE_PRIO_FIRST = INT_MAX, - MCE_PRIO_SRAO = INT_MAX - 1, + MCE_PRIO_UC = INT_MAX - 1, MCE_PRIO_EXTLOG = INT_MAX - 2, MCE_PRIO_NFIT = INT_MAX - 3, MCE_PRIO_EDAC = INT_MAX - 4, @@ -290,6 +290,7 @@ extern void apei_mce_report_mem_error(int corrected, /* These may be used by multiple smca_hwid_mcatypes */ enum smca_bank_types { SMCA_LS = 0, /* Load Store */ + SMCA_LS_V2, /* Load Store */ SMCA_IF, /* Instruction Fetch */ SMCA_L2_CACHE, /* L2 Cache */ SMCA_DE, /* Decoder Unit */ diff --git a/arch/x86/include/asm/memtype.h b/arch/x86/include/asm/memtype.h new file mode 100644 index 000000000000..9c2447b3555d --- /dev/null +++ b/arch/x86/include/asm/memtype.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MEMTYPE_H +#define _ASM_X86_MEMTYPE_H + +#include <linux/types.h> +#include <asm/pgtable_types.h> + +extern bool pat_enabled(void); +extern void pat_disable(const char *reason); +extern void pat_init(void); +extern void init_cache_modes(void); + +extern int memtype_reserve(u64 start, u64 end, + enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); +extern int memtype_free(u64 start, u64 end); + +extern int memtype_kernel_map_sync(u64 base, unsigned long size, + enum page_cache_mode pcm); + +extern int memtype_reserve_io(resource_size_t start, resource_size_t end, + enum page_cache_mode *pcm); + +extern void memtype_free_io(resource_size_t start, resource_size_t end); + +extern bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); + +#endif /* _ASM_X86_MEMTYPE_H */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 209492849566..6685e1218959 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -53,6 +53,6 @@ static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(unsigned int family) {} static inline int __init save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } -void reload_ucode_amd(void) {} +static inline void reload_ucode_amd(void) {} #endif #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 5f33924e200f..b243234e90cb 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -69,14 +69,6 @@ struct ldt_struct { int slot; }; -/* This is a multiple of PAGE_SIZE. */ -#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) - -static inline void *ldt_slot_va(int slot) -{ - return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); -} - /* * Used for LDT copy/destruction. */ @@ -99,87 +91,21 @@ static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif -static inline void load_mm_ldt(struct mm_struct *mm) -{ #ifdef CONFIG_MODIFY_LDT_SYSCALL - struct ldt_struct *ldt; - - /* READ_ONCE synchronizes with smp_store_release */ - ldt = READ_ONCE(mm->context.ldt); - - /* - * Any change to mm->context.ldt is followed by an IPI to all - * CPUs with the mm active. The LDT will not be freed until - * after the IPI is handled by all such CPUs. This means that, - * if the ldt_struct changes before we return, the values we see - * will be safe, and the new values will be loaded before we run - * any user code. - * - * NB: don't try to convert this to use RCU without extreme care. - * We would still need IRQs off, because we don't want to change - * the local LDT after an IPI loaded a newer value than the one - * that we can see. - */ - - if (unlikely(ldt)) { - if (static_cpu_has(X86_FEATURE_PTI)) { - if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { - /* - * Whoops -- either the new LDT isn't mapped - * (if slot == -1) or is mapped into a bogus - * slot (if slot > 1). - */ - clear_LDT(); - return; - } - - /* - * If page table isolation is enabled, ldt->entries - * will not be mapped in the userspace pagetables. - * Tell the CPU to access the LDT through the alias - * at ldt_slot_va(ldt->slot). - */ - set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); - } else { - set_ldt(ldt->entries, ldt->nr_entries); - } - } else { - clear_LDT(); - } +extern void load_mm_ldt(struct mm_struct *mm); +extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else +static inline void load_mm_ldt(struct mm_struct *mm) +{ clear_LDT(); -#endif } - static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { -#ifdef CONFIG_MODIFY_LDT_SYSCALL - /* - * Load the LDT if either the old or new mm had an LDT. - * - * An mm will never go from having an LDT to not having an LDT. Two - * mms never share an LDT, so we don't gain anything by checking to - * see whether the LDT changed. There's also no guarantee that - * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, - * then prev->context.ldt will also be non-NULL. - * - * If we really cared, we could optimize the case where prev == next - * and we're exiting lazy mode. Most of the time, if this happens, - * we don't actually need to reload LDTR, but modify_ldt() is mostly - * used by legacy code and emulators where we don't need this level of - * performance. - * - * This uses | instead of || because it generates better code. - */ - if (unlikely((unsigned long)prev->context.ldt | - (unsigned long)next->context.ldt)) - load_mm_ldt(next); -#endif - DEBUG_LOCKS_WARN_ON(preemptible()); } +#endif -void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); /* * Init a new mm. Used on mm copies, like at fork() diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index dbff1456d215..829df26fd7a3 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -24,7 +24,7 @@ #define _ASM_X86_MTRR_H #include <uapi/asm/mtrr.h> -#include <asm/pat.h> +#include <asm/memtype.h> /* @@ -86,7 +86,7 @@ static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) } static inline void mtrr_bp_init(void) { - pat_disable("MTRRs disabled, skipping PAT initialization too."); + pat_disable("PAT support disabled because CONFIG_MTRR is disabled in the kernel."); } #define mtrr_ap_init() do {} while (0) diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h deleted file mode 100644 index 92015c65fa2a..000000000000 --- a/arch/x86/include/asm/pat.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_PAT_H -#define _ASM_X86_PAT_H - -#include <linux/types.h> -#include <asm/pgtable_types.h> - -bool pat_enabled(void); -void pat_disable(const char *reason); -extern void pat_init(void); -extern void init_cache_modes(void); - -extern int reserve_memtype(u64 start, u64 end, - enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); -extern int free_memtype(u64 start, u64 end); - -extern int kernel_map_sync_memtype(u64 base, unsigned long size, - enum page_cache_mode pcm); - -int io_reserve_memtype(resource_size_t start, resource_size_t end, - enum page_cache_mode *pcm); - -void io_free_memtype(resource_size_t start, resource_size_t end); - -bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); - -#endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 90d0731fdcb6..c1fdd43fe187 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -9,7 +9,7 @@ #include <linux/scatterlist.h> #include <linux/numa.h> #include <asm/io.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/x86_init.h> struct pci_sysdata { diff --git a/arch/x86/include/asm/pgtable_32_areas.h b/arch/x86/include/asm/pgtable_32_areas.h new file mode 100644 index 000000000000..b6355416a15a --- /dev/null +++ b/arch/x86/include/asm/pgtable_32_areas.h @@ -0,0 +1,53 @@ +#ifndef _ASM_X86_PGTABLE_32_AREAS_H +#define _ASM_X86_PGTABLE_32_AREAS_H + +#include <asm/cpu_entry_area.h> + +/* + * Just any arbitrary offset to the start of the vmalloc VM area: the + * current 8MB value just means that there will be a 8MB "hole" after the + * physical memory until the kernel virtual memory starts. That means that + * any out-of-bounds memory accesses will hopefully be caught. + * The vmalloc() routines leaves a hole of 4kB between each vmalloced + * area for the same reason. ;) + */ +#define VMALLOC_OFFSET (8 * 1024 * 1024) + +#ifndef __ASSEMBLY__ +extern bool __vmalloc_start_set; /* set once high_memory is set */ +#endif + +#define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) +#ifdef CONFIG_X86_PAE +#define LAST_PKMAP 512 +#else +#define LAST_PKMAP 1024 +#endif + +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * DIV_ROUND_UP(sizeof(struct cpu_entry_area), PAGE_SIZE)) + +/* The +1 is for the readonly IDT page: */ +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK) + +#define LDT_BASE_ADDR \ + ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) + +#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) + +#define PKMAP_BASE \ + ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) + +#ifdef CONFIG_HIGHMEM +# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) +#else +# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) +#endif + +#define MODULES_VADDR VMALLOC_START +#define MODULES_END VMALLOC_END +#define MODULES_LEN (MODULES_VADDR - MODULES_END) + +#define MAXMEM (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE) + +#endif /* _ASM_X86_PGTABLE_32_AREAS_H */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index 0416d42e5bdd..5356a46b0373 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_PGTABLE_32_DEFS_H -#define _ASM_X86_PGTABLE_32_DEFS_H +#ifndef _ASM_X86_PGTABLE_32_TYPES_H +#define _ASM_X86_PGTABLE_32_TYPES_H /* * The Linux x86 paging architecture is 'compile-time dual-mode', it @@ -20,55 +20,4 @@ #define PGDIR_SIZE (1UL << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE - 1)) -/* Just any arbitrary offset to the start of the vmalloc VM area: the - * current 8MB value just means that there will be a 8MB "hole" after the - * physical memory until the kernel virtual memory starts. That means that - * any out-of-bounds memory accesses will hopefully be caught. - * The vmalloc() routines leaves a hole of 4kB between each vmalloced - * area for the same reason. ;) - */ -#define VMALLOC_OFFSET (8 * 1024 * 1024) - -#ifndef __ASSEMBLY__ -extern bool __vmalloc_start_set; /* set once high_memory is set */ -#endif - -#define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif - -/* - * This is an upper bound on sizeof(struct cpu_entry_area) / PAGE_SIZE. - * Define this here and validate with BUILD_BUG_ON() in cpu_entry_area.c - * to avoid include recursion hell. - */ -#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 43) - -/* The +1 is for the readonly IDT page: */ -#define CPU_ENTRY_AREA_BASE \ - ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK) - -#define LDT_BASE_ADDR \ - ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) - -#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) - -#define PKMAP_BASE \ - ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) - -#ifdef CONFIG_HIGHMEM -# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) -#else -# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) -#endif - -#define MODULES_VADDR VMALLOC_START -#define MODULES_END VMALLOC_END -#define MODULES_LEN (MODULES_VADDR - MODULES_END) - -#define MAXMEM (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE) - -#endif /* _ASM_X86_PGTABLE_32_DEFS_H */ +#endif /* _ASM_X86_PGTABLE_32_TYPES_H */ diff --git a/arch/x86/include/asm/pgtable_areas.h b/arch/x86/include/asm/pgtable_areas.h new file mode 100644 index 000000000000..d34cce1b995c --- /dev/null +++ b/arch/x86/include/asm/pgtable_areas.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_PGTABLE_AREAS_H +#define _ASM_X86_PGTABLE_AREAS_H + +#ifdef CONFIG_X86_32 +# include <asm/pgtable_32_areas.h> +#endif + +/* Single page reserved for the readonly IDT mapping: */ +#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE +#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) + +#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +#define CPU_ENTRY_AREA_MAP_SIZE (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE) + +#endif /* _ASM_X86_PGTABLE_AREAS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index b5e49e6bac63..ea7400726d7a 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -110,11 +110,6 @@ #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -#define _PAGE_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |\ - _PAGE_ACCESSED | _PAGE_DIRTY) -#define _KERNPG_TABLE_NOENC (_PAGE_PRESENT | _PAGE_RW | \ - _PAGE_ACCESSED | _PAGE_DIRTY) - /* * Set of bits not changed in pte_modify. The pte's * protection key is treated like _PAGE_RW, for @@ -136,80 +131,93 @@ */ #ifndef __ASSEMBLY__ enum page_cache_mode { - _PAGE_CACHE_MODE_WB = 0, - _PAGE_CACHE_MODE_WC = 1, + _PAGE_CACHE_MODE_WB = 0, + _PAGE_CACHE_MODE_WC = 1, _PAGE_CACHE_MODE_UC_MINUS = 2, - _PAGE_CACHE_MODE_UC = 3, - _PAGE_CACHE_MODE_WT = 4, - _PAGE_CACHE_MODE_WP = 5, - _PAGE_CACHE_MODE_NUM = 8 + _PAGE_CACHE_MODE_UC = 3, + _PAGE_CACHE_MODE_WT = 4, + _PAGE_CACHE_MODE_WP = 5, + + _PAGE_CACHE_MODE_NUM = 8 }; #endif -#define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) -#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) -#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) +#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) -#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) -#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_NX) - -#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | \ - _PAGE_USER | _PAGE_ACCESSED) -#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED) -#define PAGE_COPY PAGE_COPY_NOEXEC -#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \ - _PAGE_ACCESSED) - -#define __PAGE_KERNEL_EXEC \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL) -#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC | _PAGE_NX) - -#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) -#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) -#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) -#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) -#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) -#define __PAGE_KERNEL_WP (__PAGE_KERNEL | _PAGE_CACHE_WP) - -#define __PAGE_KERNEL_IO (__PAGE_KERNEL) -#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) +#define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) -#ifndef __ASSEMBLY__ +#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) +#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) -#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) +#define __PP _PAGE_PRESENT +#define __RW _PAGE_RW +#define _USR _PAGE_USER +#define ___A _PAGE_ACCESSED +#define ___D _PAGE_DIRTY +#define ___G _PAGE_GLOBAL +#define __NX _PAGE_NX + +#define _ENC _PAGE_ENC +#define __WP _PAGE_CACHE_WP +#define __NC _PAGE_NOCACHE +#define _PSE _PAGE_PSE + +#define pgprot_val(x) ((x).pgprot) +#define __pgprot(x) ((pgprot_t) { (x) } ) +#define __pg(x) __pgprot(x) + +#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) + +#define PAGE_NONE __pg( 0| 0| 0|___A| 0| 0| 0|___G) +#define PAGE_SHARED __pg(__PP|__RW|_USR|___A|__NX| 0| 0| 0) +#define PAGE_SHARED_EXEC __pg(__PP|__RW|_USR|___A| 0| 0| 0| 0) +#define PAGE_COPY_NOEXEC __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_COPY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) +#define PAGE_COPY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_READONLY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_READONLY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) + +#define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G) +#define _KERNPG_TABLE_NOENC (__PP|__RW| 0|___A| 0|___D| 0| 0) +#define _KERNPG_TABLE (__PP|__RW| 0|___A| 0|___D| 0| 0| _ENC) +#define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) +#define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) +#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_RX (__PP| 0| 0|___A| 0|___D| 0|___G) +#define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) +#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) +#define __PAGE_KERNEL_LARGE_EXEC (__PP|__RW| 0|___A| 0|___D|_PSE|___G) +#define __PAGE_KERNEL_WP (__PP|__RW| 0|___A|__NX|___D| 0|___G| __WP) + + +#define __PAGE_KERNEL_IO __PAGE_KERNEL +#define __PAGE_KERNEL_IO_NOCACHE __PAGE_KERNEL_NOCACHE -#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ - _PAGE_DIRTY | _PAGE_ENC) -#define _PAGE_TABLE (_KERNPG_TABLE | _PAGE_USER) -#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) -#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _PAGE_ENC) +#ifndef __ASSEMBLY__ -#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL) -#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP) +#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _ENC) +#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _ENC) +#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL | 0) +#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP | 0) -#define default_pgprot(x) __pgprot((x) & __default_kernel_pte_mask) +#define __pgprot_mask(x) __pgprot((x) & __default_kernel_pte_mask) -#define PAGE_KERNEL default_pgprot(__PAGE_KERNEL | _PAGE_ENC) -#define PAGE_KERNEL_NOENC default_pgprot(__PAGE_KERNEL) -#define PAGE_KERNEL_RO default_pgprot(__PAGE_KERNEL_RO | _PAGE_ENC) -#define PAGE_KERNEL_EXEC default_pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_EXEC_NOENC default_pgprot(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_RX default_pgprot(__PAGE_KERNEL_RX | _PAGE_ENC) -#define PAGE_KERNEL_NOCACHE default_pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) -#define PAGE_KERNEL_LARGE default_pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) -#define PAGE_KERNEL_LARGE_EXEC default_pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VVAR default_pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) +#define PAGE_KERNEL __pgprot_mask(__PAGE_KERNEL | _ENC) +#define PAGE_KERNEL_NOENC __pgprot_mask(__PAGE_KERNEL | 0) +#define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) +#define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) +#define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_RX __pgprot_mask(__PAGE_KERNEL_RX | _ENC) +#define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) +#define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) +#define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) +#define PAGE_KERNEL_VVAR __pgprot_mask(__PAGE_KERNEL_VVAR | _ENC) -#define PAGE_KERNEL_IO default_pgprot(__PAGE_KERNEL_IO) -#define PAGE_KERNEL_IO_NOCACHE default_pgprot(__PAGE_KERNEL_IO_NOCACHE) +#define PAGE_KERNEL_IO __pgprot_mask(__PAGE_KERNEL_IO) +#define PAGE_KERNEL_IO_NOCACHE __pgprot_mask(__PAGE_KERNEL_IO_NOCACHE) #endif /* __ASSEMBLY__ */ @@ -449,9 +457,6 @@ static inline pteval_t pte_flags(pte_t pte) return native_pte_val(pte) & PTE_FLAGS_MASK; } -#define pgprot_val(x) ((x).pgprot) -#define __pgprot(x) ((pgprot_t) { (x) } ) - extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM]; extern uint8_t __pte2cachemode_tbl[8]; diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 5057a8ed100b..78897a8da01f 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -339,22 +339,6 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, #define ARCH_HAS_USER_SINGLE_STEP_REPORT -/* - * When hitting ptrace_stop(), we cannot return using SYSRET because - * that does not restore the full CPU state, only a minimal set. The - * ptracer can change arbitrary register values, which is usually okay - * because the usual ptrace stops run off the signal delivery path which - * forces IRET; however, ptrace_event() stops happen in arbitrary places - * in the kernel and don't force IRET path. - * - * So force IRET path after a ptrace stop. - */ -#define arch_ptrace_stop_needed(code, info) \ -({ \ - force_iret(); \ - false; \ -}) - struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 2ee8e469dcf5..64c3dce374e5 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -81,8 +81,6 @@ int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); extern int kernel_set_to_readonly; -void set_kernel_text_rw(void); -void set_kernel_text_ro(void); #ifdef CONFIG_X86_64 static inline int set_mce_nospec(unsigned long pfn) diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 23c626a742e8..67315fa3956a 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -25,14 +25,6 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, */ #define POKE_MAX_OPCODE_SIZE 5 -struct text_poke_loc { - void *addr; - int len; - s32 rel32; - u8 opcode; - const u8 text[POKE_MAX_OPCODE_SIZE]; -}; - extern void text_poke_early(void *addr, const void *opcode, size_t len); /* @@ -50,21 +42,13 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); * an inconsistent instruction while you patch. */ extern void *text_poke(void *addr, const void *opcode, size_t len); +extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate); -extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries); -extern void text_poke_loc_init(struct text_poke_loc *tp, void *addr, - const void *opcode, size_t len, const void *emulate); -extern int after_bootmem; -extern __ro_after_init struct mm_struct *poking_mm; -extern __ro_after_init unsigned long poking_addr; -#ifndef CONFIG_UML_X86 -static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) -{ - regs->ip = ip; -} +extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate); +extern void text_poke_finish(void); #define INT3_INSN_SIZE 1 #define INT3_INSN_OPCODE 0xCC @@ -78,6 +62,67 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) #define JMP8_INSN_SIZE 2 #define JMP8_INSN_OPCODE 0xEB +#define DISP32_SIZE 4 + +static inline int text_opcode_size(u8 opcode) +{ + int size = 0; + +#define __CASE(insn) \ + case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break + + switch(opcode) { + __CASE(INT3); + __CASE(CALL); + __CASE(JMP32); + __CASE(JMP8); + } + +#undef __CASE + + return size; +} + +union text_poke_insn { + u8 text[POKE_MAX_OPCODE_SIZE]; + struct { + u8 opcode; + s32 disp; + } __attribute__((packed)); +}; + +static __always_inline +void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +{ + static union text_poke_insn insn; /* per instance */ + int size = text_opcode_size(opcode); + + insn.opcode = opcode; + + if (size > 1) { + insn.disp = (long)dest - (long)(addr + size); + if (size == 2) { + /* + * Ensure that for JMP9 the displacement + * actually fits the signed byte. + */ + BUG_ON((insn.disp >> 31) != (insn.disp >> 7)); + } + } + + return &insn.text; +} + +extern int after_bootmem; +extern __ro_after_init struct mm_struct *poking_mm; +extern __ro_after_init unsigned long poking_addr; + +#ifndef CONFIG_UML_X86 +static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} + static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) { /* @@ -85,6 +130,9 @@ static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) * stack where the break point happened, and the saving of * pt_regs. We can extend the original stack because of * this gap. See the idtentry macro's create_gap option. + * + * Similarly entry_32.S will have a gap on the stack for (any) hardware + * exception and pt_regs; see FIXUP_FRAME. */ regs->sp -= sizeof(unsigned long); *(unsigned long *)regs->sp = val; diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d779366ce3f8..cf4327986e98 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -239,15 +239,6 @@ static inline int arch_within_stack_frames(const void * const stack, current_thread_info()->status & TS_COMPAT) #endif -/* - * Force syscall return via IRET by making it look as if there was - * some work pending. IRET is our most capable (but slowest) syscall - * return path, which is able to restore modified SS, CS and certain - * EFLAGS values that other (fast) syscall return instructions - * are not able to restore properly. - */ -#define force_iret() set_thread_flag(TIF_NOTIFY_RESUME) - extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 230474e2ddb5..bbcdc7b8f963 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -21,6 +21,7 @@ struct vdso_image { long sym_vvar_page; long sym_pvclock_page; long sym_hvclock_page; + long sym_timens_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index e9ee139cf29e..6ee1f7dba34b 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -21,6 +21,7 @@ #include <clocksource/hyperv_timer.h> #define __vdso_data (VVAR(_vdso_data)) +#define __timens_vdso_data (TIMENS(_vdso_data)) #define VDSO_HAS_TIME 1 @@ -56,6 +57,13 @@ extern struct ms_hyperv_tsc_page hvclock_page __attribute__((visibility("hidden"))); #endif +#ifdef CONFIG_TIME_NS +static __always_inline const struct vdso_data *__arch_get_timens_vdso_data(void) +{ + return __timens_vdso_data; +} +#endif + #ifndef BUILD_VDSO32 static __always_inline @@ -96,8 +104,6 @@ long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) #else -#define VDSO_HAS_32BIT_FALLBACK 1 - static __always_inline long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h new file mode 100644 index 000000000000..29837740b520 --- /dev/null +++ b/arch/x86/include/asm/vmalloc.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_VMALLOC_H +#define _ASM_X86_VMALLOC_H + +#include <asm/pgtable_areas.h> + +#endif /* _ASM_X86_VMALLOC_H */ diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 32f5d9a0b90e..183e98e49ab9 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -19,10 +19,10 @@ #ifndef _ASM_X86_VVAR_H #define _ASM_X86_VVAR_H -#if defined(__VVAR_KERNEL_LDS) - -/* The kernel linker script defines its own magic to put vvars in the - * right place. +#ifdef EMIT_VVAR +/* + * EMIT_VVAR() is used by the kernel linker script to put vvars in the + * right place. Also, it's used by kernel code to import offsets values. */ #define DECLARE_VVAR(offset, type, name) \ EMIT_VVAR(name, offset) @@ -33,9 +33,12 @@ extern char __vvar_page; #define DECLARE_VVAR(offset, type, name) \ extern type vvar_ ## name[CS_BASES] \ - __attribute__((visibility("hidden"))); + __attribute__((visibility("hidden"))); \ + extern type timens_ ## name[CS_BASES] \ + __attribute__((visibility("hidden"))); \ #define VVAR(name) (vvar_ ## name) +#define TIMENS(name) (timens_ ## name) #define DEFINE_VVAR(type, name) \ type name[CS_BASES] \ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ca13851f0570..26b7256f590f 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -27,6 +27,17 @@ static char temp_stack[4096]; #endif /** + * acpi_get_wakeup_address - provide physical address for S3 wakeup + * + * Returns the physical address where the kernel should be resumed after the + * system awakes from S3, e.g. for programming into the firmware waking vector. + */ +unsigned long acpi_get_wakeup_address(void) +{ + return ((unsigned long)(real_mode_header->wakeup_start)); +} + +/** * x86_acpi_enter_sleep_state - enter sleep state * @state: Sleep state to enter. * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index fbb60ca4255c..d06c2079b6c1 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -3,7 +3,7 @@ * Variables and functions used by the code in sleep.c */ -#include <asm/realmode.h> +#include <linux/linkage.h> extern unsigned long saved_video_mode; extern long saved_magic; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 9ec463fe96f2..34360ca301a2 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -936,44 +936,81 @@ static void do_sync_core(void *info) sync_core(); } -static struct bp_patching_desc { +void text_poke_sync(void) +{ + on_each_cpu(do_sync_core, NULL, 1); +} + +struct text_poke_loc { + s32 rel_addr; /* addr := _stext + rel_addr */ + s32 rel32; + u8 opcode; + const u8 text[POKE_MAX_OPCODE_SIZE]; +}; + +struct bp_patching_desc { struct text_poke_loc *vec; int nr_entries; -} bp_patching; + atomic_t refs; +}; + +static struct bp_patching_desc *bp_desc; + +static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +{ + struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */ + + if (!desc || !atomic_inc_not_zero(&desc->refs)) + return NULL; + + return desc; +} + +static inline void put_desc(struct bp_patching_desc *desc) +{ + smp_mb__before_atomic(); + atomic_dec(&desc->refs); +} -static int patch_cmp(const void *key, const void *elt) +static inline void *text_poke_addr(struct text_poke_loc *tp) +{ + return _stext + tp->rel_addr; +} + +static int notrace patch_cmp(const void *key, const void *elt) { struct text_poke_loc *tp = (struct text_poke_loc *) elt; - if (key < tp->addr) + if (key < text_poke_addr(tp)) return -1; - if (key > tp->addr) + if (key > text_poke_addr(tp)) return 1; return 0; } NOKPROBE_SYMBOL(patch_cmp); -int poke_int3_handler(struct pt_regs *regs) +int notrace poke_int3_handler(struct pt_regs *regs) { + struct bp_patching_desc *desc; struct text_poke_loc *tp; + int len, ret = 0; void *ip; + if (user_mode(regs)) + return 0; + /* * Having observed our INT3 instruction, we now must observe - * bp_patching.nr_entries. + * bp_desc: * - * nr_entries != 0 INT3 + * bp_desc = desc INT3 * WMB RMB - * write INT3 if (nr_entries) - * - * Idem for other elements in bp_patching. + * write INT3 if (desc) */ smp_rmb(); - if (likely(!bp_patching.nr_entries)) - return 0; - - if (user_mode(regs)) + desc = try_get_desc(&bp_desc); + if (!desc) return 0; /* @@ -984,19 +1021,20 @@ int poke_int3_handler(struct pt_regs *regs) /* * Skip the binary search if there is a single member in the vector. */ - if (unlikely(bp_patching.nr_entries > 1)) { - tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries, + if (unlikely(desc->nr_entries > 1)) { + tp = bsearch(ip, desc->vec, desc->nr_entries, sizeof(struct text_poke_loc), patch_cmp); if (!tp) - return 0; + goto out_put; } else { - tp = bp_patching.vec; - if (tp->addr != ip) - return 0; + tp = desc->vec; + if (text_poke_addr(tp) != ip) + goto out_put; } - ip += tp->len; + len = text_opcode_size(tp->opcode); + ip += len; switch (tp->opcode) { case INT3_INSN_OPCODE: @@ -1004,7 +1042,7 @@ int poke_int3_handler(struct pt_regs *regs) * Someone poked an explicit INT3, they'll want to handle it, * do not consume. */ - return 0; + goto out_put; case CALL_INSN_OPCODE: int3_emulate_call(regs, (long)ip + tp->rel32); @@ -1019,10 +1057,18 @@ int poke_int3_handler(struct pt_regs *regs) BUG(); } - return 1; + ret = 1; + +out_put: + put_desc(desc); + return ret; } NOKPROBE_SYMBOL(poke_int3_handler); +#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) +static struct text_poke_loc tp_vec[TP_VEC_MAX]; +static int tp_vec_nr; + /** * text_poke_bp_batch() -- update instructions on live kernel on SMP * @tp: vector of instructions to patch @@ -1044,16 +1090,20 @@ NOKPROBE_SYMBOL(poke_int3_handler); * replacing opcode * - sync cores */ -void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) +static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { + struct bp_patching_desc desc = { + .vec = tp, + .nr_entries = nr_entries, + .refs = ATOMIC_INIT(1), + }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - bp_patching.vec = tp; - bp_patching.nr_entries = nr_entries; + smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ /* * Corresponding read barrier in int3 notifier for making sure the @@ -1065,18 +1115,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * First step: add a int3 trap to the address that will be patched. */ for (i = 0; i < nr_entries; i++) - text_poke(tp[i].addr, &int3, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE); - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* * Second step: update all but the first byte of the patched range. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - if (tp[i].len - sizeof(int3) > 0) { - text_poke((char *)tp[i].addr + sizeof(int3), - (const char *)tp[i].text + sizeof(int3), - tp[i].len - sizeof(int3)); + int len = text_opcode_size(tp[i].opcode); + + if (len - INT3_INSN_SIZE > 0) { + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, + (const char *)tp[i].text + INT3_INSN_SIZE, + len - INT3_INSN_SIZE); do_sync++; } } @@ -1087,7 +1139,7 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * not necessary and we'd be safe even without it. But * better safe than sorry (plus there's not only Intel). */ - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); } /* @@ -1098,19 +1150,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) if (tp[i].text[0] == INT3_INSN_OPCODE) continue; - text_poke(tp[i].addr, tp[i].text, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); do_sync++; } if (do_sync) - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* - * sync_core() implies an smp_mb() and orders this store against - * the writing of the new instruction. + * Remove and synchronize_rcu(), except we have a very primitive + * refcount based completion. */ - bp_patching.vec = NULL; - bp_patching.nr_entries = 0; + WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ + if (!atomic_dec_and_test(&desc.refs)) + atomic_cond_read_acquire(&desc.refs, !VAL); } void text_poke_loc_init(struct text_poke_loc *tp, void *addr, @@ -1118,11 +1171,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, { struct insn insn; - if (!opcode) - opcode = (void *)tp->text; - else - memcpy((void *)tp->text, opcode, len); - + memcpy((void *)tp->text, opcode, len); if (!emulate) emulate = opcode; @@ -1132,8 +1181,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, BUG_ON(!insn_complete(&insn)); BUG_ON(len != insn.length); - tp->addr = addr; - tp->len = len; + tp->rel_addr = addr - (void *)_stext; tp->opcode = insn.opcode.bytes[0]; switch (tp->opcode) { @@ -1167,6 +1215,55 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, } } +/* + * We hard rely on the tp_vec being ordered; ensure this is so by flushing + * early if needed. + */ +static bool tp_order_fail(void *addr) +{ + struct text_poke_loc *tp; + + if (!tp_vec_nr) + return false; + + if (!addr) /* force */ + return true; + + tp = &tp_vec[tp_vec_nr - 1]; + if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr) + return true; + + return false; +} + +static void text_poke_flush(void *addr) +{ + if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) { + text_poke_bp_batch(tp_vec, tp_vec_nr); + tp_vec_nr = 0; + } +} + +void text_poke_finish(void) +{ + text_poke_flush(NULL); +} + +void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate) +{ + struct text_poke_loc *tp; + + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + + text_poke_flush(addr); + + tp = &tp_vec[tp_vec_nr++]; + text_poke_loc_init(tp, addr, opcode, len, emulate); +} + /** * text_poke_bp() -- update instructions on live kernel on SMP * @addr: address to patch @@ -1178,10 +1275,15 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, * dynamically allocated memory. This function should be used when it is * not possible to allocate memory. */ -void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) +void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) { struct text_poke_loc tp; + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + text_poke_loc_init(&tp, addr, opcode, len, emulate); text_poke_bp_batch(&tp, 1); } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 251c795b4eb3..69aed0ebbdfc 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -22,6 +22,7 @@ #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -52,6 +53,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -66,6 +68,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 5da106f84e84..fe698f96617c 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -95,7 +95,7 @@ static inline void apbt_set_mapping(void) printk(KERN_WARNING "No timer base from SFI, use default\n"); apbt_address = APBT_DEFAULT_BASE; } - apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE); + apbt_virt_address = ioremap(apbt_address, APBT_MMAP_SIZE); if (!apbt_virt_address) { pr_debug("Failed mapping APBT phy address at %lu\n",\ (unsigned long)apbt_address); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d5b51a740524..ad53b2abc859 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1493,65 +1493,34 @@ static void check_efi_reboot(void) } /* Setup user proc fs files */ -static int proc_hubbed_show(struct seq_file *file, void *data) +static int __maybe_unused proc_hubbed_show(struct seq_file *file, void *data) { seq_printf(file, "0x%x\n", uv_hubbed_system); return 0; } -static int proc_hubless_show(struct seq_file *file, void *data) +static int __maybe_unused proc_hubless_show(struct seq_file *file, void *data) { seq_printf(file, "0x%x\n", uv_hubless_system); return 0; } -static int proc_oemid_show(struct seq_file *file, void *data) +static int __maybe_unused proc_oemid_show(struct seq_file *file, void *data) { seq_printf(file, "%s/%s\n", oem_id, oem_table_id); return 0; } -static int proc_hubbed_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_hubbed_show, (void *)NULL); -} - -static int proc_hubless_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_hubless_show, (void *)NULL); -} - -static int proc_oemid_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_oemid_show, (void *)NULL); -} - -/* (struct is "non-const" as open function is set at runtime) */ -static struct file_operations proc_version_fops = { - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static const struct file_operations proc_oemid_fops = { - .open = proc_oemid_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static __init void uv_setup_proc_files(int hubless) { struct proc_dir_entry *pde; - char *name = hubless ? "hubless" : "hubbed"; pde = proc_mkdir(UV_PROC_NODE, NULL); - proc_create("oemid", 0, pde, &proc_oemid_fops); - proc_create(name, 0, pde, &proc_version_fops); + proc_create_single("oemid", 0, pde, proc_oemid_show); if (hubless) - proc_version_fops.open = proc_hubless_open; + proc_create_single("hubless", 0, pde, proc_hubless_show); else - proc_version_fops.open = proc_hubbed_open; + proc_create_single("hubbed", 0, pde, proc_hubbed_show); } /* Initialize UV hubless systems */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 8a88d3f01476..ac83a0fef628 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -608,9 +608,9 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) return; clear_all: - clear_cpu_cap(c, X86_FEATURE_SME); + setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: - clear_cpu_cap(c, X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV); } } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 6b95f18255fa..745c40135bd3 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -50,7 +50,7 @@ #include <asm/cpu.h> #include <asm/mce.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/intel-family.h> @@ -1024,6 +1024,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define MSBDS_ONLY BIT(5) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) +#define NO_SPECTRE_V2 BIT(8) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1085,6 +1086,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + + /* Zhaoxin Family 7 */ + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), {} }; @@ -1117,7 +1122,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + + if (!cpu_matches(NO_SPECTRE_V2)) + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 5167bd2bb6b1..b3a50d962851 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -78,6 +78,7 @@ struct smca_bank_name { static struct smca_bank_name smca_names[] = { [SMCA_LS] = { "load_store", "Load Store Unit" }, + [SMCA_LS_V2] = { "load_store", "Load Store Unit" }, [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, [SMCA_DE] = { "decode_unit", "Decode Unit" }, @@ -138,6 +139,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = { /* ZN Core (HWID=0xB0) MCA types */ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF }, + { SMCA_LS_V2, HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, @@ -266,10 +268,10 @@ static void smca_configure(unsigned int bank, unsigned int cpu) smca_set_misc_banks_map(bank, cpu); /* Return early if this bank was already initialized. */ - if (smca_banks[bank].hwid) + if (smca_banks[bank].hwid && smca_banks[bank].hwid->hwid_mcatype != 0) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 5f42f25bac8f..2c4f949611e4 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,8 +53,6 @@ #include "internal.h" -static DEFINE_MUTEX(mce_log_mutex); - /* sysfs synchronization */ static DEFINE_MUTEX(mce_sysfs_mutex); @@ -156,19 +154,10 @@ void mce_log(struct mce *m) if (!mce_gen_pool_add(m)) irq_work_queue(&mce_irq_work); } - -void mce_inject_log(struct mce *m) -{ - mutex_lock(&mce_log_mutex); - mce_log(m); - mutex_unlock(&mce_log_mutex); -} -EXPORT_SYMBOL_GPL(mce_inject_log); - -static struct notifier_block mce_srao_nb; +EXPORT_SYMBOL_GPL(mce_log); /* - * We run the default notifier if we have only the SRAO, the first and the + * We run the default notifier if we have only the UC, the first and the * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS * notifiers registered on the chain. */ @@ -594,26 +583,29 @@ static struct notifier_block first_nb = { .priority = MCE_PRIO_FIRST, }; -static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, - void *data) +static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) { struct mce *mce = (struct mce *)data; unsigned long pfn; - if (!mce) + if (!mce || !mce_usable_address(mce)) return NOTIFY_DONE; - if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { - pfn = mce->addr >> PAGE_SHIFT; - if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); - } + if (mce->severity != MCE_AO_SEVERITY && + mce->severity != MCE_DEFERRED_SEVERITY) + return NOTIFY_DONE; + + pfn = mce->addr >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); return NOTIFY_OK; } -static struct notifier_block mce_srao_nb = { - .notifier_call = srao_decode_notifier, - .priority = MCE_PRIO_SRAO, + +static struct notifier_block mce_uc_nb = { + .notifier_call = uc_decode_notifier, + .priority = MCE_PRIO_UC, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -763,26 +755,22 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) log_it: error_seen = true; - mce_read_aux(&m, i); + if (flags & MCP_DONTLOG) + goto clear_it; + mce_read_aux(&m, i); m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) - mce_log(&m); - else if (mce_usable_address(&m)) { - /* - * Although we skipped logging this, we still want - * to take action. Add to the pool so the registered - * notifiers will see it. - */ - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } + if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) + goto clear_it; + + mce_log(&m); + +clear_it: /* * Clear state for this bank. */ @@ -807,7 +795,7 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - char *tmp; + char *tmp = *msg; int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { @@ -819,8 +807,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, if (quirk_no_way_out) quirk_no_way_out(i, m, regs); + m->bank = i; if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { - m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; @@ -1232,8 +1220,8 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; int cpu = smp_processor_id(); - char *msg = "Unknown"; struct mce m, *final; + char *msg = NULL; int worst = 0; /* @@ -1365,7 +1353,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) ist_end_non_atomic(); } else { if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) - mce_panic("Failed kernel mode recovery", &m, NULL); + mce_panic("Failed kernel mode recovery", &m, msg); } out_ist: @@ -2041,7 +2029,7 @@ int __init mcheck_init(void) { mcheck_intel_therm_init(); mce_register_decode_chain(&first_nb); - mce_register_decode_chain(&mce_srao_nb); + mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 1f30117b24ba..3413b41b8d55 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -494,7 +494,7 @@ static void do_inject(void) i_mce.status |= MCI_STATUS_SYNDV; if (inj_type == SW_INJ) { - mce_inject_log(&i_mce); + mce_log(&i_mce); return; } diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 842b273bce31..b785c0d0b590 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -84,8 +84,6 @@ static inline int apei_clear_mce(u64 record_id) } #endif -void mce_inject_log(struct mce *m); - /* * We consider records to be equivalent if bank+status+addr+misc all match. * This is only used when the system is going down because of a fatal error diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index b38010b541d6..58b4ee3cda77 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -235,7 +235,7 @@ static void get_therm_status(int level, bool *proc_hot, u8 *temp) *temp = (msr_val >> 16) & 0x7F; } -static void throttle_active_work(struct work_struct *work) +static void __maybe_unused throttle_active_work(struct work_struct *work) { struct _thermal_state *state = container_of(to_delayed_work(work), struct _thermal_state, therm_work); @@ -467,6 +467,7 @@ static int thermal_throttle_online(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + u32 l; state->package_throttle.level = PACKAGE_LEVEL; state->core_throttle.level = CORE_LEVEL; @@ -474,6 +475,10 @@ static int thermal_throttle_online(unsigned int cpu) INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work); INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work); + /* Unmask the thermal vector after the above workqueues are initialized. */ + l = apic_read(APIC_LVTTHMR); + apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); + return thermal_throttle_add_dev(dev, cpu); } @@ -722,10 +727,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c) rdmsr(MSR_IA32_MISC_ENABLE, l, h); wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h); - /* Unmask the thermal vector: */ - l = apic_read(APIC_LVTTHMR); - apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", tm2 ? "TM2" : "TM1"); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index aa5c064a6a22..51b9190c628b 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -15,7 +15,7 @@ #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include "mtrr.h" diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 507039c20128..6a80f36b5d59 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -52,7 +52,7 @@ #include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include "mtrr.h" diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 03eb90d00af0..89049b343c7a 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -618,7 +618,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) if (static_branch_unlikely(&rdt_mon_enable_key)) rmdir_mondata_subdir_allrdtgrp(r, d->id); list_del(&d->list); - if (is_mbm_enabled()) + if (r->mon_capable && is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { /* diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e49b77283924..181c992f448c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) } DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /** * struct mon_evt - Entry in the event list of a resource diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 397206f23d14..773124b0e18a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); @@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2e3b06d6bbc6..1504bcabc63c 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -532,11 +532,15 @@ static void move_myself(struct callback_head *head) kfree(rdtgrp); } + if (unlikely(current->flags & PF_EXITING)) + goto out; + preempt_disable(); /* update PQR_ASSOC MSR to make resource group go into effect */ resctrl_sched_in(); preempt_enable(); +out: kfree(callback); } @@ -725,6 +729,92 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +#ifdef CONFIG_PROC_CPU_RESCTRL + +/* + * A task can only be part of one resctrl control group and of one monitor + * group which is associated to that control group. + * + * 1) res: + * mon: + * + * resctrl is not available. + * + * 2) res:/ + * mon: + * + * Task is part of the root resctrl control group, and it is not associated + * to any monitor group. + * + * 3) res:/ + * mon:mon0 + * + * Task is part of the root resctrl control group and monitor group mon0. + * + * 4) res:group0 + * mon: + * + * Task is part of resctrl control group group0, and it is not associated + * to any monitor group. + * + * 5) res:group0 + * mon:mon1 + * + * Task is part of resctrl control group group0 and monitor group mon1. + */ +int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + struct rdtgroup *rdtg; + int ret = 0; + + mutex_lock(&rdtgroup_mutex); + + /* Return empty if resctrl has not been mounted. */ + if (!static_branch_unlikely(&rdt_enable_key)) { + seq_puts(s, "res:\nmon:\n"); + goto unlock; + } + + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) { + struct rdtgroup *crg; + + /* + * Task information is only relevant for shareable + * and exclusive groups. + */ + if (rdtg->mode != RDT_MODE_SHAREABLE && + rdtg->mode != RDT_MODE_EXCLUSIVE) + continue; + + if (rdtg->closid != tsk->closid) + continue; + + seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", + rdtg->kn->name); + seq_puts(s, "mon:"); + list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, + mon.crdtgrp_list) { + if (tsk->rmid != crg->mon.rmid) + continue; + seq_printf(s, "%s", crg->kn->name); + break; + } + seq_putc(s, '\n'); + goto unlock; + } + /* + * The above search should succeed. Otherwise return + * with an error. + */ + ret = -ENOENT; +unlock: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} +#endif + static int rdt_last_cmd_status_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { @@ -1741,9 +1831,6 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; - if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) - return -ENOMEM; - if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -1751,6 +1838,9 @@ static int set_cache_qos_cfg(int level, bool enable) else return -EINVAL; + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) + return -ENOMEM; + r_l = &rdt_resources_all[level]; list_for_each_entry(d, &r_l->domains, list) { /* Pick one CPU from each domain instance to update MSR */ diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index adf9b71386ef..62b137c3c97a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -4,7 +4,7 @@ */ #include <linux/cpu.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/apic.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index ee48c3fc8a65..d3a0791bc052 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -7,7 +7,7 @@ #include <linux/cpu.h> #include <asm/apic.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 3e20d322bc98..032509adf9de 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -115,11 +115,12 @@ void __init tsx_init(void) tsx_disable(); /* - * tsx_disable() will change the state of the - * RTM CPUID bit. Clear it here since it is now - * expected to be not set. + * tsx_disable() will change the state of the RTM and HLE CPUID + * bits. Clear them here since they are now expected to be not + * set. */ setup_clear_cpu_cap(X86_FEATURE_RTM); + setup_clear_cpu_cap(X86_FEATURE_HLE); } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { /* @@ -131,10 +132,10 @@ void __init tsx_init(void) tsx_enable(); /* - * tsx_enable() will change the state of the - * RTM CPUID bit. Force it here since it is now - * expected to be set. + * tsx_enable() will change the state of the RTM and HLE CPUID + * bits. Force them here since they are now expected to be set. */ setup_force_cpu_cap(X86_FEATURE_RTM); + setup_force_cpu_cap(X86_FEATURE_HLE); } } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 4cba91ec8049..2f9ec14be3b1 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -710,8 +710,12 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3e20, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_INTEL, 0x3ec4, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x8a12, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 319be936c348..fa31470bbf24 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -259,7 +259,7 @@ static void __init setup_xstate_features(void) xmm_space); xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; - xstate_sizes[XFEATURE_SSE] = FIELD_SIZEOF(struct fxregs_state, + xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 060a361d9d11..37a0aeaf89e7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/memory.h> +#include <linux/vmalloc.h> #include <trace/syscall.h> @@ -34,6 +35,8 @@ #ifdef CONFIG_DYNAMIC_FTRACE +static int ftrace_poke_late = 0; + int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { @@ -43,84 +46,37 @@ int ftrace_arch_code_modify_prepare(void) * ftrace has it set to "read/write". */ mutex_lock(&text_mutex); - set_kernel_text_rw(); - set_all_modules_text_rw(); + ftrace_poke_late = 1; return 0; } int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { - set_all_modules_text_ro(); - set_kernel_text_ro(); + /* + * ftrace_make_{call,nop}() may be called during + * module load, and we need to finish the text_poke_queue() + * that they do, here. + */ + text_poke_finish(); + ftrace_poke_late = 0; mutex_unlock(&text_mutex); return 0; } -union ftrace_code_union { - char code[MCOUNT_INSN_SIZE]; - struct { - unsigned char op; - int offset; - } __attribute__((packed)); -}; - -static int ftrace_calc_offset(long ip, long addr) -{ - return (int)(addr - ip); -} - -static unsigned char * -ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) +static const char *ftrace_nop_replace(void) { - static union ftrace_code_union calc; - - calc.op = op; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - return calc.code; -} - -static unsigned char * -ftrace_call_replace(unsigned long ip, unsigned long addr) -{ - return ftrace_text_replace(0xe8, ip, addr); -} - -static inline int -within(unsigned long addr, unsigned long start, unsigned long end) -{ - return addr >= start && addr < end; + return ideal_nops[NOP_ATOMIC5]; } -static unsigned long text_ip_addr(unsigned long ip) +static const char *ftrace_call_replace(unsigned long ip, unsigned long addr) { - /* - * On x86_64, kernel text mappings are mapped read-only, so we use - * the kernel identity mapping instead of the kernel text mapping - * to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); - - return ip; + return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr); } -static const unsigned char *ftrace_nop_replace(void) +static int ftrace_verify_code(unsigned long ip, const char *old_code) { - return ideal_nops[NOP_ATOMIC5]; -} - -static int -ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - - ftrace_expected = old_code; + char cur_code[MCOUNT_INSN_SIZE]; /* * Note: @@ -129,31 +85,46 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, * Carefully read and modify the code with probe_kernel_*(), and make * sure what we read is what we expected it to be before modifying it. */ - /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + WARN_ON(1); return -EFAULT; + } /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) { + WARN_ON(1); return -EINVAL; + } - ip = text_ip_addr(ip); - - /* replace the text with the new text */ - if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) - return -EPERM; + return 0; +} - sync_core(); +/* + * Marked __ref because it calls text_poke_early() which is .init.text. That is + * ok because that call will happen early, during boot, when .init sections are + * still present. + */ +static int __ref +ftrace_modify_code_direct(unsigned long ip, const char *old_code, + const char *new_code) +{ + int ret = ftrace_verify_code(ip, old_code); + if (ret) + return ret; + /* replace the text with the new text */ + if (ftrace_poke_late) + text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL); + else + text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE); return 0; } -int ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_call_replace(ip, addr); new = ftrace_nop_replace(); @@ -167,19 +138,20 @@ int ftrace_make_nop(struct module *mod, * just modify the code directly. */ if (addr == MCOUNT_ADDR) - return ftrace_modify_code_direct(rec->ip, old, new); + return ftrace_modify_code_direct(ip, old, new); - ftrace_expected = NULL; - - /* Normal cases use add_brk_on_nop */ + /* + * x86 overrides ftrace_replace_code -- this function will never be used + * in this case. + */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_nop_replace(); new = ftrace_call_replace(ip, addr); @@ -189,43 +161,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* - * The modifying_ftrace_code is used to tell the breakpoint - * handler to call ftrace_int3_handler(). If it fails to - * call this handler for a breakpoint added by ftrace, then - * the kernel may crash. - * - * As atomic_writes on x86 do not need a barrier, we do not - * need to add smp_mb()s for this to work. It is also considered - * that we can not read the modifying_ftrace_code before - * executing the breakpoint. That would be quite remarkable if - * it could do that. Here's the flow that is required: - * - * CPU-0 CPU-1 - * - * atomic_inc(mfc); - * write int3s - * <trap-int3> // implicit (r)mb - * if (atomic_read(mfc)) - * call ftrace_int3_handler() - * - * Then when we are finished: - * - * atomic_dec(mfc); - * - * If we hit a breakpoint that was not set by ftrace, it does not - * matter if ftrace_int3_handler() is called or not. It will - * simply be ignored. But it is crucial that a ftrace nop/caller - * breakpoint is handled. No other user should ever place a - * breakpoint on an ftrace nop/caller location. It must only - * be done by this code. - */ -atomic_t modifying_ftrace_code __read_mostly; - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code); - -/* * Should never be called: * As it is only called by __ftrace_replace_code() which is called by * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() @@ -237,452 +172,84 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); - ftrace_expected = NULL; return -EINVAL; } -static unsigned long ftrace_update_func; -static unsigned long ftrace_update_func_call; - -static int update_ftrace_func(unsigned long ip, void *new) -{ - unsigned char old[MCOUNT_INSN_SIZE]; - int ret; - - memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); - - ftrace_update_func = ip; - /* Make sure the breakpoints see the ftrace_update_func update */ - smp_wmb(); - - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - - ret = ftrace_modify_code(ip, old, new); - - atomic_dec(&modifying_ftrace_code); - - return ret; -} - int ftrace_update_ftrace_func(ftrace_func_t func) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char *new; - int ret; - - ftrace_update_func_call = (unsigned long)func; - - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - - /* Also update the regs callback function */ - if (!ret) { - ip = (unsigned long)(&ftrace_regs_call); - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - } - - return ret; -} - -static nokprobe_inline int is_ftrace_caller(unsigned long ip) -{ - if (ip == ftrace_update_func) - return 1; - - return 0; -} - -/* - * A breakpoint was added to the code address we are about to - * modify, and this is the handle that will just skip over it. - * We are either changing a nop into a trace call, or a trace - * call to a nop. While the change is taking place, we treat - * it just like it was a nop. - */ -int ftrace_int3_handler(struct pt_regs *regs) -{ unsigned long ip; + const char *new; - if (WARN_ON_ONCE(!regs)) - return 0; - - ip = regs->ip - INT3_INSN_SIZE; - - if (ftrace_location(ip)) { - int3_emulate_call(regs, (unsigned long)ftrace_regs_caller); - return 1; - } else if (is_ftrace_caller(ip)) { - if (!ftrace_update_func_call) { - int3_emulate_jmp(regs, ip + CALL_INSN_SIZE); - return 1; - } - int3_emulate_call(regs, ftrace_update_func_call); - return 1; - } - - return 0; -} -NOKPROBE_SYMBOL(ftrace_int3_handler); - -static int ftrace_write(unsigned long ip, const char *val, int size) -{ - ip = text_ip_addr(ip); - - if (probe_kernel_write((void *)ip, val, size)) - return -EPERM; - - return 0; -} - -static int add_break(unsigned long ip, const char *old) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - ftrace_expected = old; - - /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) - return -EINVAL; - - return ftrace_write(ip, &brk, 1); -} - -static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned const char *old; - unsigned long ip = rec->ip; - - old = ftrace_call_replace(ip, addr); - - return add_break(rec->ip, old); -} - - -static int add_brk_on_nop(struct dyn_ftrace *rec) -{ - unsigned const char *old; - - old = ftrace_nop_replace(); - - return add_break(rec->ip, old); -} - -static int add_breakpoints(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ftrace_addr = ftrace_get_addr_curr(rec); - - ret = ftrace_test_record(rec, enable); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_brk_on_nop(rec); - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_brk_on_call(rec, ftrace_addr); - } - return 0; -} - -/* - * On error, we need to remove breakpoints. This needs to - * be done caefully. If the address does not currently have a - * breakpoint, we know we are done. Otherwise, we look at the - * remaining 4 bytes of the instruction. If it matches a nop - * we replace the breakpoint with the nop. Otherwise we replace - * it with the call instruction. - */ -static int remove_breakpoint(struct dyn_ftrace *rec) -{ - unsigned char ins[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - const unsigned char *nop; - unsigned long ftrace_addr; - unsigned long ip = rec->ip; - - /* If we fail the read, just give up */ - if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - /* If this does not have a breakpoint, we are done */ - if (ins[0] != brk) - return 0; - - nop = ftrace_nop_replace(); - - /* - * If the last 4 bytes of the instruction do not match - * a nop, then we assume that this is a call to ftrace_addr. - */ - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) { - /* - * For extra paranoidism, we check if the breakpoint is on - * a call that would actually jump to the ftrace_addr. - * If not, don't touch the breakpoint, we make just create - * a disaster. - */ - ftrace_addr = ftrace_get_addr_new(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) - goto update; - - /* Check both ftrace_addr and ftrace_old_addr */ - ftrace_addr = ftrace_get_addr_curr(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - ftrace_expected = nop; - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) - return -EINVAL; - } - - update: - return ftrace_write(ip, nop, 1); -} - -static int add_update_code(unsigned long ip, unsigned const char *new) -{ - /* skip breakpoint */ - ip++; - new++; - return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1); -} - -static int add_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - return add_update_code(ip, new); -} - -static int add_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - return add_update_code(ip, new); -} - -static int add_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_test_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_update_call(rec, ftrace_addr); - - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_update_nop(rec); - } - - return 0; -} - -static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - - return ftrace_write(ip, new, 1); -} - -static int finish_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - - return ftrace_write(ip, new, 1); -} - -static int finish_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_update_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return finish_update_call(rec, ftrace_addr); + ip = (unsigned long)(&ftrace_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return finish_update_nop(rec); - } + ip = (unsigned long)(&ftrace_regs_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); return 0; } -static void do_sync_core(void *data) -{ - sync_core(); -} - -static void run_sync(void) -{ - int enable_irqs; - - /* No need to sync if there's only one CPU */ - if (num_online_cpus() == 1) - return; - - enable_irqs = irqs_disabled(); - - /* We may be called with interrupts disabled (on bootup). */ - if (enable_irqs) - local_irq_enable(); - on_each_cpu(do_sync_core, NULL, 1); - if (enable_irqs) - local_irq_disable(); -} - void ftrace_replace_code(int enable) { struct ftrace_rec_iter *iter; struct dyn_ftrace *rec; - const char *report = "adding breakpoints"; - int count = 0; + const char *new, *old; int ret; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = add_breakpoints(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } - - run_sync(); + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - report = "updating code"; - count = 0; + case FTRACE_UPDATE_MAKE_CALL: + old = ftrace_nop_replace(); + break; - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); + case FTRACE_UPDATE_MODIFY_CALL: + case FTRACE_UPDATE_MAKE_NOP: + old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec)); + break; + } - ret = add_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; + ret = ftrace_verify_code(rec->ip, old); + if (ret) { + ftrace_bug(ret, rec); + return; + } } - run_sync(); - - report = "removing breakpoints"; - count = 0; - for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = finish_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - run_sync(); + case FTRACE_UPDATE_MAKE_CALL: + case FTRACE_UPDATE_MODIFY_CALL: + new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec)); + break; - return; + case FTRACE_UPDATE_MAKE_NOP: + new = ftrace_nop_replace(); + break; + } - remove_breakpoints: - pr_warn("Failed on %s (%d):\n", report, count); - ftrace_bug(ret, rec); - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); - /* - * Breakpoints are handled only when this function is in - * progress. The system could not work with them. - */ - if (remove_breakpoint(rec)) - BUG(); + text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL); + ftrace_update_record(rec, enable); } - run_sync(); -} - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - int ret; - - ret = add_break(ip, old_code); - if (ret) - goto out; - - run_sync(); - - ret = add_update_code(ip, new_code); - if (ret) - goto fail_update; - - run_sync(); - - ret = ftrace_write(ip, new_code, 1); - /* - * The breakpoint is handled only when this function is in progress. - * The system could not work if we could not remove it. - */ - BUG_ON(ret); - out: - run_sync(); - return ret; - - fail_update: - /* Also here the system could not work with the breakpoint */ - if (ftrace_write(ip, old_code, 1)) - BUG(); - goto out; + text_poke_finish(); } void arch_ftrace_update_code(int command) { - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - ftrace_modify_all_code(command); - - atomic_dec(&modifying_ftrace_code); } int __init ftrace_dyn_arch_init(void) @@ -747,6 +314,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long start_offset; unsigned long end_offset; unsigned long op_offset; + unsigned long call_offset; unsigned long offset; unsigned long npages; unsigned long size; @@ -763,10 +331,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) start_offset = (unsigned long)ftrace_regs_caller; end_offset = (unsigned long)ftrace_regs_caller_end; op_offset = (unsigned long)ftrace_regs_caller_op_ptr; + call_offset = (unsigned long)ftrace_regs_call; } else { start_offset = (unsigned long)ftrace_caller; end_offset = (unsigned long)ftrace_epilogue; op_offset = (unsigned long)ftrace_caller_op_ptr; + call_offset = (unsigned long)ftrace_call; } size = end_offset - start_offset; @@ -823,16 +393,21 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* put in the new offset to the ftrace_ops */ memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + /* put in the call to the function */ + mutex_lock(&text_mutex); + call_offset -= start_offset; + memcpy(trampoline + call_offset, + text_gen_insn(CALL_INSN_OPCODE, + trampoline + call_offset, + ftrace_ops_get_func(ops)), CALL_INSN_SIZE); + mutex_unlock(&text_mutex); + /* ALLOC_TRAMP flags lets us know we created it */ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; set_vm_flush_reset_perms(trampoline); - /* - * Module allocation needs to be completed by making the page - * executable. The page is still writable, which is a security hazard, - * but anyhow ftrace breaks W^X completely. - */ + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -859,62 +434,54 @@ static unsigned long calc_trampoline_call_offset(bool save_regs) void arch_ftrace_update_trampoline(struct ftrace_ops *ops) { ftrace_func_t func; - unsigned char *new; unsigned long offset; unsigned long ip; unsigned int size; - int ret, npages; + const char *new; - if (ops->trampoline) { - /* - * The ftrace_ops caller may set up its own trampoline. - * In such a case, this code must not modify it. - */ - if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) - return; - npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT; - set_memory_rw(ops->trampoline, npages); - } else { + if (!ops->trampoline) { ops->trampoline = create_trampoline(ops, &size); if (!ops->trampoline) return; ops->trampoline_size = size; - npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + return; } + /* + * The ftrace_ops caller may set up its own trampoline. + * In such a case, this code must not modify it. + */ + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); ip = ops->trampoline + offset; - func = ftrace_ops_get_func(ops); - ftrace_update_func_call = (unsigned long)func; - + mutex_lock(&text_mutex); /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - set_memory_ro(ops->trampoline, npages); - - /* The update should never fail */ - WARN_ON(ret); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + mutex_unlock(&text_mutex); } /* Return the address of the function the trampoline calls */ static void *addr_from_call(void *ptr) { - union ftrace_code_union calc; + union text_poke_insn call; int ret; - ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE); + ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.op != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.op); + if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) { + pr_warn("Expected E8, got %x\n", call.opcode); return NULL; } - return ptr + MCOUNT_INSN_SIZE + calc.offset; + return ptr + CALL_INSN_SIZE + call.disp; } void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, @@ -981,19 +548,18 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - return ftrace_text_replace(0xe9, ip, addr); + return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); } static int ftrace_mod_jmp(unsigned long ip, void *func) { - unsigned char *new; + const char *new; - ftrace_update_func_call = 0UL; new = ftrace_jmp_replace(ip, (unsigned long)func); - - return update_ftrace_func(ip, new); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + return 0; } int ftrace_enable_ftrace_graph_caller(void) @@ -1019,10 +585,9 @@ int ftrace_disable_ftrace_graph_caller(void) void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) { + unsigned long return_hooker = (unsigned long)&return_to_handler; unsigned long old; int faulted; - unsigned long return_hooker = (unsigned long) - &return_to_handler; /* * When resuming from suspend-to-ram, this function can be indirectly @@ -1043,20 +608,6 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, return; /* - * If the return location is actually pointing directly to - * the start of a direct trampoline (if we trace the trampoline - * it will still be offset by MCOUNT_INSN_SIZE), then the - * return address is actually off by one word, and we - * need to adjust for that. - */ - if (ftrace_direct_func_count) { - if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) { - self_addr = *parent; - parent++; - } - } - - /* * Protect against fault, even if it shouldn't * happen. This tool is too much intrusive to * ignore such a protection. diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c6f791bc481e..7a50f0b62a70 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -84,7 +84,7 @@ static inline void hpet_writel(unsigned int d, unsigned int a) static inline void hpet_set_mapping(void) { - hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); + hpet_virt_address = ioremap(hpet_address, HPET_MMAP_SIZE); } static inline void hpet_clear_mapping(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index c1a8b9e71408..9c4498ea0b3c 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -16,15 +16,7 @@ #include <asm/alternative.h> #include <asm/text-patching.h> -union jump_code_union { - char code[JUMP_LABEL_NOP_SIZE]; - struct { - char jump; - int offset; - } __attribute__((packed)); -}; - -static void bug_at(unsigned char *ip, int line) +static void bug_at(const void *ip, int line) { /* * The location is not an op that we were expecting. @@ -35,42 +27,42 @@ static void bug_at(unsigned char *ip, int line) BUG(); } -static void __jump_label_set_jump_code(struct jump_entry *entry, - enum jump_label_type type, - union jump_code_union *code, - int init) +static const void * +__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, int init) { const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - const void *expect; + const void *expect, *code; + const void *addr, *dest; int line; - code->jump = 0xe9; - code->offset = jump_entry_target(entry) - - (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); + addr = (void *)jump_entry_code(entry); + dest = (void *)jump_entry_target(entry); + + code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); if (init) { expect = default_nop; line = __LINE__; } else if (type == JUMP_LABEL_JMP) { expect = ideal_nop; line = __LINE__; } else { - expect = code->code; line = __LINE__; + expect = code; line = __LINE__; } - if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE)) - bug_at((void *)jump_entry_code(entry), line); + if (memcmp(addr, expect, JUMP_LABEL_NOP_SIZE)) + bug_at(addr, line); if (type == JUMP_LABEL_NOP) - memcpy(code, ideal_nop, JUMP_LABEL_NOP_SIZE); + code = ideal_nop; + + return code; } -static void __ref __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static void inline __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { - union jump_code_union code; - - __jump_label_set_jump_code(entry, type, &code, init); + const void *opcode = __jump_label_set_jump_code(entry, type, init); /* * As long as only a single processor is running and the code is still @@ -84,31 +76,33 @@ static void __ref __jump_label_transform(struct jump_entry *entry, * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { - text_poke_early((void *)jump_entry_code(entry), &code, + text_poke_early((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE); return; } - text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL); + text_poke_bp((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE, NULL); } -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +static void __ref jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { mutex_lock(&text_mutex); - __jump_label_transform(entry, type, 0); + __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } -#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) -static struct text_poke_loc tp_vec[TP_VEC_MAX]; -static int tp_vec_nr; +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_transform(entry, type, 0); +} bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { - struct text_poke_loc *tp; - void *entry_code; + const void *opcode; if (system_state == SYSTEM_BOOTING) { /* @@ -118,53 +112,19 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, return true; } - /* - * No more space in the vector, tell upper layer to apply - * the queue before continuing. - */ - if (tp_vec_nr == TP_VEC_MAX) - return false; - - tp = &tp_vec[tp_vec_nr]; - - entry_code = (void *)jump_entry_code(entry); - - /* - * The INT3 handler will do a bsearch in the queue, so we need entries - * to be sorted. We can survive an unsorted list by rejecting the entry, - * forcing the generic jump_label code to apply the queue. Warning once, - * to raise the attention to the case of an unsorted entry that is - * better not happen, because, in the worst case we will perform in the - * same way as we do without batching - with some more overhead. - */ - if (tp_vec_nr > 0) { - int prev = tp_vec_nr - 1; - struct text_poke_loc *prev_tp = &tp_vec[prev]; - - if (WARN_ON_ONCE(prev_tp->addr > entry_code)) - return false; - } - - __jump_label_set_jump_code(entry, type, - (union jump_code_union *)&tp->text, 0); - - text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL); - - tp_vec_nr++; - + mutex_lock(&text_mutex); + opcode = __jump_label_set_jump_code(entry, type, 0); + text_poke_queue((void *)jump_entry_code(entry), + opcode, JUMP_LABEL_NOP_SIZE, NULL); + mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { - if (!tp_vec_nr) - return; - mutex_lock(&text_mutex); - text_poke_bp_batch(tp_vec, tp_vec_nr); + text_poke_finish(); mutex_unlock(&text_mutex); - - tp_vec_nr = 0; } static enum { @@ -193,5 +153,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, jlstate = JL_STATE_NO_UPDATE; } if (jlstate == JL_STATE_UPDATE) - __jump_label_transform(entry, type, 1); + jump_label_transform(entry, type, 1); } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index d2f4e706a428..f293d872602a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -177,7 +177,7 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, * acpi_rsdp=<addr> on kernel command line to make second kernel boot * without efi. */ - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; params->secure_boot = boot_params.secure_boot; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 4f13af7cbcdb..4d7022a740ab 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -40,6 +40,7 @@ #include <linux/frame.h> #include <linux/kasan.h> #include <linux/moduleloader.h> +#include <linux/vmalloc.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -119,14 +120,14 @@ __synthesize_relative_insn(void *dest, void *from, void *to, u8 op) /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ void synthesize_reljump(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE); + __synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ void synthesize_relcall(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE); + __synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_relcall); @@ -301,7 +302,7 @@ static int can_probe(unsigned long paddr) * Another debugging subsystem might insert this breakpoint. * In that case, we can't recover it. */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; addr += insn.length; } @@ -356,7 +357,7 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) return 0; /* Another subsystem puts a breakpoint, failed to recover */ - if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn->opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* We should not singlestep on the exception masking instructions */ @@ -400,14 +401,14 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, int len = insn->length; if (can_boost(insn, p->addr) && - MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) { + MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) { /* * These instructions can be executed directly if it * jumps back to correct address. */ synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; p->ainsn.boostable = true; } else { p->ainsn.boostable = false; @@ -501,12 +502,14 @@ int arch_prepare_kprobe(struct kprobe *p) void arch_arm_kprobe(struct kprobe *p) { - text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); + text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1); + text_poke_sync(); } void arch_disarm_kprobe(struct kprobe *p) { text_poke(p->addr, &p->opcode, 1); + text_poke_sync(); } void arch_remove_kprobe(struct kprobe *p) @@ -609,7 +612,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, regs->flags |= X86_EFLAGS_TF; regs->flags &= ~X86_EFLAGS_IF; /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) + if (p->opcode == INT3_INSN_OPCODE) regs->ip = (unsigned long)p->addr; else regs->ip = (unsigned long)p->ainsn.insn; @@ -695,7 +698,7 @@ int kprobe_int3_handler(struct pt_regs *regs) reset_current_kprobe(); return 1; } - } else if (*addr != BREAKPOINT_INSTRUCTION) { + } else if (*addr != INT3_INSN_OPCODE) { /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 8900329c28a7..3f45b5c43a71 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -38,7 +38,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) long offs; int i; - for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + for (i = 0; i < JMP32_INSN_SIZE; i++) { kp = get_kprobe((void *)addr - i); /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { @@ -62,10 +62,10 @@ found: if (addr == (unsigned long)kp->addr) { buf[0] = kp->opcode; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE); } else { offs = addr - (unsigned long)kp->addr - 1; - memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs); } return (unsigned long)buf; @@ -141,8 +141,6 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_END_IDX \ ((long)optprobe_template_end - (long)optprobe_template_entry) -#define INT3_SIZE sizeof(kprobe_opcode_t) - /* Optimized kprobe call back function: called from optinsn */ static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) @@ -162,7 +160,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE; regs->orig_ax = ~0UL; __this_cpu_write(current_kprobe, &op->kp); @@ -179,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) struct insn insn; int len = 0, ret; - while (len < RELATIVEJUMP_SIZE) { + while (len < JMP32_INSN_SIZE) { ret = __copy_instruction(dest + len, src + len, real + len, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; @@ -271,7 +269,7 @@ static int can_optimize(unsigned long paddr) return 0; /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) + if (size - offset < JMP32_INSN_SIZE) return 0; /* Decode instructions */ @@ -290,15 +288,15 @@ static int can_optimize(unsigned long paddr) kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); /* Check any instructions don't jump into target */ if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) + insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE, + DISP32_SIZE)) return 0; addr += insn.length; } @@ -374,7 +372,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE; if (abs(rel) > 0x7fffffff) { ret = -ERANGE; goto err; @@ -401,7 +399,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, /* Set returning jmp instruction at the tail of out-of-line buffer */ synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; /* We have to use text_poke() for instruction buffer because it is RO */ text_poke(slot, buf, len); @@ -416,49 +414,50 @@ err: } /* - * Replace breakpoints (int3) with relative jumps. + * Replace breakpoints (INT3) with relative jumps (JMP.d32). * Caller must call with locking kprobe_mutex and text_mutex. + * + * The caller will have installed a regular kprobe and after that issued + * syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in + * the 4 bytes after the INT3 are unused and can now be overwritten. */ void arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - u8 insn_buff[RELATIVEJUMP_SIZE]; + u8 insn_buff[JMP32_INSN_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + ((long)op->kp.addr + JMP32_INSN_SIZE)); WARN_ON(kprobe_disabled(&op->kp)); /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE, + DISP32_SIZE); - insn_buff[0] = RELATIVEJUMP_OPCODE; + insn_buff[0] = JMP32_INSN_OPCODE; *(s32 *)(&insn_buff[1]) = rel; - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL); + text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL); list_del_init(&op->list); } } -/* Replace a relative jump with a breakpoint (int3). */ +/* + * Replace a relative jump (JMP.d32) with a breakpoint (INT3). + * + * After that, we can restore the 4 bytes after the INT3 to undo what + * arch_optimize_kprobes() scribbled. This is safe since those bytes will be + * unused once the INT3 lands. + */ void arch_unoptimize_kprobe(struct optimized_kprobe *op) { - u8 insn_buff[RELATIVEJUMP_SIZE]; - u8 emulate_buff[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - insn_buff[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - emulate_buff[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, - emulate_buff); + arch_arm_kprobe(&op->kp); + text_poke(op->kp.addr + INT3_INSN_SIZE, + op->optinsn.copied_insn, DISP32_SIZE); + text_poke_sync(); } /* diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 32ef1ee733b7..81045aabb6f4 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -245,17 +245,13 @@ NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); dotraplinkage void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { - enum ctx_state prev_state; - switch (kvm_read_and_reset_pf_reason()) { default: do_page_fault(regs, error_code, address); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - prev_state = exception_enter(); kvm_async_pf_task_wait((u32)address, !user_mode(regs)); - exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index b2463fcb20a8..c57e1ca70fd1 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -28,6 +28,89 @@ #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/syscalls.h> +#include <asm/pgtable_areas.h> + +/* This is a multiple of PAGE_SIZE. */ +#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) + +static inline void *ldt_slot_va(int slot) +{ + return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); +} + +void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) { + if (static_cpu_has(X86_FEATURE_PTI)) { + if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { + /* + * Whoops -- either the new LDT isn't mapped + * (if slot == -1) or is mapped into a bogus + * slot (if slot > 1). + */ + clear_LDT(); + return; + } + + /* + * If page table isolation is enabled, ldt->entries + * will not be mapped in the userspace pagetables. + * Tell the CPU to access the LDT through the alias + * at ldt_slot_va(ldt->slot). + */ + set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); + } else { + set_ldt(ldt->entries, ldt->nr_entries); + } + } else { + clear_LDT(); + } +} + +void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ + /* + * Load the LDT if either the old or new mm had an LDT. + * + * An mm will never go from having an LDT to not having an LDT. Two + * mms never share an LDT, so we don't gain anything by checking to + * see whether the LDT changed. There's also no guarantee that + * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, + * then prev->context.ldt will also be non-NULL. + * + * If we really cared, we could optimize the case where prev == next + * and we're exiting lazy mode. Most of the time, if this happens, + * we don't actually need to reload LDTR, but modify_ldt() is mostly + * used by legacy code and emulators where we don't need this level of + * performance. + * + * This uses | instead of || because it generates better code. + */ + if (unlikely((unsigned long)prev->context.ldt | + (unsigned long)next->context.ldt)) + load_mm_ldt(next); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} static void refresh_ldt_segments(void) { diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 323499f48858..5052ced43373 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -124,7 +124,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->ip = new_ip; regs->sp = new_sp; regs->flags = X86_EFLAGS_IF; - force_iret(); } EXPORT_SYMBOL_GPL(start_thread); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 506d66830d4d..ffd497804dbc 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -394,7 +394,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - force_iret(); } void diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 1daf8f2aa21f..896d74cb5081 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -110,7 +110,7 @@ static void ich_force_enable_hpet(struct pci_dev *dev) } /* use bits 31:14, 16 kB aligned */ - rcba_base = ioremap_nocache(rcba, 0x4000); + rcba_base = ioremap(rcba, 0x4000); if (rcba_base == NULL) { dev_printk(KERN_DEBUG, &dev->dev, "ioremap failed; " "cannot force enable HPET\n"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b5ac9932bcf6..2441b64d061f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -35,12 +35,14 @@ #include <asm/kaslr.h> #include <asm/mce.h> #include <asm/mtrr.h> +#include <asm/realmode.h> #include <asm/olpc_ofw.h> #include <asm/pci-direct.h> #include <asm/prom.h> #include <asm/proto.h> #include <asm/unwind.h> #include <asm/vsyscall.h> +#include <linux/vmalloc.h> /* * max_low_pfn_mapped: highest directly mapped pfn < 4 GB diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 8eb7193e158d..8a29573851a3 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -151,8 +151,6 @@ static int restore_sigcontext(struct pt_regs *regs, err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); - force_iret(); - return err; } diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 01f0e2263b86..298fc1edd9c9 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -90,11 +90,11 @@ __init int create_simplefb(const struct screen_info *si, if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) size <<= 16; length = mode->height * mode->stride; - length = PAGE_ALIGN(length); if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } + length = PAGE_ALIGN(length); /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 4c61f0713832..b89f6ac6a0c0 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -354,7 +354,7 @@ static ssize_t tboot_log_read(struct file *file, char __user *user_buf, size_t c void *kbuf; int ret = -EFAULT; - log_base = ioremap_nocache(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); + log_base = ioremap(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); if (!log_base) return ret; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 05da6b5b167b..f19de6f45d48 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -572,15 +572,6 @@ NOKPROBE_SYMBOL(do_general_protection); dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * ftrace must be first, everything else may cause a recursive crash. - * See note by declaration of modifying_ftrace_code in ftrace.c - */ - if (unlikely(atomic_read(&modifying_ftrace_code)) && - ftrace_int3_handler(regs)) - return; -#endif if (poke_int3_handler(regs)) return; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 332ae6530fa8..e9cc182aa97e 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -187,6 +187,8 @@ static struct orc_entry *orc_find(unsigned long ip) return orc_ftrace_find(ip); } +#ifdef CONFIG_MODULES + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -229,7 +231,6 @@ static int orc_sort_cmp(const void *_a, const void *_b) return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; } -#ifdef CONFIG_MODULES void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, void *_orc, size_t orc_size) { @@ -273,9 +274,11 @@ void __init unwind_init(void) return; } - /* Sort the .orc_unwind and .orc_unwind_ip tables: */ - sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp, - orc_sort_swap); + /* + * Note, the orc_unwind and orc_unwind_ip tables were already + * sorted at build time via the 'sorttable' tool. + * It's ready for binary search straight away, no need to sort it. + */ /* Initialize the fast lookup table: */ lookup_num_blocks = orc_lookup_end - orc_lookup; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index a76c12b38e92..91d55454e702 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -381,7 +381,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) mark_screen_rdonly(tsk->mm); memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); - force_iret(); return regs->ax; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3a1a819da137..e3296aa028fe 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -193,12 +193,10 @@ SECTIONS __vvar_beginning_hack = .; /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) \ +#define EMIT_VVAR(name, offset) \ . = __vvar_beginning_hack + offset; \ *(.vvar_ ## name) -#define __VVAR_KERNEL_LDS #include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS #undef EMIT_VVAR /* diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ce89430a7f80..23e25f3034c2 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -20,7 +20,7 @@ #include <asm/irq.h> #include <asm/io_apic.h> #include <asm/hpet.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/tsc.h> #include <asm/iommu.h> #include <asm/mach_traps.h> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index cfafa320a8cf..cf55629ff0ff 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -402,7 +402,8 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) entry->edx |= F(SPEC_CTRL); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->edx |= F(INTEL_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->edx |= F(SPEC_CTRL_SSBD); /* * We emulate ARCH_CAPABILITIES in software even @@ -759,7 +760,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx |= F(AMD_IBRS); if (boot_cpu_has(X86_FEATURE_STIBP)) entry->ebx |= F(AMD_STIBP); - if (boot_cpu_has(X86_FEATURE_SSBD)) + if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) entry->ebx |= F(AMD_SSBD); if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) entry->ebx |= F(AMD_SSB_NO); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6f92b40d798c..a32b847a8089 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -40,7 +40,7 @@ #include <linux/kthread.h> #include <asm/page.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/cmpxchg.h> #include <asm/e820/api.h> #include <asm/io.h> diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 337830d7a59c..7ff00ea64e4f 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -29,10 +29,7 @@ SYM_FUNC_START_ALIAS(memmove) SYM_FUNC_START(__memmove) - /* Handle more 32 bytes in loop */ mov %rdi, %rax - cmp $0x20, %rdx - jb 1f /* Decide forward/backward copy mode */ cmp %rdi, %rsi @@ -42,7 +39,9 @@ SYM_FUNC_START(__memmove) cmp %rdi, %r8 jg 2f + /* FSRM implies ERMS => no length checks, do the copy directly */ .Lmemmove_begin_forward: + ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS /* @@ -114,6 +113,8 @@ SYM_FUNC_START(__memmove) */ .p2align 4 2: + cmp $0x20, %rdx + jb 1f cmp $680, %rdx jb 6f cmp %dil, %sil diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 3b89c201ac26..345848f270e3 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -12,8 +12,10 @@ CFLAGS_REMOVE_mem_encrypt.o = -pg CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif -obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o +obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ + pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o + +obj-y += pat/ # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) @@ -23,8 +25,6 @@ CFLAGS_mem_encrypt_identity.o := $(nostackp) CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace -obj-$(CONFIG_X86_PAT) += pat_interval.o - obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 304d31d8cbbc..fa4ea09593ab 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -29,6 +29,7 @@ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ +#include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -1486,27 +1487,6 @@ good_area: } NOKPROBE_SYMBOL(do_user_addr_fault); -/* - * Explicitly marked noinline such that the function tracer sees this as the - * page_fault entry point. - */ -static noinline void -__do_page_fault(struct pt_regs *regs, unsigned long hw_error_code, - unsigned long address) -{ - prefetchw(¤t->mm->mmap_sem); - - if (unlikely(kmmio_fault(regs, address))) - return; - - /* Was the fault on kernel-controlled part of the address space? */ - if (unlikely(fault_in_kernel_space(address))) - do_kern_addr_fault(regs, hw_error_code, address); - else - do_user_addr_fault(regs, hw_error_code, address); -} -NOKPROBE_SYMBOL(__do_page_fault); - static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) @@ -1521,13 +1501,19 @@ trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, } dotraplinkage void -do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) +do_page_fault(struct pt_regs *regs, unsigned long hw_error_code, + unsigned long address) { - enum ctx_state prev_state; + prefetchw(¤t->mm->mmap_sem); + trace_page_fault_entries(regs, hw_error_code, address); - prev_state = exception_enter(); - trace_page_fault_entries(regs, error_code, address); - __do_page_fault(regs, error_code, address); - exception_exit(prev_state); + if (unlikely(kmmio_fault(regs, address))) + return; + + /* Was the fault on kernel-controlled part of the address space? */ + if (unlikely(fault_in_kernel_space(address))) + do_kern_addr_fault(regs, hw_error_code, address); + else + do_user_addr_fault(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_page_fault); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 930edeb41ec3..23df4885bbed 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -52,6 +52,7 @@ #include <asm/page_types.h> #include <asm/cpu_entry_area.h> #include <asm/init.h> +#include <asm/pgtable_areas.h> #include "mm_internal.h" @@ -865,43 +866,13 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif int kernel_set_to_readonly __read_mostly; -void set_kernel_text_rw(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long size = PFN_ALIGN(_etext) - start; - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read write\n", - start, start+size); - - set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long size = PFN_ALIGN(_etext) - start; - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read only\n", - start, start+size); - - set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); -} - static void mark_nxdata_nx(void) { /* diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index dcb9bc961b39..abbdecb75fad 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); - struct zone *zone = page_zone(page); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -1260,42 +1258,6 @@ void __init mem_init(void) int kernel_set_to_readonly; -void set_kernel_text_rw(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long end = PFN_ALIGN(_etext); - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read write\n", - start, end); - - /* - * Make the kernel identity mapping for text RW. Kernel text - * mapping will always be RO. Refer to the comment in - * static_protections() in pageattr.c - */ - set_memory_rw(start, (end - start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long start = PFN_ALIGN(_text); - unsigned long end = PFN_ALIGN(_etext); - - if (!kernel_set_to_readonly) - return; - - pr_debug("Set kernel text: %lx - %lx for read only\n", - start, end); - - /* - * Set the kernel identity mapping for text RO. - */ - set_memory_ro(start, (end - start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 6748b4c2baff..f60398aeb644 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -4,7 +4,7 @@ */ #include <asm/iomap.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <linux/export.h> #include <linux/highmem.h> @@ -26,7 +26,7 @@ int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot) if (!is_io_mapping_possible(base, size)) return -EINVAL; - ret = io_reserve_memtype(base, base + size, &pcm); + ret = memtype_reserve_io(base, base + size, &pcm); if (ret) return ret; @@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(iomap_create_wc); void iomap_free(resource_size_t base, unsigned long size) { - io_free_memtype(base, base + size); + memtype_free_io(base, base + size); } EXPORT_SYMBOL_GPL(iomap_free); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b3a2936377b5..44e4beb4239f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -24,7 +24,7 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/pgalloc.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/setup.h> #include "physaddr.h" @@ -196,10 +196,10 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, phys_addr &= PHYSICAL_PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; - retval = reserve_memtype(phys_addr, (u64)phys_addr + size, + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { - printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval); + printk(KERN_ERR "ioremap memtype_reserve failed %d\n", retval); return NULL; } @@ -255,7 +255,7 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; - if (kernel_map_sync_memtype(phys_addr, size, pcm)) + if (memtype_kernel_map_sync(phys_addr, size, pcm)) goto err_free_area; if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) @@ -275,7 +275,7 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, err_free_area: free_vm_area(area); err_free_memtype: - free_memtype(phys_addr, phys_addr + size); + memtype_free(phys_addr, phys_addr + size); return NULL; } @@ -451,7 +451,7 @@ void iounmap(volatile void __iomem *addr) return; } - free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p)); + memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p)); /* Finally remove it */ o = remove_vm_area((void __force *)addr); diff --git a/arch/x86/mm/pat/Makefile b/arch/x86/mm/pat/Makefile new file mode 100644 index 000000000000..ea464c995161 --- /dev/null +++ b/arch/x86/mm/pat/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y := set_memory.o memtype.o + +obj-$(CONFIG_X86_PAT) += memtype_interval.o diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pat/cpa-test.c index facce271e8b9..facce271e8b9 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pat/cpa-test.c diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat/memtype.c index 2d758e19ef22..394be8611748 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat/memtype.c @@ -1,11 +1,34 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Handle caching attributes in page tables (PAT) + * Page Attribute Table (PAT) support: handle memory caching attributes in page tables. * * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> * Suresh B Siddha <suresh.b.siddha@intel.com> * * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen. + * + * Basic principles: + * + * PAT is a CPU feature supported by all modern x86 CPUs, to allow the firmware and + * the kernel to set one of a handful of 'caching type' attributes for physical + * memory ranges: uncached, write-combining, write-through, write-protected, + * and the most commonly used and default attribute: write-back caching. + * + * PAT support supercedes and augments MTRR support in a compatible fashion: MTRR is + * a hardware interface to enumerate a limited number of physical memory ranges + * and set their caching attributes explicitly, programmed into the CPU via MSRs. + * Even modern CPUs have MTRRs enabled - but these are typically not touched + * by the kernel or by user-space (such as the X server), we rely on PAT for any + * additional cache attribute logic. + * + * PAT doesn't work via explicit memory ranges, but uses page table entries to add + * cache attribute information to the mapped memory range: there's 3 bits used, + * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT), with the 8 possible values mapped by the + * CPU to actual cache attributes via an MSR loaded into the CPU (MSR_IA32_CR_PAT). + * + * ( There's a metric ton of finer details, such as compatibility with CPU quirks + * that only support 4 types of PAT entries, and interaction with MTRRs, see + * below for details. ) */ #include <linux/seq_file.h> @@ -29,44 +52,48 @@ #include <asm/mtrr.h> #include <asm/page.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/io.h> -#include "pat_internal.h" -#include "mm_internal.h" +#include "memtype.h" +#include "../mm_internal.h" #undef pr_fmt #define pr_fmt(fmt) "" fmt -static bool __read_mostly boot_cpu_done; +static bool __read_mostly pat_bp_initialized; static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); -static bool __read_mostly pat_initialized; -static bool __read_mostly init_cm_done; +static bool __read_mostly pat_bp_enabled; +static bool __read_mostly pat_cm_initialized; -void pat_disable(const char *reason) +/* + * PAT support is enabled by default, but can be disabled for + * various user-requested or hardware-forced reasons: + */ +void pat_disable(const char *msg_reason) { if (pat_disabled) return; - if (boot_cpu_done) { + if (pat_bp_initialized) { WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); return; } pat_disabled = true; - pr_info("x86/PAT: %s\n", reason); + pr_info("x86/PAT: %s\n", msg_reason); } static int __init nopat(char *str) { - pat_disable("PAT support disabled."); + pat_disable("PAT support disabled via boot option."); return 0; } early_param("nopat", nopat); bool pat_enabled(void) { - return pat_initialized; + return pat_bp_enabled; } EXPORT_SYMBOL_GPL(pat_enabled); @@ -197,6 +224,8 @@ static void __init_cache_modes(u64 pat) char pat_msg[33]; int i; + WARN_ON_ONCE(pat_cm_initialized); + pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, @@ -205,28 +234,28 @@ static void __init_cache_modes(u64 pat) } pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); - init_cm_done = true; + pat_cm_initialized = true; } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) -static void pat_bsp_init(u64 pat) +static void pat_bp_init(u64 pat) { u64 tmp_pat; if (!boot_cpu_has(X86_FEATURE_PAT)) { - pat_disable("PAT not supported by CPU."); + pat_disable("PAT not supported by the CPU."); return; } rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { - pat_disable("PAT MSR is 0, disabled."); + pat_disable("PAT support disabled by the firmware."); return; } wrmsrl(MSR_IA32_CR_PAT, pat); - pat_initialized = true; + pat_bp_enabled = true; __init_cache_modes(pat); } @@ -248,7 +277,7 @@ void init_cache_modes(void) { u64 pat = 0; - if (init_cm_done) + if (pat_cm_initialized) return; if (boot_cpu_has(X86_FEATURE_PAT)) { @@ -291,7 +320,7 @@ void init_cache_modes(void) } /** - * pat_init - Initialize PAT MSR and PAT table + * pat_init - Initialize the PAT MSR and PAT table on the current CPU * * This function initializes PAT MSR and PAT table with an OS-defined value * to enable additional cache attributes, WC, WT and WP. @@ -305,6 +334,10 @@ void pat_init(void) u64 pat; struct cpuinfo_x86 *c = &boot_cpu_data; +#ifndef CONFIG_X86_PAT + pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); +#endif + if (pat_disabled) return; @@ -364,9 +397,9 @@ void pat_init(void) PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT); } - if (!boot_cpu_done) { - pat_bsp_init(pat); - boot_cpu_done = true; + if (!pat_bp_initialized) { + pat_bp_init(pat); + pat_bp_initialized = true; } else { pat_ap_init(pat); } @@ -542,10 +575,10 @@ static u64 sanitize_phys(u64 address) * available type in new_type in case of no error. In case of any error * it will return a negative return value. */ -int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, +int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type, enum page_cache_mode *new_type) { - struct memtype *new; + struct memtype *entry_new; enum page_cache_mode actual_type; int is_range_ram; int err = 0; @@ -593,22 +626,22 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, return -EINVAL; } - new = kzalloc(sizeof(struct memtype), GFP_KERNEL); - if (!new) + entry_new = kzalloc(sizeof(struct memtype), GFP_KERNEL); + if (!entry_new) return -ENOMEM; - new->start = start; - new->end = end; - new->type = actual_type; + entry_new->start = start; + entry_new->end = end; + entry_new->type = actual_type; spin_lock(&memtype_lock); - err = memtype_check_insert(new, new_type); + err = memtype_check_insert(entry_new, new_type); if (err) { - pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", + pr_info("x86/PAT: memtype_reserve failed [mem %#010Lx-%#010Lx], track %s, req %s\n", start, end - 1, - cattr_name(new->type), cattr_name(req_type)); - kfree(new); + cattr_name(entry_new->type), cattr_name(req_type)); + kfree(entry_new); spin_unlock(&memtype_lock); return err; @@ -616,18 +649,17 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, spin_unlock(&memtype_lock); - dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n", - start, end - 1, cattr_name(new->type), cattr_name(req_type), + dprintk("memtype_reserve added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n", + start, end - 1, cattr_name(entry_new->type), cattr_name(req_type), new_type ? cattr_name(*new_type) : "-"); return err; } -int free_memtype(u64 start, u64 end) +int memtype_free(u64 start, u64 end) { - int err = -EINVAL; int is_range_ram; - struct memtype *entry; + struct memtype *entry_old; if (!pat_enabled()) return 0; @@ -640,28 +672,24 @@ int free_memtype(u64 start, u64 end) return 0; is_range_ram = pat_pagerange_is_ram(start, end); - if (is_range_ram == 1) { - - err = free_ram_pages_type(start, end); - - return err; - } else if (is_range_ram < 0) { + if (is_range_ram == 1) + return free_ram_pages_type(start, end); + if (is_range_ram < 0) return -EINVAL; - } spin_lock(&memtype_lock); - entry = memtype_erase(start, end); + entry_old = memtype_erase(start, end); spin_unlock(&memtype_lock); - if (IS_ERR(entry)) { + if (IS_ERR(entry_old)) { pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, start, end - 1); return -EINVAL; } - kfree(entry); + kfree(entry_old); - dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1); + dprintk("memtype_free request [mem %#010Lx-%#010Lx]\n", start, end - 1); return 0; } @@ -700,6 +728,7 @@ static enum page_cache_mode lookup_memtype(u64 paddr) rettype = _PAGE_CACHE_MODE_UC_MINUS; spin_unlock(&memtype_lock); + return rettype; } @@ -723,7 +752,7 @@ bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn) EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr); /** - * io_reserve_memtype - Request a memory type mapping for a region of memory + * memtype_reserve_io - Request a memory type mapping for a region of memory * @start: start (physical address) of the region * @end: end (physical address) of the region * @type: A pointer to memtype, with requested type. On success, requested @@ -732,7 +761,7 @@ EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr); * On success, returns 0 * On failure, returns non-zero */ -int io_reserve_memtype(resource_size_t start, resource_size_t end, +int memtype_reserve_io(resource_size_t start, resource_size_t end, enum page_cache_mode *type) { resource_size_t size = end - start; @@ -742,47 +771,47 @@ int io_reserve_memtype(resource_size_t start, resource_size_t end, WARN_ON_ONCE(iomem_map_sanity_check(start, size)); - ret = reserve_memtype(start, end, req_type, &new_type); + ret = memtype_reserve(start, end, req_type, &new_type); if (ret) goto out_err; if (!is_new_memtype_allowed(start, size, req_type, new_type)) goto out_free; - if (kernel_map_sync_memtype(start, size, new_type) < 0) + if (memtype_kernel_map_sync(start, size, new_type) < 0) goto out_free; *type = new_type; return 0; out_free: - free_memtype(start, end); + memtype_free(start, end); ret = -EBUSY; out_err: return ret; } /** - * io_free_memtype - Release a memory type mapping for a region of memory + * memtype_free_io - Release a memory type mapping for a region of memory * @start: start (physical address) of the region * @end: end (physical address) of the region */ -void io_free_memtype(resource_size_t start, resource_size_t end) +void memtype_free_io(resource_size_t start, resource_size_t end) { - free_memtype(start, end); + memtype_free(start, end); } int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size) { enum page_cache_mode type = _PAGE_CACHE_MODE_WC; - return io_reserve_memtype(start, start + size, &type); + return memtype_reserve_io(start, start + size, &type); } EXPORT_SYMBOL(arch_io_reserve_memtype_wc); void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) { - io_free_memtype(start, start + size); + memtype_free_io(start, start + size); } EXPORT_SYMBOL(arch_io_free_memtype_wc); @@ -839,10 +868,10 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, } /* - * Change the memory type for the physial address range in kernel identity + * Change the memory type for the physical address range in kernel identity * mapping space if that range is a part of identity map. */ -int kernel_map_sync_memtype(u64 base, unsigned long size, +int memtype_kernel_map_sync(u64 base, unsigned long size, enum page_cache_mode pcm) { unsigned long id_sz; @@ -851,15 +880,14 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, return 0; /* - * some areas in the middle of the kernel identity range - * are not mapped, like the PCI space. + * Some areas in the middle of the kernel identity range + * are not mapped, for example the PCI space. */ if (!page_is_ram(base >> PAGE_SHIFT)) return 0; id_sz = (__pa(high_memory-1) <= base + size) ? - __pa(high_memory) - base : - size; + __pa(high_memory) - base : size; if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) { pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n", @@ -873,7 +901,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, /* * Internal interface to reserve a range of physical memory with prot. - * Reserved non RAM regions only and after successful reserve_memtype, + * Reserved non RAM regions only and after successful memtype_reserve, * this func also keeps identity mapping (if any) in sync with this new prot. */ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, @@ -910,14 +938,14 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, return 0; } - ret = reserve_memtype(paddr, paddr + size, want_pcm, &pcm); + ret = memtype_reserve(paddr, paddr + size, want_pcm, &pcm); if (ret) return ret; if (pcm != want_pcm) { if (strict_prot || !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { - free_memtype(paddr, paddr + size); + memtype_free(paddr, paddr + size); pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, cattr_name(want_pcm), @@ -935,8 +963,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, cachemode2protval(pcm)); } - if (kernel_map_sync_memtype(paddr, size, pcm) < 0) { - free_memtype(paddr, paddr + size); + if (memtype_kernel_map_sync(paddr, size, pcm) < 0) { + memtype_free(paddr, paddr + size); return -EINVAL; } return 0; @@ -952,7 +980,7 @@ static void free_pfn_range(u64 paddr, unsigned long size) is_ram = pat_pagerange_is_ram(paddr, paddr + size); if (is_ram == 0) - free_memtype(paddr, paddr + size); + memtype_free(paddr, paddr + size); } /* @@ -1099,25 +1127,30 @@ EXPORT_SYMBOL_GPL(pgprot_writethrough); #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) +/* + * We are allocating a temporary printout-entry to be passed + * between seq_start()/next() and seq_show(): + */ static struct memtype *memtype_get_idx(loff_t pos) { - struct memtype *print_entry; + struct memtype *entry_print; int ret; - print_entry = kzalloc(sizeof(struct memtype), GFP_KERNEL); - if (!print_entry) + entry_print = kzalloc(sizeof(struct memtype), GFP_KERNEL); + if (!entry_print) return NULL; spin_lock(&memtype_lock); - ret = memtype_copy_nth_element(print_entry, pos); + ret = memtype_copy_nth_element(entry_print, pos); spin_unlock(&memtype_lock); - if (!ret) { - return print_entry; - } else { - kfree(print_entry); + /* Free it on error: */ + if (ret) { + kfree(entry_print); return NULL; } + + return entry_print; } static void *memtype_seq_start(struct seq_file *seq, loff_t *pos) @@ -1142,11 +1175,14 @@ static void memtype_seq_stop(struct seq_file *seq, void *v) static int memtype_seq_show(struct seq_file *seq, void *v) { - struct memtype *print_entry = (struct memtype *)v; + struct memtype *entry_print = (struct memtype *)v; + + seq_printf(seq, "PAT: [mem 0x%016Lx-0x%016Lx] %s\n", + entry_print->start, + entry_print->end, + cattr_name(entry_print->type)); - seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type), - print_entry->start, print_entry->end); - kfree(print_entry); + kfree(entry_print); return 0; } @@ -1178,7 +1214,6 @@ static int __init pat_memtype_list_init(void) } return 0; } - late_initcall(pat_memtype_list_init); #endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */ diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat/memtype.h index 79a06684349e..cacecdbceb55 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat/memtype.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PAT_INTERNAL_H_ -#define __PAT_INTERNAL_H_ +#ifndef __MEMTYPE_H_ +#define __MEMTYPE_H_ extern int pat_debug_enable; @@ -29,13 +29,13 @@ static inline char *cattr_name(enum page_cache_mode pcm) } #ifdef CONFIG_X86_PAT -extern int memtype_check_insert(struct memtype *new, +extern int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *new_type); extern struct memtype *memtype_erase(u64 start, u64 end); extern struct memtype *memtype_lookup(u64 addr); -extern int memtype_copy_nth_element(struct memtype *out, loff_t pos); +extern int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos); #else -static inline int memtype_check_insert(struct memtype *new, +static inline int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *new_type) { return 0; } static inline struct memtype *memtype_erase(u64 start, u64 end) @@ -46,4 +46,4 @@ static inline int memtype_copy_nth_element(struct memtype *out, loff_t pos) { return 0; } #endif -#endif /* __PAT_INTERNAL_H_ */ +#endif /* __MEMTYPE_H_ */ diff --git a/arch/x86/mm/pat/memtype_interval.c b/arch/x86/mm/pat/memtype_interval.c new file mode 100644 index 000000000000..a07e4882bf36 --- /dev/null +++ b/arch/x86/mm/pat/memtype_interval.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handle caching attributes in page tables (PAT) + * + * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Suresh B Siddha <suresh.b.siddha@intel.com> + * + * Interval tree used to store the PAT memory type reservations. + */ + +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/interval_tree_generic.h> +#include <linux/sched.h> +#include <linux/gfp.h> + +#include <asm/pgtable.h> +#include <asm/memtype.h> + +#include "memtype.h" + +/* + * The memtype tree keeps track of memory type for specific + * physical memory areas. Without proper tracking, conflicting memory + * types in different mappings can cause CPU cache corruption. + * + * The tree is an interval tree (augmented rbtree) which tree is ordered + * by the starting address. The tree can contain multiple entries for + * different regions which overlap. All the aliases have the same + * cache attributes of course, as enforced by the PAT logic. + * + * memtype_lock protects the rbtree. + */ + +static inline u64 interval_start(struct memtype *entry) +{ + return entry->start; +} + +static inline u64 interval_end(struct memtype *entry) +{ + return entry->end - 1; +} + +INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end, + interval_start, interval_end, + static, interval) + +static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED; + +enum { + MEMTYPE_EXACT_MATCH = 0, + MEMTYPE_END_MATCH = 1 +}; + +static struct memtype *memtype_match(u64 start, u64 end, int match_type) +{ + struct memtype *entry_match; + + entry_match = interval_iter_first(&memtype_rbroot, start, end-1); + + while (entry_match != NULL && entry_match->start < end) { + if ((match_type == MEMTYPE_EXACT_MATCH) && + (entry_match->start == start) && (entry_match->end == end)) + return entry_match; + + if ((match_type == MEMTYPE_END_MATCH) && + (entry_match->start < start) && (entry_match->end == end)) + return entry_match; + + entry_match = interval_iter_next(entry_match, start, end-1); + } + + return NULL; /* Returns NULL if there is no match */ +} + +static int memtype_check_conflict(u64 start, u64 end, + enum page_cache_mode reqtype, + enum page_cache_mode *newtype) +{ + struct memtype *entry_match; + enum page_cache_mode found_type = reqtype; + + entry_match = interval_iter_first(&memtype_rbroot, start, end-1); + if (entry_match == NULL) + goto success; + + if (entry_match->type != found_type && newtype == NULL) + goto failure; + + dprintk("Overlap at 0x%Lx-0x%Lx\n", entry_match->start, entry_match->end); + found_type = entry_match->type; + + entry_match = interval_iter_next(entry_match, start, end-1); + while (entry_match) { + if (entry_match->type != found_type) + goto failure; + + entry_match = interval_iter_next(entry_match, start, end-1); + } +success: + if (newtype) + *newtype = found_type; + + return 0; + +failure: + pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", + current->comm, current->pid, start, end, + cattr_name(found_type), cattr_name(entry_match->type)); + + return -EBUSY; +} + +int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_type) +{ + int err = 0; + + err = memtype_check_conflict(entry_new->start, entry_new->end, entry_new->type, ret_type); + if (err) + return err; + + if (ret_type) + entry_new->type = *ret_type; + + interval_insert(entry_new, &memtype_rbroot); + return 0; +} + +struct memtype *memtype_erase(u64 start, u64 end) +{ + struct memtype *entry_old; + + /* + * Since the memtype_rbroot tree allows overlapping ranges, + * memtype_erase() checks with EXACT_MATCH first, i.e. free + * a whole node for the munmap case. If no such entry is found, + * it then checks with END_MATCH, i.e. shrink the size of a node + * from the end for the mremap case. + */ + entry_old = memtype_match(start, end, MEMTYPE_EXACT_MATCH); + if (!entry_old) { + entry_old = memtype_match(start, end, MEMTYPE_END_MATCH); + if (!entry_old) + return ERR_PTR(-EINVAL); + } + + if (entry_old->start == start) { + /* munmap: erase this node */ + interval_remove(entry_old, &memtype_rbroot); + } else { + /* mremap: update the end value of this node */ + interval_remove(entry_old, &memtype_rbroot); + entry_old->end = start; + interval_insert(entry_old, &memtype_rbroot); + + return NULL; + } + + return entry_old; +} + +struct memtype *memtype_lookup(u64 addr) +{ + return interval_iter_first(&memtype_rbroot, addr, addr + PAGE_SIZE-1); +} + +/* + * Debugging helper, copy the Nth entry of the tree into a + * a copy for printout. This allows us to print out the tree + * via debugfs, without holding the memtype_lock too long: + */ +#ifdef CONFIG_DEBUG_FS +int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos) +{ + struct memtype *entry_match; + int i = 1; + + entry_match = interval_iter_first(&memtype_rbroot, 0, ULONG_MAX); + + while (entry_match && pos != i) { + entry_match = interval_iter_next(entry_match, 0, ULONG_MAX); + i++; + } + + if (entry_match) { /* pos == i */ + *entry_out = *entry_match; + return 0; + } else { + return 1; + } +} +#endif diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pat/set_memory.c index 1b99ad05b117..62a8ebe72a52 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pat/set_memory.c @@ -24,10 +24,10 @@ #include <linux/uaccess.h> #include <asm/pgalloc.h> #include <asm/proto.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/set_memory.h> -#include "mm_internal.h" +#include "../mm_internal.h" /* * The current flushing context - we pass it instead of 5 arguments: @@ -331,7 +331,7 @@ static void cpa_flush_all(unsigned long cache) on_each_cpu(__cpa_flush_all, (void *) cache, 1); } -void __cpa_flush_tlb(void *data) +static void __cpa_flush_tlb(void *data) { struct cpa_data *cpa = data; unsigned int i; @@ -1801,7 +1801,7 @@ int set_memory_uc(unsigned long addr, int numpages) /* * for now UC MINUS. see comments in ioremap() */ - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_UC_MINUS, NULL); if (ret) goto out_err; @@ -1813,7 +1813,7 @@ int set_memory_uc(unsigned long addr, int numpages) return 0; out_free: - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); out_err: return ret; } @@ -1839,14 +1839,14 @@ int set_memory_wc(unsigned long addr, int numpages) { int ret; - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_WC, NULL); if (ret) return ret; ret = _set_memory_wc(addr, numpages); if (ret) - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return ret; } @@ -1873,7 +1873,7 @@ int set_memory_wb(unsigned long addr, int numpages) if (ret) return ret; - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return 0; } EXPORT_SYMBOL(set_memory_wb); @@ -2014,7 +2014,7 @@ static int _set_pages_array(struct page **pages, int numpages, continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - if (reserve_memtype(start, end, new_type, NULL)) + if (memtype_reserve(start, end, new_type, NULL)) goto err_out; } @@ -2040,7 +2040,7 @@ err_out: continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - free_memtype(start, end); + memtype_free(start, end); } return -EINVAL; } @@ -2089,7 +2089,7 @@ int set_pages_array_wb(struct page **pages, int numpages) continue; start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; - free_memtype(start, end); + memtype_free(start, end); } return 0; @@ -2215,7 +2215,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, .pgd = pgd, .numpages = numpages, .mask_set = __pgprot(0), - .mask_clr = __pgprot(0), + .mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)), .flags = 0, }; @@ -2224,12 +2224,6 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, if (!(__supported_pte_mask & _PAGE_NX)) goto out; - if (!(page_flags & _PAGE_NX)) - cpa.mask_clr = __pgprot(_PAGE_NX); - - if (!(page_flags & _PAGE_RW)) - cpa.mask_clr = __pgprot(_PAGE_RW); - if (!(page_flags & _PAGE_ENC)) cpa.mask_clr = pgprot_encrypted(cpa.mask_clr); @@ -2281,5 +2275,5 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, * be exposed to the rest of the kernel. Include these directly here. */ #ifdef CONFIG_CPA_DEBUG -#include "pageattr-test.c" +#include "cpa-test.c" #endif diff --git a/arch/x86/mm/pat_interval.c b/arch/x86/mm/pat_interval.c deleted file mode 100644 index 6855362eaf21..000000000000 --- a/arch/x86/mm/pat_interval.c +++ /dev/null @@ -1,185 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Handle caching attributes in page tables (PAT) - * - * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> - * Suresh B Siddha <suresh.b.siddha@intel.com> - * - * Interval tree used to store the PAT memory type reservations. - */ - -#include <linux/seq_file.h> -#include <linux/debugfs.h> -#include <linux/kernel.h> -#include <linux/interval_tree_generic.h> -#include <linux/sched.h> -#include <linux/gfp.h> - -#include <asm/pgtable.h> -#include <asm/pat.h> - -#include "pat_internal.h" - -/* - * The memtype tree keeps track of memory type for specific - * physical memory areas. Without proper tracking, conflicting memory - * types in different mappings can cause CPU cache corruption. - * - * The tree is an interval tree (augmented rbtree) with tree ordered - * on starting address. Tree can contain multiple entries for - * different regions which overlap. All the aliases have the same - * cache attributes of course. - * - * memtype_lock protects the rbtree. - */ -static inline u64 memtype_interval_start(struct memtype *memtype) -{ - return memtype->start; -} - -static inline u64 memtype_interval_end(struct memtype *memtype) -{ - return memtype->end - 1; -} -INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end, - memtype_interval_start, memtype_interval_end, - static, memtype_interval) - -static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED; - -enum { - MEMTYPE_EXACT_MATCH = 0, - MEMTYPE_END_MATCH = 1 -}; - -static struct memtype *memtype_match(u64 start, u64 end, int match_type) -{ - struct memtype *match; - - match = memtype_interval_iter_first(&memtype_rbroot, start, end-1); - while (match != NULL && match->start < end) { - if ((match_type == MEMTYPE_EXACT_MATCH) && - (match->start == start) && (match->end == end)) - return match; - - if ((match_type == MEMTYPE_END_MATCH) && - (match->start < start) && (match->end == end)) - return match; - - match = memtype_interval_iter_next(match, start, end-1); - } - - return NULL; /* Returns NULL if there is no match */ -} - -static int memtype_check_conflict(u64 start, u64 end, - enum page_cache_mode reqtype, - enum page_cache_mode *newtype) -{ - struct memtype *match; - enum page_cache_mode found_type = reqtype; - - match = memtype_interval_iter_first(&memtype_rbroot, start, end-1); - if (match == NULL) - goto success; - - if (match->type != found_type && newtype == NULL) - goto failure; - - dprintk("Overlap at 0x%Lx-0x%Lx\n", match->start, match->end); - found_type = match->type; - - match = memtype_interval_iter_next(match, start, end-1); - while (match) { - if (match->type != found_type) - goto failure; - - match = memtype_interval_iter_next(match, start, end-1); - } -success: - if (newtype) - *newtype = found_type; - - return 0; - -failure: - pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", - current->comm, current->pid, start, end, - cattr_name(found_type), cattr_name(match->type)); - return -EBUSY; -} - -int memtype_check_insert(struct memtype *new, - enum page_cache_mode *ret_type) -{ - int err = 0; - - err = memtype_check_conflict(new->start, new->end, new->type, ret_type); - if (err) - return err; - - if (ret_type) - new->type = *ret_type; - - memtype_interval_insert(new, &memtype_rbroot); - return 0; -} - -struct memtype *memtype_erase(u64 start, u64 end) -{ - struct memtype *data; - - /* - * Since the memtype_rbroot tree allows overlapping ranges, - * memtype_erase() checks with EXACT_MATCH first, i.e. free - * a whole node for the munmap case. If no such entry is found, - * it then checks with END_MATCH, i.e. shrink the size of a node - * from the end for the mremap case. - */ - data = memtype_match(start, end, MEMTYPE_EXACT_MATCH); - if (!data) { - data = memtype_match(start, end, MEMTYPE_END_MATCH); - if (!data) - return ERR_PTR(-EINVAL); - } - - if (data->start == start) { - /* munmap: erase this node */ - memtype_interval_remove(data, &memtype_rbroot); - } else { - /* mremap: update the end value of this node */ - memtype_interval_remove(data, &memtype_rbroot); - data->end = start; - memtype_interval_insert(data, &memtype_rbroot); - return NULL; - } - - return data; -} - -struct memtype *memtype_lookup(u64 addr) -{ - return memtype_interval_iter_first(&memtype_rbroot, addr, - addr + PAGE_SIZE-1); -} - -#if defined(CONFIG_DEBUG_FS) -int memtype_copy_nth_element(struct memtype *out, loff_t pos) -{ - struct memtype *match; - int i = 1; - - match = memtype_interval_iter_first(&memtype_rbroot, 0, ULONG_MAX); - while (match && pos != i) { - match = memtype_interval_iter_next(match, 0, ULONG_MAX); - i++; - } - - if (match) { /* pos == i */ - *out = *match; - return 0; - } else { - return 1; - } -} -#endif diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 9bb7f0ab9fe6..0e6700eaa4f9 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -18,6 +18,7 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/io.h> +#include <linux/vmalloc.h> unsigned int __VMALLOC_RESERVE = 128 << 20; diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index bdc98150d4db..fc3f3d3e2ef2 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -5,6 +5,7 @@ #include <linux/mm.h> #include <asm/page.h> +#include <linux/vmalloc.h> #include "physaddr.h" diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index 92153d054d6c..bda73cb7a044 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -79,7 +79,7 @@ static void do_read_far_test(void __iomem *p) static void do_test(unsigned long size) { - void __iomem *p = ioremap_nocache(mmio_address, size); + void __iomem *p = ioremap(mmio_address, size); if (!p) { pr_err("could not ioremap, aborting.\n"); return; @@ -104,7 +104,7 @@ static void do_test_bulk_ioremapping(void) int i; for (i = 0; i < 10; ++i) { - p = ioremap_nocache(mmio_address, PAGE_SIZE); + p = ioremap(mmio_address, PAGE_SIZE); if (p) iounmap(p); } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index e6a9edc5baaf..66f96f21a7b6 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -708,7 +708,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, (void *)info, 1); else on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func_remote, - (void *)info, 1, GFP_ATOMIC, cpumask); + (void *)info, 1, cpumask); } /* diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 9df652d3d927..fa855bbaebaf 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -34,7 +34,7 @@ #include <linux/errno.h> #include <linux/memblock.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/e820/api.h> #include <asm/pci_x86.h> #include <asm/io_apic.h> diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 887d181b769b..0c7b6e66c644 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -105,7 +105,7 @@ static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg) start = cfg->address + PCI_MMCFG_BUS_OFFSET(cfg->start_bus); num_buses = cfg->end_bus - cfg->start_bus + 1; size = PCI_MMCFG_BUS_OFFSET(num_buses); - addr = ioremap_nocache(start, size); + addr = ioremap(start, size); if (addr) addr -= PCI_MMCFG_BUS_OFFSET(cfg->start_bus); return addr; diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index fe29f3f5d384..84b09c230cbd 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y -OBJECT_FILES_NON_STANDARD_efi_stub_$(BITS).o := y +KASAN_SANITIZE := n +GCOV_PROFILE := n obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 38d44f36d5ed..59f7f6d60cf6 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -54,8 +54,8 @@ #include <asm/x86_init.h> #include <asm/uv/uv.h> -static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; +static u64 efi_systab_phys __initdata; static efi_config_table_type_t arch_tables[] __initdata = { #ifdef CONFIG_X86_UV @@ -97,32 +97,6 @@ static int __init setup_add_efi_memmap(char *arg) } early_param("add_efi_memmap", setup_add_efi_memmap); -static efi_status_t __init phys_efi_set_virtual_address_map( - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map) -{ - efi_status_t status; - unsigned long flags; - pgd_t *save_pgd; - - save_pgd = efi_call_phys_prolog(); - if (!save_pgd) - return EFI_ABORTED; - - /* Disable interrupts around EFI calls: */ - local_irq_save(flags); - status = efi_call_phys(efi_phys.set_virtual_address_map, - memory_map_size, descriptor_size, - descriptor_version, virtual_map); - local_irq_restore(flags); - - efi_call_phys_epilog(save_pgd); - - return status; -} - void __init efi_find_mirror(void) { efi_memory_desc_t *md; @@ -330,10 +304,16 @@ static void __init efi_clean_memmap(void) } if (n_removal > 0) { - u64 size = efi.memmap.nr_map - n_removal; + struct efi_memory_map_data data = { + .phys_map = efi.memmap.phys_map, + .desc_version = efi.memmap.desc_version, + .desc_size = efi.memmap.desc_size, + .size = data.desc_size * (efi.memmap.nr_map - n_removal), + .flags = 0, + }; pr_warn("Removing %d invalid memory map entries.\n", n_removal); - efi_memmap_install(efi.memmap.phys_map, size); + efi_memmap_install(&data); } } @@ -353,89 +333,90 @@ void __init efi_print_memmap(void) } } -static int __init efi_systab_init(void *phys) +static int __init efi_systab_init(u64 phys) { + int size = efi_enabled(EFI_64BIT) ? sizeof(efi_system_table_64_t) + : sizeof(efi_system_table_32_t); + bool over4g = false; + void *p; + + p = early_memremap_ro(phys, size); + if (p == NULL) { + pr_err("Couldn't map the system table!\n"); + return -ENOMEM; + } + if (efi_enabled(EFI_64BIT)) { - efi_system_table_64_t *systab64; - struct efi_setup_data *data = NULL; - u64 tmp = 0; + const efi_system_table_64_t *systab64 = p; + + efi_systab.hdr = systab64->hdr; + efi_systab.fw_vendor = systab64->fw_vendor; + efi_systab.fw_revision = systab64->fw_revision; + efi_systab.con_in_handle = systab64->con_in_handle; + efi_systab.con_in = systab64->con_in; + efi_systab.con_out_handle = systab64->con_out_handle; + efi_systab.con_out = (void *)(unsigned long)systab64->con_out; + efi_systab.stderr_handle = systab64->stderr_handle; + efi_systab.stderr = systab64->stderr; + efi_systab.runtime = (void *)(unsigned long)systab64->runtime; + efi_systab.boottime = (void *)(unsigned long)systab64->boottime; + efi_systab.nr_tables = systab64->nr_tables; + efi_systab.tables = systab64->tables; + + over4g = systab64->con_in_handle > U32_MAX || + systab64->con_in > U32_MAX || + systab64->con_out_handle > U32_MAX || + systab64->con_out > U32_MAX || + systab64->stderr_handle > U32_MAX || + systab64->stderr > U32_MAX || + systab64->boottime > U32_MAX; if (efi_setup) { - data = early_memremap(efi_setup, sizeof(*data)); - if (!data) + struct efi_setup_data *data; + + data = early_memremap_ro(efi_setup, sizeof(*data)); + if (!data) { + early_memunmap(p, size); return -ENOMEM; - } - systab64 = early_memremap((unsigned long)phys, - sizeof(*systab64)); - if (systab64 == NULL) { - pr_err("Couldn't map the system table!\n"); - if (data) - early_memunmap(data, sizeof(*data)); - return -ENOMEM; - } + } + + efi_systab.fw_vendor = (unsigned long)data->fw_vendor; + efi_systab.runtime = (void *)(unsigned long)data->runtime; + efi_systab.tables = (unsigned long)data->tables; + + over4g |= data->fw_vendor > U32_MAX || + data->runtime > U32_MAX || + data->tables > U32_MAX; - efi_systab.hdr = systab64->hdr; - efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor : - systab64->fw_vendor; - tmp |= data ? data->fw_vendor : systab64->fw_vendor; - efi_systab.fw_revision = systab64->fw_revision; - efi_systab.con_in_handle = systab64->con_in_handle; - tmp |= systab64->con_in_handle; - efi_systab.con_in = systab64->con_in; - tmp |= systab64->con_in; - efi_systab.con_out_handle = systab64->con_out_handle; - tmp |= systab64->con_out_handle; - efi_systab.con_out = systab64->con_out; - tmp |= systab64->con_out; - efi_systab.stderr_handle = systab64->stderr_handle; - tmp |= systab64->stderr_handle; - efi_systab.stderr = systab64->stderr; - tmp |= systab64->stderr; - efi_systab.runtime = data ? - (void *)(unsigned long)data->runtime : - (void *)(unsigned long)systab64->runtime; - tmp |= data ? data->runtime : systab64->runtime; - efi_systab.boottime = (void *)(unsigned long)systab64->boottime; - tmp |= systab64->boottime; - efi_systab.nr_tables = systab64->nr_tables; - efi_systab.tables = data ? (unsigned long)data->tables : - systab64->tables; - tmp |= data ? data->tables : systab64->tables; - - early_memunmap(systab64, sizeof(*systab64)); - if (data) early_memunmap(data, sizeof(*data)); -#ifdef CONFIG_X86_32 - if (tmp >> 32) { - pr_err("EFI data located above 4GB, disabling EFI.\n"); - return -EINVAL; + } else { + over4g |= systab64->fw_vendor > U32_MAX || + systab64->runtime > U32_MAX || + systab64->tables > U32_MAX; } -#endif } else { - efi_system_table_32_t *systab32; - - systab32 = early_memremap((unsigned long)phys, - sizeof(*systab32)); - if (systab32 == NULL) { - pr_err("Couldn't map the system table!\n"); - return -ENOMEM; - } - - efi_systab.hdr = systab32->hdr; - efi_systab.fw_vendor = systab32->fw_vendor; - efi_systab.fw_revision = systab32->fw_revision; - efi_systab.con_in_handle = systab32->con_in_handle; - efi_systab.con_in = systab32->con_in; - efi_systab.con_out_handle = systab32->con_out_handle; - efi_systab.con_out = systab32->con_out; - efi_systab.stderr_handle = systab32->stderr_handle; - efi_systab.stderr = systab32->stderr; - efi_systab.runtime = (void *)(unsigned long)systab32->runtime; - efi_systab.boottime = (void *)(unsigned long)systab32->boottime; - efi_systab.nr_tables = systab32->nr_tables; - efi_systab.tables = systab32->tables; - - early_memunmap(systab32, sizeof(*systab32)); + const efi_system_table_32_t *systab32 = p; + + efi_systab.hdr = systab32->hdr; + efi_systab.fw_vendor = systab32->fw_vendor; + efi_systab.fw_revision = systab32->fw_revision; + efi_systab.con_in_handle = systab32->con_in_handle; + efi_systab.con_in = systab32->con_in; + efi_systab.con_out_handle = systab32->con_out_handle; + efi_systab.con_out = (void *)(unsigned long)systab32->con_out; + efi_systab.stderr_handle = systab32->stderr_handle; + efi_systab.stderr = systab32->stderr; + efi_systab.runtime = (void *)(unsigned long)systab32->runtime; + efi_systab.boottime = (void *)(unsigned long)systab32->boottime; + efi_systab.nr_tables = systab32->nr_tables; + efi_systab.tables = systab32->tables; + } + + early_memunmap(p, size); + + if (IS_ENABLED(CONFIG_X86_32) && over4g) { + pr_err("EFI data located above 4GB, disabling EFI.\n"); + return -EINVAL; } efi.systab = &efi_systab; @@ -455,108 +436,23 @@ static int __init efi_systab_init(void *phys) return 0; } -static int __init efi_runtime_init32(void) -{ - efi_runtime_services_32_t *runtime; - - runtime = early_memremap((unsigned long)efi.systab->runtime, - sizeof(efi_runtime_services_32_t)); - if (!runtime) { - pr_err("Could not map the runtime service table!\n"); - return -ENOMEM; - } - - /* - * We will only need *early* access to the SetVirtualAddressMap - * EFI runtime service. All other runtime services will be called - * via the virtual mapping. - */ - efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - (unsigned long)runtime->set_virtual_address_map; - early_memunmap(runtime, sizeof(efi_runtime_services_32_t)); - - return 0; -} - -static int __init efi_runtime_init64(void) -{ - efi_runtime_services_64_t *runtime; - - runtime = early_memremap((unsigned long)efi.systab->runtime, - sizeof(efi_runtime_services_64_t)); - if (!runtime) { - pr_err("Could not map the runtime service table!\n"); - return -ENOMEM; - } - - /* - * We will only need *early* access to the SetVirtualAddressMap - * EFI runtime service. All other runtime services will be called - * via the virtual mapping. - */ - efi_phys.set_virtual_address_map = - (efi_set_virtual_address_map_t *) - (unsigned long)runtime->set_virtual_address_map; - early_memunmap(runtime, sizeof(efi_runtime_services_64_t)); - - return 0; -} - -static int __init efi_runtime_init(void) -{ - int rv; - - /* - * Check out the runtime services table. We need to map - * the runtime services table so that we can grab the physical - * address of several of the EFI runtime functions, needed to - * set the firmware into virtual mode. - * - * When EFI_PARAVIRT is in force then we could not map runtime - * service memory region because we do not have direct access to it. - * However, runtime services are available through proxy functions - * (e.g. in case of Xen dom0 EFI implementation they call special - * hypercall which executes relevant EFI functions) and that is why - * they are always enabled. - */ - - if (!efi_enabled(EFI_PARAVIRT)) { - if (efi_enabled(EFI_64BIT)) - rv = efi_runtime_init64(); - else - rv = efi_runtime_init32(); - - if (rv) - return rv; - } - - set_bit(EFI_RUNTIME_SERVICES, &efi.flags); - - return 0; -} - void __init efi_init(void) { efi_char16_t *c16; char vendor[100] = "unknown"; int i = 0; - void *tmp; -#ifdef CONFIG_X86_32 - if (boot_params.efi_info.efi_systab_hi || - boot_params.efi_info.efi_memmap_hi) { + if (IS_ENABLED(CONFIG_X86_32) && + (boot_params.efi_info.efi_systab_hi || + boot_params.efi_info.efi_memmap_hi)) { pr_info("Table located above 4GB, disabling EFI.\n"); return; } - efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab; -#else - efi_phys.systab = (efi_system_table_t *) - (boot_params.efi_info.efi_systab | - ((__u64)boot_params.efi_info.efi_systab_hi<<32)); -#endif - if (efi_systab_init(efi_phys.systab)) + efi_systab_phys = boot_params.efi_info.efi_systab | + ((__u64)boot_params.efi_info.efi_systab_hi << 32); + + if (efi_systab_init(efi_systab_phys)) return; efi.config_table = (unsigned long)efi.systab->tables; @@ -566,14 +462,16 @@ void __init efi_init(void) /* * Show what we know for posterity */ - c16 = tmp = early_memremap(efi.systab->fw_vendor, 2); + c16 = early_memremap_ro(efi.systab->fw_vendor, + sizeof(vendor) * sizeof(efi_char16_t)); if (c16) { - for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = *c16++; + for (i = 0; i < sizeof(vendor) - 1 && c16[i]; ++i) + vendor[i] = c16[i]; vendor[i] = '\0'; - } else + early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); + } else { pr_err("Could not map the firmware vendor!\n"); - early_memunmap(tmp, 2); + } pr_info("EFI v%u.%.02u by %s\n", efi.systab->hdr.revision >> 16, @@ -592,19 +490,21 @@ void __init efi_init(void) if (!efi_runtime_supported()) pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); - else { - if (efi_runtime_disabled() || efi_runtime_init()) { - efi_memmap_unmap(); - return; - } + + if (!efi_runtime_supported() || efi_runtime_disabled()) { + efi_memmap_unmap(); + return; } + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); efi_clean_memmap(); if (efi_enabled(EFI_DBG)) efi_print_memmap(); } +#if defined(CONFIG_X86_32) || defined(CONFIG_X86_UV) + void __init efi_set_executable(efi_memory_desc_t *md, bool executable) { u64 addr, npages; @@ -669,6 +569,8 @@ void __init old_map_region(efi_memory_desc_t *md) (unsigned long long)md->phys_addr); } +#endif + /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { @@ -707,7 +609,7 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; - systab = (u64)(unsigned long)efi_phys.systab; + systab = efi_systab_phys; if (md->phys_addr <= systab && systab < end) { systab += md->virt_addr - md->phys_addr; efi.systab = (efi_system_table_t *)(unsigned long)systab; @@ -767,7 +669,7 @@ static inline void *efi_map_next_entry_reverse(void *entry) */ static void *efi_map_next_entry(void *entry) { - if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) { + if (!efi_have_uv1_memmap() && efi_enabled(EFI_64BIT)) { /* * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE * config table feature requires us to map all entries @@ -828,7 +730,7 @@ static bool should_map_region(efi_memory_desc_t *md) * Map all of RAM so that we can access arguments in the 1:1 * mapping when making EFI runtime calls. */ - if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_is_native()) { + if (efi_is_mixed()) { if (md->type == EFI_CONVENTIONAL_MEMORY || md->type == EFI_LOADER_DATA || md->type == EFI_LOADER_CODE) @@ -899,11 +801,11 @@ static void __init kexec_enter_virtual_mode(void) /* * We don't do virtual mode, since we don't do runtime services, on - * non-native EFI. With efi=old_map, we don't do runtime services in + * non-native EFI. With the UV1 memmap, we don't do runtime services in * kexec kernel because in the initial boot something else might * have been mapped at these virtual addresses. */ - if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) { + if (efi_is_mixed() || efi_have_uv1_memmap()) { efi_memmap_unmap(); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; @@ -958,11 +860,6 @@ static void __init kexec_enter_virtual_mode(void) efi.runtime_version = efi_systab.hdr.revision; efi_native_runtime_setup(); - - efi.set_virtual_address_map = NULL; - - if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) - runtime_code_page_mkexec(); #endif } @@ -974,9 +871,9 @@ static void __init kexec_enter_virtual_mode(void) * * The old method which used to update that memory descriptor with the * virtual address obtained from ioremap() is still supported when the - * kernel is booted with efi=old_map on its command line. Same old - * method enabled the runtime services to be called without having to - * thunk back into physical mode for every invocation. + * kernel is booted on SG1 UV1 hardware. Same old method enabled the + * runtime services to be called without having to thunk back into + * physical mode for every invocation. * * The new method does a pagetable switch in a preemption-safe manner * so that we're in a different address space when calling a runtime @@ -999,16 +896,14 @@ static void __init __efi_enter_virtual_mode(void) if (efi_alloc_page_tables()) { pr_err("Failed to allocate EFI page tables\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } efi_merge_regions(); new_memmap = efi_map_regions(&count, &pg_shift); if (!new_memmap) { pr_err("Error reallocating memory, EFI runtime non-functional!\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } pa = __pa(new_memmap); @@ -1022,8 +917,7 @@ static void __init __efi_enter_virtual_mode(void) if (efi_memmap_init_late(pa, efi.memmap.desc_size * count)) { pr_err("Failed to remap late EFI memory map\n"); - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; + goto err; } if (efi_enabled(EFI_DBG)) { @@ -1031,34 +925,22 @@ static void __init __efi_enter_virtual_mode(void) efi_print_memmap(); } - BUG_ON(!efi.systab); + if (WARN_ON(!efi.systab)) + goto err; - if (efi_setup_page_tables(pa, 1 << pg_shift)) { - clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); - return; - } + if (efi_setup_page_tables(pa, 1 << pg_shift)) + goto err; efi_sync_low_kernel_mappings(); - if (efi_is_native()) { - status = phys_efi_set_virtual_address_map( - efi.memmap.desc_size * count, - efi.memmap.desc_size, - efi.memmap.desc_version, - (efi_memory_desc_t *)pa); - } else { - status = efi_thunk_set_virtual_address_map( - efi_phys.set_virtual_address_map, - efi.memmap.desc_size * count, - efi.memmap.desc_size, - efi.memmap.desc_version, - (efi_memory_desc_t *)pa); - } - + status = efi_set_virtual_address_map(efi.memmap.desc_size * count, + efi.memmap.desc_size, + efi.memmap.desc_version, + (efi_memory_desc_t *)pa); if (status != EFI_SUCCESS) { - pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", - status); - panic("EFI call to SetVirtualAddressMap() failed!"); + pr_err("Unable to switch EFI into virtual mode (status=%lx)!\n", + status); + goto err; } efi_free_boot_services(); @@ -1071,13 +953,11 @@ static void __init __efi_enter_virtual_mode(void) */ efi.runtime_version = efi_systab.hdr.revision; - if (efi_is_native()) + if (!efi_is_mixed()) efi_native_runtime_setup(); else efi_thunk_runtime_setup(); - efi.set_virtual_address_map = NULL; - /* * Apply more restrictive page table mapping attributes now that * SVAM() has been called and the firmware has performed all @@ -1087,6 +967,10 @@ static void __init __efi_enter_virtual_mode(void) /* clean DUMMY object */ efi_delete_dummy_variable(); + return; + +err: + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); } void __init efi_enter_virtual_mode(void) @@ -1102,20 +986,6 @@ void __init efi_enter_virtual_mode(void) efi_dump_pagetable(); } -static int __init arch_parse_efi_cmdline(char *str) -{ - if (!str) { - pr_warn("need at least one option\n"); - return -EINVAL; - } - - if (parse_option_str(str, "old_map")) - set_bit(EFI_OLD_MEMMAP, &efi.flags); - - return 0; -} -early_param("efi", arch_parse_efi_cmdline); - bool efi_is_table_address(unsigned long phys_addr) { unsigned int i; diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 9959657127f4..71dddd1620f9 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -66,9 +66,17 @@ void __init efi_map_region(efi_memory_desc_t *md) void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} -pgd_t * __init efi_call_phys_prolog(void) +efi_status_t efi_call_svam(efi_set_virtual_address_map_t *__efiapi *, + u32, u32, u32, void *); + +efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) { struct desc_ptr gdt_descr; + efi_status_t status; + unsigned long flags; pgd_t *save_pgd; /* Current pgd is swapper_pg_dir, we'll restore it later: */ @@ -80,14 +88,18 @@ pgd_t * __init efi_call_phys_prolog(void) gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); - return save_pgd; -} + /* Disable interrupts around EFI calls: */ + local_irq_save(flags); + status = efi_call_svam(&efi.systab->runtime->set_virtual_address_map, + memory_map_size, descriptor_size, + descriptor_version, virtual_map); + local_irq_restore(flags); -void __init efi_call_phys_epilog(pgd_t *save_pgd) -{ load_fixmap_gdt(0); load_cr3(save_pgd); __flush_tlb_all(); + + return status; } void __init efi_runtime_update_mappings(void) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 08ce8177c3af..e2accfe636bd 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -57,142 +57,6 @@ static u64 efi_va = EFI_VA_START; struct efi_scratch efi_scratch; -static void __init early_code_mapping_set_exec(int executable) -{ - efi_memory_desc_t *md; - - if (!(__supported_pte_mask & _PAGE_NX)) - return; - - /* Make EFI service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type == EFI_RUNTIME_SERVICES_CODE || - md->type == EFI_BOOT_SERVICES_CODE) - efi_set_executable(md, executable); - } -} - -pgd_t * __init efi_call_phys_prolog(void) -{ - unsigned long vaddr, addr_pgd, addr_p4d, addr_pud; - pgd_t *save_pgd, *pgd_k, *pgd_efi; - p4d_t *p4d, *p4d_k, *p4d_efi; - pud_t *pud; - - int pgd; - int n_pgds, i, j; - - if (!efi_enabled(EFI_OLD_MEMMAP)) { - efi_switch_mm(&efi_mm); - return efi_mm.pgd; - } - - early_code_mapping_set_exec(1); - - n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); - save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); - if (!save_pgd) - return NULL; - - /* - * Build 1:1 identity mapping for efi=old_map usage. Note that - * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while - * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical - * address X, the pud_index(X) != pud_index(__va(X)), we can only copy - * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping. - * This means here we can only reuse the PMD tables of the direct mapping. - */ - for (pgd = 0; pgd < n_pgds; pgd++) { - addr_pgd = (unsigned long)(pgd * PGDIR_SIZE); - vaddr = (unsigned long)__va(pgd * PGDIR_SIZE); - pgd_efi = pgd_offset_k(addr_pgd); - save_pgd[pgd] = *pgd_efi; - - p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd); - if (!p4d) { - pr_err("Failed to allocate p4d table!\n"); - goto out; - } - - for (i = 0; i < PTRS_PER_P4D; i++) { - addr_p4d = addr_pgd + i * P4D_SIZE; - p4d_efi = p4d + p4d_index(addr_p4d); - - pud = pud_alloc(&init_mm, p4d_efi, addr_p4d); - if (!pud) { - pr_err("Failed to allocate pud table!\n"); - goto out; - } - - for (j = 0; j < PTRS_PER_PUD; j++) { - addr_pud = addr_p4d + j * PUD_SIZE; - - if (addr_pud > (max_pfn << PAGE_SHIFT)) - break; - - vaddr = (unsigned long)__va(addr_pud); - - pgd_k = pgd_offset_k(vaddr); - p4d_k = p4d_offset(pgd_k, vaddr); - pud[j] = *pud_offset(p4d_k, vaddr); - } - } - pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; - } - - __flush_tlb_all(); - return save_pgd; -out: - efi_call_phys_epilog(save_pgd); - return NULL; -} - -void __init efi_call_phys_epilog(pgd_t *save_pgd) -{ - /* - * After the lock is released, the original page table is restored. - */ - int pgd_idx, i; - int nr_pgds; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - - if (!efi_enabled(EFI_OLD_MEMMAP)) { - efi_switch_mm(efi_scratch.prev_mm); - return; - } - - nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); - - for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) { - pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE); - set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); - - if (!pgd_present(*pgd)) - continue; - - for (i = 0; i < PTRS_PER_P4D; i++) { - p4d = p4d_offset(pgd, - pgd_idx * PGDIR_SIZE + i * P4D_SIZE); - - if (!p4d_present(*p4d)) - continue; - - pud = (pud_t *)p4d_page_vaddr(*p4d); - pud_free(&init_mm, pud); - } - - p4d = (p4d_t *)pgd_page_vaddr(*pgd); - p4d_free(&init_mm, p4d); - } - - kfree(save_pgd); - - __flush_tlb_all(); - early_code_mapping_set_exec(0); -} - EXPORT_SYMBOL_GPL(efi_mm); /* @@ -211,7 +75,7 @@ int __init efi_alloc_page_tables(void) pud_t *pud; gfp_t gfp_mask; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; gfp_mask = GFP_KERNEL | __GFP_ZERO; @@ -252,7 +116,7 @@ void efi_sync_low_kernel_mappings(void) pud_t *pud_k, *pud_efi; pgd_t *efi_pgd = efi_mm.pgd; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return; /* @@ -346,7 +210,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) unsigned npages; pgd_t *pgd = efi_mm.pgd; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; /* @@ -373,10 +237,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * as trim_bios_range() will reserve the first page and isolate it away * from memory allocators anyway. */ - pf = _PAGE_RW; - if (sev_active()) - pf |= _PAGE_ENC; - if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, pf)) { pr_err("Failed to create 1:1 mapping for the first page!\n"); return 1; @@ -388,21 +248,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * text and allocate a new stack because we can't rely on the * stack pointer being < 4GB. */ - if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native()) + if (!efi_is_mixed()) return 0; page = alloc_page(GFP_KERNEL|__GFP_DMA32); - if (!page) - panic("Unable to allocate EFI runtime stack < 4GB\n"); + if (!page) { + pr_err("Unable to allocate EFI runtime stack < 4GB\n"); + return 1; + } - efi_scratch.phys_stack = virt_to_phys(page_address(page)); - efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */ + efi_scratch.phys_stack = page_to_phys(page + 1); /* stack grows down */ - npages = (_etext - _text) >> PAGE_SHIFT; + npages = (__end_rodata_aligned - _text) >> PAGE_SHIFT; text = __pa(_text); pfn = text >> PAGE_SHIFT; - pf = _PAGE_RW | _PAGE_ENC; + pf = _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, text, npages, pf)) { pr_err("Failed to map kernel text 1:1\n"); return 1; @@ -417,6 +278,22 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) unsigned long pfn; pgd_t *pgd = efi_mm.pgd; + /* + * EFI_RUNTIME_SERVICES_CODE regions typically cover PE/COFF + * executable images in memory that consist of both R-X and + * RW- sections, so we cannot apply read-only or non-exec + * permissions just yet. However, modern EFI systems provide + * a memory attributes table that describes those sections + * with the appropriate restricted permissions, which are + * applied in efi_runtime_update_mappings() below. All other + * regions can be mapped non-executable at this point, with + * the exception of boot services code regions, but those will + * be unmapped again entirely in efi_free_boot_services(). + */ + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_CODE) + flags |= _PAGE_NX; + if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; @@ -434,7 +311,7 @@ void __init efi_map_region(efi_memory_desc_t *md) unsigned long size = md->num_pages << PAGE_SHIFT; u64 pa = md->phys_addr; - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return old_map_region(md); /* @@ -449,7 +326,7 @@ void __init efi_map_region(efi_memory_desc_t *md) * booting in EFI mixed mode, because even though we may be * running a 64-bit kernel, the firmware may only be 32-bit. */ - if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) { + if (efi_is_mixed()) { md->virt_addr = md->phys_addr; return; } @@ -491,26 +368,6 @@ void __init efi_map_region_fixed(efi_memory_desc_t *md) __map_region(md, md->virt_addr); } -void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, - u32 type, u64 attribute) -{ - unsigned long last_map_pfn; - - if (type == EFI_MEMORY_MAPPED_IO) - return ioremap(phys_addr, size); - - last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); - if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) { - unsigned long top = last_map_pfn << PAGE_SHIFT; - efi_ioremap(top, size - (top - phys_addr), type, attribute); - } - - if (!(attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)__va(phys_addr), size); - - return (void __iomem *)__va(phys_addr); -} - void __init parse_efi_setup(u64 phys_addr, u32 data_len) { efi_setup = phys_addr + sizeof(struct setup_data); @@ -559,7 +416,7 @@ void __init efi_runtime_update_mappings(void) { efi_memory_desc_t *md; - if (efi_enabled(EFI_OLD_MEMMAP)) { + if (efi_have_uv1_memmap()) { if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); return; @@ -613,7 +470,7 @@ void __init efi_runtime_update_mappings(void) void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) ptdump_walk_pgd_level(NULL, swapper_pg_dir); else ptdump_walk_pgd_level(NULL, efi_mm.pgd); @@ -634,63 +491,74 @@ void efi_switch_mm(struct mm_struct *mm) switch_mm(efi_scratch.prev_mm, mm, NULL); } -#ifdef CONFIG_EFI_MIXED -extern efi_status_t efi64_thunk(u32, ...); - static DEFINE_SPINLOCK(efi_runtime_lock); -#define runtime_service32(func) \ -({ \ - u32 table = (u32)(unsigned long)efi.systab; \ - u32 *rt, *___f; \ - \ - rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime)); \ - ___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \ - *___f; \ +/* + * DS and ES contain user values. We need to save them. + * The 32-bit EFI code needs a valid DS, ES, and SS. There's no + * need to save the old SS: __KERNEL_DS is always acceptable. + */ +#define __efi_thunk(func, ...) \ +({ \ + efi_runtime_services_32_t *__rt; \ + unsigned short __ds, __es; \ + efi_status_t ____s; \ + \ + __rt = (void *)(unsigned long)efi.systab->mixed_mode.runtime; \ + \ + savesegment(ds, __ds); \ + savesegment(es, __es); \ + \ + loadsegment(ss, __KERNEL_DS); \ + loadsegment(ds, __KERNEL_DS); \ + loadsegment(es, __KERNEL_DS); \ + \ + ____s = efi64_thunk(__rt->func, __VA_ARGS__); \ + \ + loadsegment(ds, __ds); \ + loadsegment(es, __es); \ + \ + ____s ^= (____s & BIT(31)) | (____s & BIT_ULL(31)) << 32; \ + ____s; \ }) /* * Switch to the EFI page tables early so that we can access the 1:1 * runtime services mappings which are not mapped in any other page - * tables. This function must be called before runtime_service32(). + * tables. * * Also, disable interrupts because the IDT points to 64-bit handlers, * which aren't going to function correctly when we switch to 32-bit. */ -#define efi_thunk(f, ...) \ +#define efi_thunk(func...) \ ({ \ efi_status_t __s; \ - u32 __func; \ \ arch_efi_call_virt_setup(); \ \ - __func = runtime_service32(f); \ - __s = efi64_thunk(__func, __VA_ARGS__); \ + __s = __efi_thunk(func); \ \ arch_efi_call_virt_teardown(); \ \ __s; \ }) -efi_status_t efi_thunk_set_virtual_address_map( - void *phys_set_virtual_address_map, - unsigned long memory_map_size, - unsigned long descriptor_size, - u32 descriptor_version, - efi_memory_desc_t *virtual_map) +static efi_status_t __init __no_sanitize_address +efi_thunk_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) { efi_status_t status; unsigned long flags; - u32 func; efi_sync_low_kernel_mappings(); local_irq_save(flags); efi_switch_mm(&efi_mm); - func = (u32)(unsigned long)phys_set_virtual_address_map; - status = efi64_thunk(func, memory_map_size, descriptor_size, - descriptor_version, virtual_map); + status = __efi_thunk(set_virtual_address_map, memory_map_size, + descriptor_size, descriptor_version, virtual_map); efi_switch_mm(efi_scratch.prev_mm); local_irq_restore(flags); @@ -993,8 +861,11 @@ efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules, return EFI_UNSUPPORTED; } -void efi_thunk_runtime_setup(void) +void __init efi_thunk_runtime_setup(void) { + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return; + efi.get_time = efi_thunk_get_time; efi.set_time = efi_thunk_set_time; efi.get_wakeup_time = efi_thunk_get_wakeup_time; @@ -1010,4 +881,46 @@ void efi_thunk_runtime_setup(void) efi.update_capsule = efi_thunk_update_capsule; efi.query_capsule_caps = efi_thunk_query_capsule_caps; } -#endif /* CONFIG_EFI_MIXED */ + +efi_status_t __init __no_sanitize_address +efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map) +{ + efi_status_t status; + unsigned long flags; + pgd_t *save_pgd = NULL; + + if (efi_is_mixed()) + return efi_thunk_set_virtual_address_map(memory_map_size, + descriptor_size, + descriptor_version, + virtual_map); + + if (efi_have_uv1_memmap()) { + save_pgd = efi_uv1_memmap_phys_prolog(); + if (!save_pgd) + return EFI_ABORTED; + } else { + efi_switch_mm(&efi_mm); + } + + kernel_fpu_begin(); + + /* Disable interrupts around EFI calls: */ + local_irq_save(flags); + status = efi_call(efi.systab->runtime->set_virtual_address_map, + memory_map_size, descriptor_size, + descriptor_version, virtual_map); + local_irq_restore(flags); + + kernel_fpu_end(); + + if (save_pgd) + efi_uv1_memmap_phys_epilog(save_pgd); + else + efi_switch_mm(efi_scratch.prev_mm); + + return status; +} diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S index eed8b5b441f8..75c46e7a809f 100644 --- a/arch/x86/platform/efi/efi_stub_32.S +++ b/arch/x86/platform/efi/efi_stub_32.S @@ -7,118 +7,43 @@ */ #include <linux/linkage.h> +#include <linux/init.h> #include <asm/page_types.h> -/* - * efi_call_phys(void *, ...) is a function with variable parameters. - * All the callers of this function assure that all the parameters are 4-bytes. - */ - -/* - * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save. - * So we'd better save all of them at the beginning of this function and restore - * at the end no matter how many we use, because we can not assure EFI runtime - * service functions will comply with gcc calling convention, too. - */ + __INIT +SYM_FUNC_START(efi_call_svam) + push 8(%esp) + push 8(%esp) + push %ecx + push %edx -.text -SYM_FUNC_START(efi_call_phys) /* - * 0. The function can only be called in Linux kernel. So CS has been - * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found - * the values of these registers are the same. And, the corresponding - * GDT entries are identical. So I will do nothing about segment reg - * and GDT, but change GDT base register in prolog and epilog. - */ - - /* - * 1. Now I am running with EIP = <physical address> + PAGE_OFFSET. - * But to make it smoothly switch from virtual mode to flat mode. - * The mapping of lower virtual memory has been created in prolog and - * epilog. + * Switch to the flat mapped alias of this routine, by jumping to the + * address of label '1' after subtracting PAGE_OFFSET from it. */ movl $1f, %edx subl $__PAGE_OFFSET, %edx jmp *%edx 1: - /* - * 2. Now on the top of stack is the return - * address in the caller of efi_call_phys(), then parameter 1, - * parameter 2, ..., param n. To make things easy, we save the return - * address of efi_call_phys in a global variable. - */ - popl %edx - movl %edx, saved_return_addr - /* get the function pointer into ECX*/ - popl %ecx - movl %ecx, efi_rt_function_ptr - movl $2f, %edx - subl $__PAGE_OFFSET, %edx - pushl %edx - - /* - * 3. Clear PG bit in %CR0. - */ + /* disable paging */ movl %cr0, %edx andl $0x7fffffff, %edx movl %edx, %cr0 - jmp 1f -1: - /* - * 4. Adjust stack pointer. - */ + /* convert the stack pointer to a flat mapped address */ subl $__PAGE_OFFSET, %esp - /* - * 5. Call the physical function. - */ - jmp *%ecx + /* call the EFI routine */ + call *(%eax) -2: - /* - * 6. After EFI runtime service returns, control will return to - * following instruction. We'd better readjust stack pointer first. - */ - addl $__PAGE_OFFSET, %esp + /* convert ESP back to a kernel VA, and pop the outgoing args */ + addl $__PAGE_OFFSET + 16, %esp - /* - * 7. Restore PG bit - */ + /* re-enable paging */ movl %cr0, %edx orl $0x80000000, %edx movl %edx, %cr0 - jmp 1f -1: - /* - * 8. Now restore the virtual mode from flat mode by - * adding EIP with PAGE_OFFSET. - */ - movl $1f, %edx - jmp *%edx -1: - - /* - * 9. Balance the stack. And because EAX contain the return value, - * we'd better not clobber it. - */ - leal efi_rt_function_ptr, %edx - movl (%edx), %ecx - pushl %ecx - /* - * 10. Push the saved return address onto the stack and return. - */ - leal saved_return_addr, %edx - movl (%edx), %ecx - pushl %ecx ret -SYM_FUNC_END(efi_call_phys) -.previous - -.data -saved_return_addr: - .long 0 -efi_rt_function_ptr: - .long 0 +SYM_FUNC_END(efi_call_svam) diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index b1d2313fe3bf..15da118f04f0 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -8,41 +8,12 @@ */ #include <linux/linkage.h> -#include <asm/segment.h> -#include <asm/msr.h> -#include <asm/processor-flags.h> -#include <asm/page_types.h> +#include <asm/nospec-branch.h> -#define SAVE_XMM \ - mov %rsp, %rax; \ - subq $0x70, %rsp; \ - and $~0xf, %rsp; \ - mov %rax, (%rsp); \ - mov %cr0, %rax; \ - clts; \ - mov %rax, 0x8(%rsp); \ - movaps %xmm0, 0x60(%rsp); \ - movaps %xmm1, 0x50(%rsp); \ - movaps %xmm2, 0x40(%rsp); \ - movaps %xmm3, 0x30(%rsp); \ - movaps %xmm4, 0x20(%rsp); \ - movaps %xmm5, 0x10(%rsp) - -#define RESTORE_XMM \ - movaps 0x60(%rsp), %xmm0; \ - movaps 0x50(%rsp), %xmm1; \ - movaps 0x40(%rsp), %xmm2; \ - movaps 0x30(%rsp), %xmm3; \ - movaps 0x20(%rsp), %xmm4; \ - movaps 0x10(%rsp), %xmm5; \ - mov 0x8(%rsp), %rsi; \ - mov %rsi, %cr0; \ - mov (%rsp), %rsp - -SYM_FUNC_START(efi_call) +SYM_FUNC_START(__efi_call) pushq %rbp movq %rsp, %rbp - SAVE_XMM + and $~0xf, %rsp mov 16(%rbp), %rax subq $48, %rsp mov %r9, 32(%rsp) @@ -50,9 +21,7 @@ SYM_FUNC_START(efi_call) mov %r8, %r9 mov %rcx, %r8 mov %rsi, %rcx - call *%rdi - addq $48, %rsp - RESTORE_XMM - popq %rbp + CALL_NOSPEC %rdi + leave ret -SYM_FUNC_END(efi_call) +SYM_FUNC_END(__efi_call) diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 3189f1394701..26f0da238c1c 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -25,15 +25,16 @@ .text .code64 -SYM_FUNC_START(efi64_thunk) +SYM_CODE_START(__efi64_thunk) push %rbp push %rbx /* * Switch to 1:1 mapped 32-bit stack pointer. */ - movq %rsp, efi_saved_sp(%rip) + movq %rsp, %rax movq efi_scratch(%rip), %rsp + push %rax /* * Calculate the physical address of the kernel text. @@ -41,113 +42,31 @@ SYM_FUNC_START(efi64_thunk) movq $__START_KERNEL_map, %rax subq phys_base(%rip), %rax - /* - * Push some physical addresses onto the stack. This is easier - * to do now in a code64 section while the assembler can address - * 64-bit values. Note that all the addresses on the stack are - * 32-bit. - */ - subq $16, %rsp - leaq efi_exit32(%rip), %rbx - subq %rax, %rbx - movl %ebx, 8(%rsp) - - leaq __efi64_thunk(%rip), %rbx + leaq 1f(%rip), %rbp + leaq 2f(%rip), %rbx + subq %rax, %rbp subq %rax, %rbx - call *%rbx - - movq efi_saved_sp(%rip), %rsp - pop %rbx - pop %rbp - retq -SYM_FUNC_END(efi64_thunk) -/* - * We run this function from the 1:1 mapping. - * - * This function must be invoked with a 1:1 mapped stack. - */ -SYM_FUNC_START_LOCAL(__efi64_thunk) - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - subq $32, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movq %r8, %rsi - movl %esi, 0xc(%rsp) - movq %r9, %rsi - movl %esi, 0x10(%rsp) - - leaq 1f(%rip), %rbx - movq %rbx, func_rt_ptr(%rip) + subq $28, %rsp + movl %ebx, 0x0(%rsp) /* return address */ + movl %esi, 0x4(%rsp) + movl %edx, 0x8(%rsp) + movl %ecx, 0xc(%rsp) + movl %r8d, 0x10(%rsp) + movl %r9d, 0x14(%rsp) /* Switch to 32-bit descriptor */ pushq $__KERNEL32_CS - leaq efi_enter32(%rip), %rax - pushq %rax + pushq %rdi /* EFI runtime service address */ lretq -1: addq $32, %rsp - +1: movq 24(%rsp), %rsp pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - - /* - * Convert 32-bit status code into 64-bit. - */ - test %rax, %rax - jz 1f - movl %eax, %ecx - andl $0x0fffffff, %ecx - andl $0xf0000000, %eax - shl $32, %rax - or %rcx, %rax -1: - ret -SYM_FUNC_END(__efi64_thunk) - -SYM_FUNC_START_LOCAL(efi_exit32) - movq func_rt_ptr(%rip), %rax - push %rax - mov %rdi, %rax - ret -SYM_FUNC_END(efi_exit32) + pop %rbp + retq .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -SYM_FUNC_START_LOCAL(efi_enter32) - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - movl %eax, %ss - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - movl 72(%esp), %eax - pushl $__KERNEL_CS - pushl %eax - +2: pushl $__KERNEL_CS + pushl %ebp lret -SYM_FUNC_END(efi_enter32) - - .data - .balign 8 -func_rt_ptr: .quad 0 -efi_saved_sp: .quad 0 +SYM_CODE_END(__efi64_thunk) diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 7675cf754d90..88d32c06cffa 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -16,6 +16,7 @@ #include <asm/efi.h> #include <asm/uv/uv.h> #include <asm/cpu_device_id.h> +#include <asm/realmode.h> #include <asm/reboot.h> #define EFI_MIN_RESERVE 5120 @@ -243,7 +244,7 @@ EXPORT_SYMBOL_GPL(efi_query_variable_store); */ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) { - phys_addr_t new_phys, new_size; + struct efi_memory_map_data data = { 0 }; struct efi_mem_range mr; efi_memory_desc_t md; int num_entries; @@ -260,10 +261,6 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - /* No need to reserve regions that will never be freed. */ - if (md.attribute & EFI_MEMORY_RUNTIME) - return; - size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); @@ -275,24 +272,23 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) num_entries = efi_memmap_split_count(&md, &mr.range); num_entries += efi.memmap.nr_map; - new_size = efi.memmap.desc_size * num_entries; - - new_phys = efi_memmap_alloc(num_entries); - if (!new_phys) { + if (efi_memmap_alloc(num_entries, &data) != 0) { pr_err("Could not allocate boot services memmap\n"); return; } - new = early_memremap(new_phys, new_size); + new = early_memremap(data.phys_map, data.size); if (!new) { pr_err("Failed to map new boot services memmap\n"); return; } efi_memmap_insert(&efi.memmap, new, &mr); - early_memunmap(new, new_size); + early_memunmap(new, data.size); - efi_memmap_install(new_phys, num_entries); + efi_memmap_install(&data); + e820__range_update(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__update_table(e820_table); } /* @@ -386,10 +382,10 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) /* * To Do: Remove this check after adding functionality to unmap EFI boot - * services code/data regions from direct mapping area because - * "efi=old_map" maps EFI regions in swapper_pg_dir. + * services code/data regions from direct mapping area because the UV1 + * memory map maps EFI regions in swapper_pg_dir. */ - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return; /* @@ -397,7 +393,7 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) * EFI runtime calls, hence don't unmap EFI boot services code/data * regions. */ - if (!efi_is_native()) + if (efi_is_mixed()) return; if (kernel_unmap_pages_in_pgd(pgd, pa, md->num_pages)) @@ -409,7 +405,7 @@ static void __init efi_unmap_pages(efi_memory_desc_t *md) void __init efi_free_boot_services(void) { - phys_addr_t new_phys, new_size; + struct efi_memory_map_data data = { 0 }; efi_memory_desc_t *md; int num_entries = 0; void *new, *new_md; @@ -464,14 +460,12 @@ void __init efi_free_boot_services(void) if (!num_entries) return; - new_size = efi.memmap.desc_size * num_entries; - new_phys = efi_memmap_alloc(num_entries); - if (!new_phys) { + if (efi_memmap_alloc(num_entries, &data) != 0) { pr_err("Failed to allocate new EFI memmap\n"); return; } - new = memremap(new_phys, new_size, MEMREMAP_WB); + new = memremap(data.phys_map, data.size, MEMREMAP_WB); if (!new) { pr_err("Failed to map new EFI memmap\n"); return; @@ -495,7 +489,7 @@ void __init efi_free_boot_services(void) memunmap(new); - if (efi_memmap_install(new_phys, num_entries)) { + if (efi_memmap_install(&data) != 0) { pr_err("Could not install new EFI memmap\n"); return; } @@ -560,7 +554,7 @@ out: return ret; } -static const struct dmi_system_id sgi_uv1_dmi[] = { +static const struct dmi_system_id sgi_uv1_dmi[] __initconst = { { NULL, "SGI UV1", { DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"), DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), @@ -583,8 +577,15 @@ void __init efi_apply_memmap_quirks(void) } /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */ - if (dmi_check_system(sgi_uv1_dmi)) - set_bit(EFI_OLD_MEMMAP, &efi.flags); + if (dmi_check_system(sgi_uv1_dmi)) { + if (IS_ENABLED(CONFIG_X86_UV)) { + set_bit(EFI_UV1_MEMMAP, &efi.flags); + } else { + pr_warn("EFI runtime disabled, needs CONFIG_X86_UV=y on UV1\n"); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + efi_memmap_unmap(); + } + } } /* @@ -722,7 +723,7 @@ void efi_recover_from_page_fault(unsigned long phys_addr) /* * Make sure that an efi runtime service caused the page fault. * "efi_mm" cannot be used to check if the page fault had occurred - * in the firmware context because efi=old_map doesn't use efi_pgd. + * in the firmware context because the UV1 memmap doesn't use efi_pgd. */ if (efi_rts_work.efi_rts_id == EFI_NONE) return; diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index 6dd25dc5f027..e9d97d52475e 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -29,6 +29,8 @@ #include <asm/cpu_device_id.h> #include <asm/imr.h> #include <asm/iosf_mbi.h> +#include <asm/io.h> + #include <linux/debugfs.h> #include <linux/init.h> #include <linux/mm.h> diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 42f879b75f9b..4307830e1b6f 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -14,6 +14,8 @@ #include <asm-generic/sections.h> #include <asm/cpu_device_id.h> #include <asm/imr.h> +#include <asm/io.h> + #include <linux/init.h> #include <linux/mm.h> #include <linux/types.h> diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index ece9cb9c1189..607f58147311 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -31,13 +31,16 @@ static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, return BIOS_STATUS_UNIMPLEMENTED; /* - * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI + * If EFI_UV1_MEMMAP is set, we need to fall back to using our old EFI * callback method, which uses efi_call() directly, with the kernel page tables: */ - if (unlikely(efi_enabled(EFI_OLD_MEMMAP))) + if (unlikely(efi_enabled(EFI_UV1_MEMMAP))) { + kernel_fpu_begin(); ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5); - else + kernel_fpu_end(); + } else { ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5); + } return ret; } @@ -214,3 +217,163 @@ int uv_bios_init(void) pr_info("UV: UVsystab: Revision:%x\n", uv_systab->revision); return 0; } + +static void __init early_code_mapping_set_exec(int executable) +{ + efi_memory_desc_t *md; + + if (!(__supported_pte_mask & _PAGE_NX)) + return; + + /* Make EFI service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type == EFI_RUNTIME_SERVICES_CODE || + md->type == EFI_BOOT_SERVICES_CODE) + efi_set_executable(md, executable); + } +} + +void __init efi_uv1_memmap_phys_epilog(pgd_t *save_pgd) +{ + /* + * After the lock is released, the original page table is restored. + */ + int pgd_idx, i; + int nr_pgds; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + + for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) { + pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE); + set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); + + if (!pgd_present(*pgd)) + continue; + + for (i = 0; i < PTRS_PER_P4D; i++) { + p4d = p4d_offset(pgd, + pgd_idx * PGDIR_SIZE + i * P4D_SIZE); + + if (!p4d_present(*p4d)) + continue; + + pud = (pud_t *)p4d_page_vaddr(*p4d); + pud_free(&init_mm, pud); + } + + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + p4d_free(&init_mm, p4d); + } + + kfree(save_pgd); + + __flush_tlb_all(); + early_code_mapping_set_exec(0); +} + +pgd_t * __init efi_uv1_memmap_phys_prolog(void) +{ + unsigned long vaddr, addr_pgd, addr_p4d, addr_pud; + pgd_t *save_pgd, *pgd_k, *pgd_efi; + p4d_t *p4d, *p4d_k, *p4d_efi; + pud_t *pud; + + int pgd; + int n_pgds, i, j; + + early_code_mapping_set_exec(1); + + n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); + save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); + if (!save_pgd) + return NULL; + + /* + * Build 1:1 identity mapping for UV1 memmap usage. Note that + * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while + * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical + * address X, the pud_index(X) != pud_index(__va(X)), we can only copy + * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping. + * This means here we can only reuse the PMD tables of the direct mapping. + */ + for (pgd = 0; pgd < n_pgds; pgd++) { + addr_pgd = (unsigned long)(pgd * PGDIR_SIZE); + vaddr = (unsigned long)__va(pgd * PGDIR_SIZE); + pgd_efi = pgd_offset_k(addr_pgd); + save_pgd[pgd] = *pgd_efi; + + p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd); + if (!p4d) { + pr_err("Failed to allocate p4d table!\n"); + goto out; + } + + for (i = 0; i < PTRS_PER_P4D; i++) { + addr_p4d = addr_pgd + i * P4D_SIZE; + p4d_efi = p4d + p4d_index(addr_p4d); + + pud = pud_alloc(&init_mm, p4d_efi, addr_p4d); + if (!pud) { + pr_err("Failed to allocate pud table!\n"); + goto out; + } + + for (j = 0; j < PTRS_PER_PUD; j++) { + addr_pud = addr_p4d + j * PUD_SIZE; + + if (addr_pud > (max_pfn << PAGE_SHIFT)) + break; + + vaddr = (unsigned long)__va(addr_pud); + + pgd_k = pgd_offset_k(vaddr); + p4d_k = p4d_offset(pgd_k, vaddr); + pud[j] = *pud_offset(p4d_k, vaddr); + } + } + pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; + } + + __flush_tlb_all(); + return save_pgd; +out: + efi_uv1_memmap_phys_epilog(save_pgd); + return NULL; +} + +void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, + u32 type, u64 attribute) +{ + unsigned long last_map_pfn; + + if (type == EFI_MEMORY_MAPPED_IO) + return ioremap(phys_addr, size); + + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); + if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) { + unsigned long top = last_map_pfn << PAGE_SHIFT; + efi_ioremap(top, size - (top - phys_addr), type, attribute); + } + + if (!(attribute & EFI_MEMORY_WB)) + efi_memory_uc((u64)(unsigned long)__va(phys_addr), size); + + return (void __iomem *)__va(phys_addr); +} + +static int __init arch_parse_efi_cmdline(char *str) +{ + if (!str) { + pr_warn("need at least one option\n"); + return -EINVAL; + } + + if (!efi_is_mixed() && parse_option_str(str, "old_map")) + set_bit(EFI_UV1_MEMMAP, &efi.flags); + + return 0; +} +early_param("efi", arch_parse_efi_cmdline); diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index 5bd949da7a4a..ac8eee093f9c 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -215,14 +215,12 @@ static int set_tls_entry(struct task_struct* task, struct user_desc *info, return 0; } -int arch_copy_tls(struct task_struct *new) +int arch_set_tls(struct task_struct *new, unsigned long tls) { struct user_desc info; int idx, ret = -EFAULT; - if (copy_from_user(&info, - (void __user *) UPT_SI(&new->thread.regs.regs), - sizeof(info))) + if (copy_from_user(&info, (void __user *) tls, sizeof(info))) goto out; ret = -EINVAL; diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index 3a621e0d3925..ebd3855d9b13 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -6,14 +6,13 @@ void clear_flushed_tls(struct task_struct *task) { } -int arch_copy_tls(struct task_struct *t) +int arch_set_tls(struct task_struct *t, unsigned long tls) { /* * If CLONE_SETTLS is set, we need to save the thread id - * (which is argument 5, child_tid, of clone) so it can be set - * during context switches. + * so it can be set during context switches. */ - t->thread.arch.fs = t->thread.regs.regs.gp[R8 / sizeof(long)]; + t->thread.arch.fs = tls; return 0; } diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index a04551ee5568..1abe455d926a 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -31,7 +31,7 @@ static efi_system_table_t efi_systab_xen __initdata = { .con_in_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .con_in = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .con_out_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ - .con_out = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ + .con_out = NULL, /* Not used under Xen. */ .stderr_handle = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .stderr = EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */ .runtime = (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR, diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index c8dbee62ec2a..bbba8b17829a 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -67,7 +67,7 @@ #include <asm/linkage.h> #include <asm/page.h> #include <asm/init.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/smp.h> #include <asm/tlb.h> |
